From 5960e46e7d81e15311ab169f0e8b6f4dd033dbd8 Mon Sep 17 00:00:00 2001 From: raulraja Date: Wed, 15 May 2024 19:25:09 +0200 Subject: [PATCH] Progress updating to OpenAI v2. Fails to generate `CreateAssistantRequestToolResourcesFileSearch` --- openai-client/generator/config/api.mustache | 4 +- .../generator/config/openai-api-commit | 2 +- .../generator/config/openai-api.yaml | 12536 +++++++++++----- 3 files changed, 8503 insertions(+), 4039 deletions(-) diff --git a/openai-client/generator/config/api.mustache b/openai-client/generator/config/api.mustache index 026d62207..bc9f2cef9 100644 --- a/openai-client/generator/config/api.mustache +++ b/openai-client/generator/config/api.mustache @@ -94,7 +94,7 @@ interface {{classname}} { {{/operations}} {{#operations}} -fun {{classname}}(client: HttpClient, config: Config): {{classname}} = object : {{classname}} { +fun {{classname}}(client: HttpClient, config: Config): {{apiPackage}}.{{classname}} = object : {{apiPackage}}.{{classname}} { {{#operation}} override suspend fun {{operationId}}({{#allParams}}{{{paramName}}}: {{#isEnum}}{{# isContainer}}kotlin.collections.List<{{enumName}}{{operationIdCamelCase}}>{{/isContainer}}{{^isContainer}}{{enumName}}{{operationIdCamelCase}}{{/isContainer}}{{/isEnum}}{{^isEnum}}{{{dataType}}}{{/isEnum}}{{^required}}?{{/required}},{{/allParams}} configure: HttpRequestBuilder.() -> Unit): {{#returnProperty}}{{#isFile}}HttpResponse{{/isFile}}{{^isFile}}{{{returnType}}}{{^returnType}}Unit{{/returnType}}{{/isFile}}{{/returnProperty}} = client.request { @@ -190,4 +190,4 @@ fun {{classname}}(client: HttpClient, config: Config): {{classname}} = object : {{/vendorExtensions.x-streaming}} {{/operation}} } -{{/operations}} \ No newline at end of file +{{/operations}} diff --git a/openai-client/generator/config/openai-api-commit b/openai-client/generator/config/openai-api-commit index 7965a2453..94b46cf74 100644 --- a/openai-client/generator/config/openai-api-commit +++ b/openai-client/generator/config/openai-api-commit @@ -1 +1 @@ -44306c2f4534144e169721e2ad160e00b6823bc7 +df5699f5c48fe455d9d036198e77fdb637edee29 diff --git a/openai-client/generator/config/openai-api.yaml b/openai-client/generator/config/openai-api.yaml index aa2f96a49..030518faf 100644 --- a/openai-client/generator/config/openai-api.yaml +++ b/openai-client/generator/config/openai-api.yaml @@ -25,6 +25,8 @@ tags: description: Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms. - name: Fine-tuning description: Manage fine-tuning jobs to tailor a model to your specific training data. + - name: Batch + description: Create large batches of API requests to run asynchronously. - name: Files description: Files are used to upload documents that can be used with features like Assistants and Fine-tuning. - name: Images @@ -32,7 +34,7 @@ tags: - name: Models description: List and describe the various models available in the API. - name: Moderations - description: Given a input text, outputs if the model classifies it as violating OpenAI's content policy. + description: Given a input text, outputs if the model classifies it as potentially harmful. paths: # Note: When adding an endpoint, make sure you also add it in the `groups` section, in the end of this file, # under the appropriate group @@ -115,7 +117,7 @@ paths: "id": "chatcmpl-123", "object": "chat.completion", "created": 1677652288, - "model": "gpt-3.5-turbo-0613", + "model": "gpt-3.5-turbo-0125", "system_fingerprint": "fp_44709d6fcb", "choices": [{ "index": 0, @@ -139,14 +141,14 @@ paths: -H "Content-Type: application/json" \ -H "Authorization: Bearer $OPENAI_API_KEY" \ -d '{ - "model": "gpt-4-vision-preview", + "model": "gpt-4-turbo", "messages": [ { "role": "user", "content": [ { "type": "text", - "text": "What’s in this image?" + "text": "What'\''s in this image?" }, { "type": "image_url", @@ -165,12 +167,12 @@ paths: client = OpenAI() response = client.chat.completions.create( - model="gpt-4-vision-preview", + model="gpt-4-turbo", messages=[ { "role": "user", "content": [ - {"type": "text", "text": "What’s in this image?"}, + {"type": "text", "text": "What's in this image?"}, { "type": "image_url", "image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg", @@ -189,12 +191,12 @@ paths: async function main() { const response = await openai.chat.completions.create({ - model: "gpt-4-vision-preview", + model: "gpt-4-turbo", messages: [ { role: "user", content: [ - { type: "text", text: "What’s in this image?" }, + { type: "text", text: "What's in this image?" }, { type: "image_url", image_url: @@ -212,13 +214,13 @@ paths: "id": "chatcmpl-123", "object": "chat.completion", "created": 1677652288, - "model": "gpt-3.5-turbo-0613", + "model": "gpt-3.5-turbo-0125", "system_fingerprint": "fp_44709d6fcb", "choices": [{ "index": 0, "message": { "role": "assistant", - "content": "\n\nHello there, how may I assist you today?", + "content": "\n\nThis image shows a wooden boardwalk extending through a lush green marshland.", }, "logprobs": null, "finish_reason": "stop" @@ -287,19 +289,13 @@ paths: main(); response: &chat_completion_chunk_example | - {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-3.5-turbo-0613", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]} - - {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-3.5-turbo-0613", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{"content":"Hello"},"logprobs":null,"finish_reason":null}]} + {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-3.5-turbo-0125", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]} - {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-3.5-turbo-0613", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{"content":"!"},"logprobs":null,"finish_reason":null}]} + {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-3.5-turbo-0125", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{"content":"Hello"},"logprobs":null,"finish_reason":null}]} .... - {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-3.5-turbo-0613", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{"content":" today"},"logprobs":null,"finish_reason":null}]} - - {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-3.5-turbo-0613", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{"content":"?"},"logprobs":null,"finish_reason":null}]} - - {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-3.5-turbo-0613", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]} + {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-3.5-turbo-0125", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]} - title: Functions request: curl: | @@ -307,11 +303,11 @@ paths: -H "Content-Type: application/json" \ -H "Authorization: Bearer $OPENAI_API_KEY" \ -d '{ - "model": "gpt-3.5-turbo", + "model": "gpt-4-turbo", "messages": [ { "role": "user", - "content": "What is the weather like in Boston?" + "content": "What'\''s the weather like in Boston today?" } ], "tools": [ @@ -401,7 +397,7 @@ paths: ]; const response = await openai.chat.completions.create({ - model: "gpt-3.5-turbo", + model: "gpt-4-turbo", messages: messages, tools: tools, tool_choice: "auto", @@ -416,7 +412,7 @@ paths: "id": "chatcmpl-abc123", "object": "chat.completion", "created": 1699896916, - "model": "gpt-3.5-turbo-0613", + "model": "gpt-3.5-turbo-0125", "choices": [ { "index": 0, @@ -498,7 +494,7 @@ paths: "id": "chatcmpl-123", "object": "chat.completion", "created": 1702685778, - "model": "gpt-3.5-turbo-0613", + "model": "gpt-3.5-turbo-0125", "choices": [ { "index": 0, @@ -1201,47 +1197,174 @@ paths: content: application/json: schema: - $ref: "#/components/schemas/CreateTranscriptionResponse" + oneOf: + - $ref: "#/components/schemas/CreateTranscriptionResponseJson" + - $ref: "#/components/schemas/CreateTranscriptionResponseVerboseJson" x-oaiMeta: name: Create transcription group: audio - returns: The transcribed text. + returns: The [transcription object](/docs/api-reference/audio/json-object) or a [verbose transcription object](/docs/api-reference/audio/verbose-json-object). examples: - request: - curl: | - curl https://api.openai.com/v1/audio/transcriptions \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: multipart/form-data" \ - -F file="@/path/to/file/audio.mp3" \ - -F model="whisper-1" - python: | - from openai import OpenAI - client = OpenAI() + - title: Default + request: + curl: | + curl https://api.openai.com/v1/audio/transcriptions \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: multipart/form-data" \ + -F file="@/path/to/file/audio.mp3" \ + -F model="whisper-1" + python: | + from openai import OpenAI + client = OpenAI() - audio_file = open("speech.mp3", "rb") - transcript = client.audio.transcriptions.create( - model="whisper-1", - file=audio_file - ) - node: | - import fs from "fs"; - import OpenAI from "openai"; + audio_file = open("speech.mp3", "rb") + transcript = client.audio.transcriptions.create( + model="whisper-1", + file=audio_file + ) + node: | + import fs from "fs"; + import OpenAI from "openai"; - const openai = new OpenAI(); + const openai = new OpenAI(); - async function main() { - const transcription = await openai.audio.transcriptions.create({ - file: fs.createReadStream("audio.mp3"), - model: "whisper-1", - }); + async function main() { + const transcription = await openai.audio.transcriptions.create({ + file: fs.createReadStream("audio.mp3"), + model: "whisper-1", + }); - console.log(transcription.text); + console.log(transcription.text); + } + main(); + response: &basic_transcription_response_example | + { + "text": "Imagine the wildest idea that you've ever had, and you're curious about how it might scale to something that's a 100, a 1,000 times bigger. This is a place where you can get to do that." + } + - title: Word timestamps + request: + curl: | + curl https://api.openai.com/v1/audio/transcriptions \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: multipart/form-data" \ + -F file="@/path/to/file/audio.mp3" \ + -F "timestamp_granularities[]=word" \ + -F model="whisper-1" \ + -F response_format="verbose_json" + python: | + from openai import OpenAI + client = OpenAI() + + audio_file = open("speech.mp3", "rb") + transcript = client.audio.transcriptions.create( + file=audio_file, + model="whisper-1", + response_format="verbose_json", + timestamp_granularities=["word"] + ) + + print(transcript.words) + node: | + import fs from "fs"; + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const transcription = await openai.audio.transcriptions.create({ + file: fs.createReadStream("audio.mp3"), + model: "whisper-1", + response_format: "verbose_json", + timestamp_granularities: ["word"] + }); + + console.log(transcription.text); + } + main(); + response: | + { + "task": "transcribe", + "language": "english", + "duration": 8.470000267028809, + "text": "The beach was a popular spot on a hot summer day. People were swimming in the ocean, building sandcastles, and playing beach volleyball.", + "words": [ + { + "word": "The", + "start": 0.0, + "end": 0.23999999463558197 + }, + ... + { + "word": "volleyball", + "start": 7.400000095367432, + "end": 7.900000095367432 + } + ] + } + - title: Segment timestamps + request: + curl: | + curl https://api.openai.com/v1/audio/transcriptions \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: multipart/form-data" \ + -F file="@/path/to/file/audio.mp3" \ + -F "timestamp_granularities[]=segment" \ + -F model="whisper-1" \ + -F response_format="verbose_json" + python: | + from openai import OpenAI + client = OpenAI() + + audio_file = open("speech.mp3", "rb") + transcript = client.audio.transcriptions.create( + file=audio_file, + model="whisper-1", + response_format="verbose_json", + timestamp_granularities=["segment"] + ) + + print(transcript.words) + node: | + import fs from "fs"; + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const transcription = await openai.audio.transcriptions.create({ + file: fs.createReadStream("audio.mp3"), + model: "whisper-1", + response_format: "verbose_json", + timestamp_granularities: ["segment"] + }); + + console.log(transcription.text); + } + main(); + response: &verbose_transcription_response_example | + { + "task": "transcribe", + "language": "english", + "duration": 8.470000267028809, + "text": "The beach was a popular spot on a hot summer day. People were swimming in the ocean, building sandcastles, and playing beach volleyball.", + "segments": [ + { + "id": 0, + "seek": 0, + "start": 0.0, + "end": 3.319999933242798, + "text": " The beach was a popular spot on a hot summer day.", + "tokens": [ + 50364, 440, 7534, 390, 257, 3743, 4008, 322, 257, 2368, 4266, 786, 13, 50530 + ], + "temperature": 0.0, + "avg_logprob": -0.2860786020755768, + "compression_ratio": 1.2363636493682861, + "no_speech_prob": 0.00985979475080967 + }, + ... + ] } - main(); - response: | - { - "text": "Imagine the wildest idea that you've ever had, and you're curious about how it might scale to something that's a 100, a 1,000 times bigger. This is a place where you can get to do that." - } /audio/translations: post: operationId: createTranslation @@ -1260,7 +1383,9 @@ paths: content: application/json: schema: - $ref: "#/components/schemas/CreateTranslationResponse" + oneOf: + - $ref: "#/components/schemas/CreateTranslationResponseJson" + - $ref: "#/components/schemas/CreateTranslationResponseVerboseJson" x-oaiMeta: name: Create translation group: audio @@ -1377,9 +1502,13 @@ paths: tags: - Files summary: | - Upload a file that can be used across various endpoints. The size of all the files uploaded by one organization can be up to 100 GB. + Upload a file that can be used across various endpoints. Individual files can be up to 512 MB, and the size of all files uploaded by one organization can be up to 100 GB. + + The Assistants API supports files up to 2 million tokens and of specific file types. See the [Assistants Tools guide](/docs/assistants/tools) for details. + + The Fine-tuning API only supports `.jsonl` files. - The size of individual files can be a maximum of 512 MB or 2 million tokens for Assistants. See the [Assistants Tools guide](/docs/assistants/tools) to learn more about the types of files supported. The Fine-tuning API only supports `.jsonl` files. + The Batch API only supports `.jsonl` files up to 100 MB in size. Please [contact us](https://help.openai.com/) if you need to increase these storage limits. requestBody: @@ -1579,14 +1708,14 @@ paths: from openai import OpenAI client = OpenAI() - content = client.files.retrieve_content("file-abc123") + content = client.files.content("file-abc123") node.js: | import OpenAI from "openai"; const openai = new OpenAI(); async function main() { - const file = await openai.files.retrieveContent("file-abc123"); + const file = await openai.files.content("file-abc123"); console.log(file); } @@ -1658,7 +1787,7 @@ paths: { "object": "fine_tuning.job", "id": "ftjob-abc123", - "model": "gpt-3.5-turbo-0613", + "model": "gpt-3.5-turbo-0125", "created_at": 1614807352, "fine_tuned_model": null, "organization_id": "org-123", @@ -1711,7 +1840,7 @@ paths: { "object": "fine_tuning.job", "id": "ftjob-abc123", - "model": "gpt-3.5-turbo-0613", + "model": "gpt-3.5-turbo-0125", "created_at": 1614807352, "fine_tuned_model": null, "organization_id": "org-123", @@ -1760,7 +1889,7 @@ paths: { "object": "fine_tuning.job", "id": "ftjob-abc123", - "model": "gpt-3.5-turbo-0613", + "model": "gpt-3.5-turbo-0125", "created_at": 1614807352, "fine_tuned_model": null, "organization_id": "org-123", @@ -1769,6 +1898,52 @@ paths: "validation_file": "file-abc123", "training_file": "file-abc123", } + - title: W&B Integration + request: + curl: | + curl https://api.openai.com/v1/fine_tuning/jobs \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "training_file": "file-abc123", + "validation_file": "file-abc123", + "model": "gpt-3.5-turbo", + "integrations": [ + { + "type": "wandb", + "wandb": { + "project": "my-wandb-project", + "name": "ft-run-display-name" + "tags": [ + "first-experiment", "v2" + ] + } + } + ] + }' + response: | + { + "object": "fine_tuning.job", + "id": "ftjob-abc123", + "model": "gpt-3.5-turbo-0125", + "created_at": 1614807352, + "fine_tuned_model": null, + "organization_id": "org-123", + "result_files": [], + "status": "queued", + "validation_file": "file-abc123", + "training_file": "file-abc123", + "integrations": [ + { + "type": "wandb", + "wandb": { + "project": "my-wandb-project", + "entity": None, + "run_id": "ftjob-abc123" + } + } + ] + } get: operationId: listPaginatedFineTuningJobs tags: @@ -1909,8 +2084,13 @@ paths: "training_file": "file-abc123", "hyperparameters": { "n_epochs": 4, + "batch_size": 1, + "learning_rate_multiplier": 1.0 }, - "trained_tokens": 5768 + "trained_tokens": 5768, + "integrations": [], + "seed": 0, + "estimated_finish": 0 } /fine_tuning/jobs/{fine_tuning_job_id}/events: get: @@ -2056,7 +2236,7 @@ paths: { "object": "fine_tuning.job", "id": "ftjob-abc123", - "model": "gpt-3.5-turbo-0613", + "model": "gpt-3.5-turbo-0125", "created_at": 1689376978, "fine_tuned_model": null, "organization_id": "org-123", @@ -2068,6 +2248,84 @@ paths: "validation_file": "file-abc123", "training_file": "file-abc123" } + /fine_tuning/jobs/{fine_tuning_job_id}/checkpoints: + get: + operationId: listFineTuningJobCheckpoints + tags: + - Fine-tuning + summary: | + List checkpoints for a fine-tuning job. + parameters: + - in: path + name: fine_tuning_job_id + required: true + schema: + type: string + example: ft-AF1WoRqd3aJAHsqc9NY7iL8F + description: | + The ID of the fine-tuning job to get checkpoints for. + - name: after + in: query + description: Identifier for the last checkpoint ID from the previous pagination request. + required: false + schema: + type: string + - name: limit + in: query + description: Number of checkpoints to retrieve. + required: false + schema: + type: integer + default: 10 + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListFineTuningJobCheckpointsResponse" + x-oaiMeta: + name: List fine-tuning checkpoints + group: fine-tuning + returns: A list of fine-tuning [checkpoint objects](/docs/api-reference/fine-tuning/checkpoint-object) for a fine-tuning job. + examples: + request: + curl: | + curl https://api.openai.com/v1/fine_tuning/jobs/ftjob-abc123/checkpoints \ + -H "Authorization: Bearer $OPENAI_API_KEY" + response: | + { + "object": "list" + "data": [ + { + "object": "fine_tuning.job.checkpoint", + "id": "ftckpt_zc4Q7MP6XxulcVzj4MZdwsAB", + "created_at": 1519129973, + "fine_tuned_model_checkpoint": "ft:gpt-3.5-turbo-0125:my-org:custom-suffix:96olL566:ckpt-step-2000", + "metrics": { + "full_valid_loss": 0.134, + "full_valid_mean_token_accuracy": 0.874 + }, + "fine_tuning_job_id": "ftjob-abc123", + "step_number": 2000, + }, + { + "object": "fine_tuning.job.checkpoint", + "id": "ftckpt_enQCFmOTGj3syEpYVhBRLTSy", + "created_at": 1519129833, + "fine_tuned_model_checkpoint": "ft:gpt-3.5-turbo-0125:my-org:custom-suffix:7q8mpxmy:ckpt-step-1000", + "metrics": { + "full_valid_loss": 0.167, + "full_valid_mean_token_accuracy": 0.781 + }, + "fine_tuning_job_id": "ftjob-abc123", + "step_number": 1000, + }, + ], + "first_id": "ftckpt_zc4Q7MP6XxulcVzj4MZdwsAB", + "last_id": "ftckpt_enQCFmOTGj3syEpYVhBRLTSy", + "has_more": true + } /models: get: @@ -2176,7 +2434,7 @@ paths: const openai = new OpenAI(); async function main() { - const model = await openai.models.retrieve("gpt-3.5-turbo"); + const model = await openai.models.retrieve("VAR_model_id"); console.log(model); } @@ -2247,7 +2505,7 @@ paths: operationId: createModeration tags: - Moderations - summary: Classifies if text violates OpenAI's Content Policy + summary: Classifies if text is potentially harmful. requestBody: required: true content: @@ -2278,7 +2536,8 @@ paths: from openai import OpenAI client = OpenAI() - client.moderations.create(input="I want to kill them.") + moderation = client.moderations.create(input="I want to kill them.") + print(moderation) node.js: | import OpenAI from "openai"; @@ -2380,7 +2639,7 @@ paths: curl "https://api.openai.com/v1/assistants?order=desc&limit=20" \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v1" + -H "OpenAI-Beta: assistants=v2" python: | from openai import OpenAI client = OpenAI() @@ -2415,11 +2674,14 @@ paths: "created_at": 1698982736, "name": "Coding Tutor", "description": null, - "model": "gpt-4", + "model": "gpt-4-turbo", "instructions": "You are a helpful assistant designed to make me better at coding!", "tools": [], - "file_ids": [], - "metadata": {} + "tool_resources": {}, + "metadata": {}, + "top_p": 1.0, + "temperature": 1.0, + "response_format": "auto" }, { "id": "asst_abc456", @@ -2427,11 +2689,14 @@ paths: "created_at": 1698982718, "name": "My Assistant", "description": null, - "model": "gpt-4", + "model": "gpt-4-turbo", "instructions": "You are a helpful assistant designed to make me better at coding!", "tools": [], - "file_ids": [], - "metadata": {} + "tool_resources": {}, + "metadata": {}, + "top_p": 1.0, + "temperature": 1.0, + "response_format": "auto" }, { "id": "asst_abc789", @@ -2439,11 +2704,14 @@ paths: "created_at": 1698982643, "name": null, "description": null, - "model": "gpt-4", + "model": "gpt-4-turbo", "instructions": null, "tools": [], - "file_ids": [], - "metadata": {} + "tool_resources": {}, + "metadata": {}, + "top_p": 1.0, + "temperature": 1.0, + "response_format": "auto" } ], "first_id": "asst_abc123", @@ -2480,12 +2748,12 @@ paths: curl "https://api.openai.com/v1/assistants" \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v1" \ + -H "OpenAI-Beta: assistants=v2" \ -d '{ "instructions": "You are a personal math tutor. When asked a question, write and run Python code to answer the question.", "name": "Math Tutor", "tools": [{"type": "code_interpreter"}], - "model": "gpt-4" + "model": "gpt-4-turbo" }' python: | @@ -2496,7 +2764,7 @@ paths: instructions="You are a personal math tutor. When asked a question, write and run Python code to answer the question.", name="Math Tutor", tools=[{"type": "code_interpreter"}], - model="gpt-4", + model="gpt-4-turbo", ) print(my_assistant) node.js: |- @@ -2510,7 +2778,7 @@ paths: "You are a personal math tutor. When asked a question, write and run Python code to answer the question.", name: "Math Tutor", tools: [{ type: "code_interpreter" }], - model: "gpt-4", + model: "gpt-4-turbo", }); console.log(myAssistant); @@ -2524,15 +2792,17 @@ paths: "created_at": 1698984975, "name": "Math Tutor", "description": null, - "model": "gpt-4", + "model": "gpt-4-turbo", "instructions": "You are a personal math tutor. When asked a question, write and run Python code to answer the question.", "tools": [ { "type": "code_interpreter" } ], - "file_ids": [], - "metadata": {} + "metadata": {}, + "top_p": 1.0, + "temperature": 1.0, + "response_format": "auto" } - title: Files request: @@ -2540,12 +2810,12 @@ paths: curl https://api.openai.com/v1/assistants \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v1" \ + -H "OpenAI-Beta: assistants=v2" \ -d '{ "instructions": "You are an HR bot, and you have access to files to answer employee questions about company policies.", - "tools": [{"type": "retrieval"}], - "model": "gpt-4", - "file_ids": ["file-abc123"] + "tools": [{"type": "file_search"}], + "tool_resources": {"file_search": {"vector_store_ids": ["vs_123"]}}, + "model": "gpt-4-turbo" }' python: | from openai import OpenAI @@ -2554,9 +2824,9 @@ paths: my_assistant = client.beta.assistants.create( instructions="You are an HR bot, and you have access to files to answer employee questions about company policies.", name="HR Helper", - tools=[{"type": "retrieval"}], - model="gpt-4", - file_ids=["file-abc123"], + tools=[{"type": "file_search"}], + tool_resources={"file_search": {"vector_store_ids": ["vs_123"]}}, + model="gpt-4-turbo" ) print(my_assistant) node.js: |- @@ -2569,9 +2839,13 @@ paths: instructions: "You are an HR bot, and you have access to files to answer employee questions about company policies.", name: "HR Helper", - tools: [{ type: "retrieval" }], - model: "gpt-4", - file_ids: ["file-abc123"], + tools: [{ type: "file_search" }], + tool_resources: { + file_search: { + vector_store_ids: ["vs_123"] + } + }, + model: "gpt-4-turbo" }); console.log(myAssistant); @@ -2585,17 +2859,22 @@ paths: "created_at": 1699009403, "name": "HR Helper", "description": null, - "model": "gpt-4", + "model": "gpt-4-turbo", "instructions": "You are an HR bot, and you have access to files to answer employee questions about company policies.", "tools": [ { - "type": "retrieval" + "type": "file_search" } ], - "file_ids": [ - "file-abc123" - ], - "metadata": {} + "tool_resources": { + "file_search": { + "vector_store_ids": ["vs_123"] + } + }, + "metadata": {}, + "top_p": 1.0, + "temperature": 1.0, + "response_format": "auto" } /assistants/{assistant_id}: @@ -2629,7 +2908,7 @@ paths: curl https://api.openai.com/v1/assistants/asst_abc123 \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v1" + -H "OpenAI-Beta: assistants=v2" python: | from openai import OpenAI client = OpenAI() @@ -2657,17 +2936,17 @@ paths: "created_at": 1699009709, "name": "HR Helper", "description": null, - "model": "gpt-4", + "model": "gpt-4-turbo", "instructions": "You are an HR bot, and you have access to files to answer employee questions about company policies.", "tools": [ { - "type": "retrieval" + "type": "file_search" } ], - "file_ids": [ - "file-abc123" - ], - "metadata": {} + "metadata": {}, + "top_p": 1.0, + "temperature": 1.0, + "response_format": "auto" } post: operationId: modifyAssistant @@ -2705,12 +2984,11 @@ paths: curl https://api.openai.com/v1/assistants/asst_abc123 \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v1" \ + -H "OpenAI-Beta: assistants=v2" \ -d '{ "instructions": "You are an HR bot, and you have access to files to answer employee questions about company policies. Always response with info from either of the files.", - "tools": [{"type": "retrieval"}], - "model": "gpt-4", - "file_ids": ["file-abc123", "file-abc456"] + "tools": [{"type": "file_search"}], + "model": "gpt-4-turbo" }' python: | from openai import OpenAI @@ -2720,9 +2998,8 @@ paths: "asst_abc123", instructions="You are an HR bot, and you have access to files to answer employee questions about company policies. Always response with info from either of the files.", name="HR Helper", - tools=[{"type": "retrieval"}], - model="gpt-4", - file_ids=["file-abc123", "file-abc456"], + tools=[{"type": "file_search"}], + model="gpt-4-turbo" ) print(my_updated_assistant) @@ -2738,12 +3015,8 @@ paths: instructions: "You are an HR bot, and you have access to files to answer employee questions about company policies. Always response with info from either of the files.", name: "HR Helper", - tools: [{ type: "retrieval" }], - model: "gpt-4", - file_ids: [ - "file-abc123", - "file-abc456", - ], + tools: [{ type: "file_search" }], + model: "gpt-4-turbo" } ); @@ -2753,23 +3026,27 @@ paths: main(); response: | { - "id": "asst_abc123", + "id": "asst_123", "object": "assistant", "created_at": 1699009709, "name": "HR Helper", "description": null, - "model": "gpt-4", + "model": "gpt-4-turbo", "instructions": "You are an HR bot, and you have access to files to answer employee questions about company policies. Always response with info from either of the files.", "tools": [ { - "type": "retrieval" + "type": "file_search" } ], - "file_ids": [ - "file-abc123", - "file-abc456" - ], - "metadata": {} + "tool_resources": { + "file_search": { + "vector_store_ids": [] + } + }, + "metadata": {}, + "top_p": 1.0, + "temperature": 1.0, + "response_format": "auto" } delete: operationId: deleteAssistant @@ -2801,7 +3078,7 @@ paths: curl https://api.openai.com/v1/assistants/asst_abc123 \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v1" \ + -H "OpenAI-Beta: assistants=v2" \ -X DELETE python: | from openai import OpenAI @@ -2857,7 +3134,7 @@ paths: curl https://api.openai.com/v1/threads \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v1" \ + -H "OpenAI-Beta: assistants=v2" \ -d '' python: | from openai import OpenAI @@ -2882,7 +3159,8 @@ paths: "id": "thread_abc123", "object": "thread", "created_at": 1699012949, - "metadata": {} + "metadata": {}, + "tool_resources": {} } - title: Messages request: @@ -2890,12 +3168,11 @@ paths: curl https://api.openai.com/v1/threads \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v1" \ + -H "OpenAI-Beta: assistants=v2" \ -d '{ "messages": [{ "role": "user", - "content": "Hello, what is AI?", - "file_ids": ["file-abc123"] + "content": "Hello, what is AI?" }, { "role": "user", "content": "How does AI work? Explain it in simple terms." @@ -2909,8 +3186,7 @@ paths: messages=[ { "role": "user", - "content": "Hello, what is AI?", - "file_ids": ["file-abc123"], + "content": "Hello, what is AI?" }, { "role": "user", @@ -2930,8 +3206,7 @@ paths: messages: [ { role: "user", - content: "Hello, what is AI?", - file_ids: ["file-abc123"], + content: "Hello, what is AI?" }, { role: "user", @@ -2946,10 +3221,11 @@ paths: main(); response: | { - id: 'thread_abc123', - object: 'thread', - created_at: 1699014083, - metadata: {} + "id": "thread_abc123", + "object": "thread", + "created_at": 1699014083, + "metadata": {}, + "tool_resources": {} } /threads/{thread_id}: @@ -2983,7 +3259,7 @@ paths: curl https://api.openai.com/v1/threads/thread_abc123 \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v1" + -H "OpenAI-Beta: assistants=v2" python: | from openai import OpenAI client = OpenAI() @@ -3009,7 +3285,12 @@ paths: "id": "thread_abc123", "object": "thread", "created_at": 1699014083, - "metadata": {} + "metadata": {}, + "tool_resources": { + "code_interpreter": { + "file_ids": [] + } + } } post: operationId: modifyThread @@ -3047,7 +3328,7 @@ paths: curl https://api.openai.com/v1/threads/thread_abc123 \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v1" \ + -H "OpenAI-Beta: assistants=v2" \ -d '{ "metadata": { "modified": "true", @@ -3091,7 +3372,8 @@ paths: "metadata": { "modified": "true", "user": "abc123" - } + }, + "tool_resources": {} } delete: operationId: deleteThread @@ -3123,7 +3405,7 @@ paths: curl https://api.openai.com/v1/threads/thread_abc123 \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v1" \ + -H "OpenAI-Beta: assistants=v2" \ -X DELETE python: | from openai import OpenAI @@ -3186,6 +3468,12 @@ paths: description: *pagination_before_param_description schema: type: string + - name: run_id + in: query + description: | + Filter messages by the run ID that generated them. + schema: + type: string responses: "200": description: OK @@ -3204,7 +3492,7 @@ paths: curl https://api.openai.com/v1/threads/thread_abc123/messages \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v1" + -H "OpenAI-Beta: assistants=v2" python: | from openai import OpenAI client = OpenAI() @@ -3233,7 +3521,9 @@ paths: "id": "msg_abc123", "object": "thread.message", "created_at": 1699016383, + "assistant_id": null, "thread_id": "thread_abc123", + "run_id": null, "role": "user", "content": [ { @@ -3244,16 +3534,16 @@ paths: } } ], - "file_ids": [], - "assistant_id": null, - "run_id": null, + "attachments": [], "metadata": {} }, { "id": "msg_abc456", "object": "thread.message", "created_at": 1699016383, + "assistant_id": null, "thread_id": "thread_abc123", + "run_id": null, "role": "user", "content": [ { @@ -3264,11 +3554,7 @@ paths: } } ], - "file_ids": [ - "file-abc123" - ], - "assistant_id": null, - "run_id": null, + "attachments": [], "metadata": {} } ], @@ -3312,7 +3598,7 @@ paths: curl https://api.openai.com/v1/threads/thread_abc123/messages \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v1" \ + -H "OpenAI-Beta: assistants=v2" \ -d '{ "role": "user", "content": "How does AI work? Explain it in simple terms." @@ -3346,8 +3632,10 @@ paths: { "id": "msg_abc123", "object": "thread.message", - "created_at": 1699017614, + "created_at": 1713226573, + "assistant_id": null, "thread_id": "thread_abc123", + "run_id": null, "role": "user", "content": [ { @@ -3358,9 +3646,7 @@ paths: } } ], - "file_ids": [], - "assistant_id": null, - "run_id": null, + "attachments": [], "metadata": {} } @@ -3401,7 +3687,7 @@ paths: curl https://api.openai.com/v1/threads/thread_abc123/messages/msg_abc123 \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v1" + -H "OpenAI-Beta: assistants=v2" python: | from openai import OpenAI client = OpenAI() @@ -3431,7 +3717,9 @@ paths: "id": "msg_abc123", "object": "thread.message", "created_at": 1699017614, + "assistant_id": null, "thread_id": "thread_abc123", + "run_id": null, "role": "user", "content": [ { @@ -3442,9 +3730,7 @@ paths: } } ], - "file_ids": [], - "assistant_id": null, - "run_id": null, + "attachments": [], "metadata": {} } post: @@ -3489,7 +3775,7 @@ paths: curl https://api.openai.com/v1/threads/thread_abc123/messages/msg_abc123 \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v1" \ + -H "OpenAI-Beta: assistants=v2" \ -d '{ "metadata": { "modified": "true", @@ -3530,7 +3816,9 @@ paths: "id": "msg_abc123", "object": "thread.message", "created_at": 1699017614, + "assistant_id": null, "thread_id": "thread_abc123", + "run_id": null, "role": "user", "content": [ { @@ -3542,273 +3830,90 @@ paths: } ], "file_ids": [], - "assistant_id": null, - "run_id": null, "metadata": { "modified": "true", "user": "abc123" } } - - /threads/runs: - post: - operationId: createThreadAndRun + delete: + operationId: deleteMessage tags: - Assistants - summary: Create a thread and run it in one request. - requestBody: - required: true - content: - application/json: - schema: - $ref: "#/components/schemas/CreateThreadAndRunRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/RunObject" - x-oaiMeta: - name: Create thread and run - group: threads - beta: true - returns: A [run](/docs/api-reference/runs/object) object. - examples: - request: - curl: | - curl https://api.openai.com/v1/threads/runs \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v1" \ - -d '{ - "assistant_id": "asst_abc123", - "thread": { - "messages": [ - {"role": "user", "content": "Explain deep learning to a 5 year old."} - ] - } - }' - python: | - from openai import OpenAI - client = OpenAI() - - run = client.beta.threads.create_and_run( - assistant_id="asst_abc123", - thread={ - "messages": [ - {"role": "user", "content": "Explain deep learning to a 5 year old."} - ] - } - ) - node.js: | - import OpenAI from "openai"; - - const openai = new OpenAI(); - - async function main() { - const run = await openai.beta.threads.createAndRun({ - assistant_id: "asst_abc123", - thread: { - messages: [ - { role: "user", content: "Explain deep learning to a 5 year old." }, - ], - }, - }); - - console.log(run); - } - - main(); - response: | - { - "id": "run_abc123", - "object": "thread.run", - "created_at": 1699076792, - "assistant_id": "asst_abc123", - "thread_id": "thread_abc123", - "status": "queued", - "started_at": null, - "expires_at": 1699077392, - "cancelled_at": null, - "failed_at": null, - "completed_at": null, - "last_error": null, - "model": "gpt-4", - "instructions": "You are a helpful assistant.", - "tools": [], - "file_ids": [], - "metadata": {}, - "usage": null - } - - /threads/{thread_id}/runs: - get: - operationId: listRuns - tags: - - Assistants - summary: Returns a list of runs belonging to a thread. + summary: Deletes a message. parameters: - - name: thread_id - in: path + - in: path + name: thread_id required: true schema: type: string - description: The ID of the thread the run belongs to. - - name: limit - in: query - description: *pagination_limit_param_description - required: false - schema: - type: integer - default: 20 - - name: order - in: query - description: *pagination_order_param_description - schema: - type: string - default: desc - enum: ["asc", "desc"] - - name: after - in: query - description: *pagination_after_param_description - schema: - type: string - - name: before - in: query - description: *pagination_before_param_description + description: The ID of the thread to which this message belongs. + - in: path + name: message_id + required: true schema: type: string + description: The ID of the message to delete. responses: "200": description: OK content: application/json: schema: - $ref: "#/components/schemas/ListRunsResponse" + $ref: "#/components/schemas/DeleteMessageResponse" x-oaiMeta: - name: List runs + name: Delete message group: threads beta: true - returns: A list of [run](/docs/api-reference/runs/object) objects. + returns: Deletion status examples: request: curl: | - curl https://api.openai.com/v1/threads/thread_abc123/runs \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ + curl -X DELETE https://api.openai.com/v1/threads/thread_abc123/messages/msg_abc123 \ -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v1" + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" python: | from openai import OpenAI client = OpenAI() - runs = client.beta.threads.runs.list( - "thread_abc123" + deleted_message = client.beta.threads.messages.delete( + message_id="msg_abc12", + thread_id="thread_abc123", ) - print(runs) - node.js: | + print(deleted_message) + node.js: |- import OpenAI from "openai"; const openai = new OpenAI(); async function main() { - const runs = await openai.beta.threads.runs.list( - "thread_abc123" + const deletedMessage = await openai.beta.threads.messages.del( + "thread_abc123", + "msg_abc123" ); - console.log(runs); + console.log(deletedMessage); } - - main(); response: | { - "object": "list", - "data": [ - { - "id": "run_abc123", - "object": "thread.run", - "created_at": 1699075072, - "assistant_id": "asst_abc123", - "thread_id": "thread_abc123", - "status": "completed", - "started_at": 1699075072, - "expires_at": null, - "cancelled_at": null, - "failed_at": null, - "completed_at": 1699075073, - "last_error": null, - "model": "gpt-3.5-turbo", - "instructions": null, - "tools": [ - { - "type": "code_interpreter" - } - ], - "file_ids": [ - "file-abc123", - "file-abc456" - ], - "metadata": {}, - "usage": { - "prompt_tokens": 123, - "completion_tokens": 456, - "total_tokens": 579 - } - }, - { - "id": "run_abc456", - "object": "thread.run", - "created_at": 1699063290, - "assistant_id": "asst_abc123", - "thread_id": "thread_abc123", - "status": "completed", - "started_at": 1699063290, - "expires_at": null, - "cancelled_at": null, - "failed_at": null, - "completed_at": 1699063291, - "last_error": null, - "model": "gpt-3.5-turbo", - "instructions": null, - "tools": [ - { - "type": "code_interpreter" - } - ], - "file_ids": [ - "file-abc123", - "file-abc456" - ], - "metadata": {}, - "usage": { - "prompt_tokens": 123, - "completion_tokens": 456, - "total_tokens": 579 - } - } - ], - "first_id": "run_abc123", - "last_id": "run_abc456", - "has_more": false + "id": "msg_abc123", + "object": "thread.message.deleted", + "deleted": true } + + + /threads/runs: post: - operationId: createRun + operationId: createThreadAndRun tags: - Assistants - summary: Create a run. - parameters: - - in: path - name: thread_id - required: true - schema: - type: string - description: The ID of the thread to run. + summary: Create a thread and run it in one request. requestBody: required: true content: application/json: schema: - $ref: "#/components/schemas/CreateRunRequest" + $ref: "#/components/schemas/CreateThreadAndRunRequest" responses: "200": description: OK @@ -3817,190 +3922,556 @@ paths: schema: $ref: "#/components/schemas/RunObject" x-oaiMeta: - name: Create run + name: Create thread and run group: threads beta: true returns: A [run](/docs/api-reference/runs/object) object. examples: - request: - curl: | - curl https://api.openai.com/v1/threads/thread_abc123/runs \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v1" \ - -d '{ - "assistant_id": "asst_abc123" - }' - python: | - from openai import OpenAI - client = OpenAI() + - title: Default + request: + curl: | + curl https://api.openai.com/v1/threads/runs \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "assistant_id": "asst_abc123", + "thread": { + "messages": [ + {"role": "user", "content": "Explain deep learning to a 5 year old."} + ] + } + }' + python: | + from openai import OpenAI + client = OpenAI() - run = client.beta.threads.runs.create( - thread_id="thread_abc123", - assistant_id="asst_abc123" - ) - print(run) - node.js: | - import OpenAI from "openai"; + run = client.beta.threads.create_and_run( + assistant_id="asst_abc123", + thread={ + "messages": [ + {"role": "user", "content": "Explain deep learning to a 5 year old."} + ] + } + ) - const openai = new OpenAI(); + print(run) + node.js: | + import OpenAI from "openai"; - async function main() { - const run = await openai.beta.threads.runs.create( - "thread_abc123", - { assistant_id: "asst_abc123" } - ); + const openai = new OpenAI(); - console.log(run); - } + async function main() { + const run = await openai.beta.threads.createAndRun({ + assistant_id: "asst_abc123", + thread: { + messages: [ + { role: "user", content: "Explain deep learning to a 5 year old." }, + ], + }, + }); - main(); - response: &run_object_example | - { - "id": "run_abc123", - "object": "thread.run", - "created_at": 1699063290, - "assistant_id": "asst_abc123", - "thread_id": "thread_abc123", - "status": "queued", - "started_at": 1699063290, - "expires_at": null, - "cancelled_at": null, - "failed_at": null, - "completed_at": 1699063291, - "last_error": null, - "model": "gpt-4", - "instructions": null, - "tools": [ - { - "type": "code_interpreter" + console.log(run); } - ], - "file_ids": [ - "file-abc123", - "file-abc456" - ], - "metadata": {}, - "usage": null - } - /threads/{thread_id}/runs/{run_id}: + main(); + response: | + { + "id": "run_abc123", + "object": "thread.run", + "created_at": 1699076792, + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "status": "queued", + "started_at": null, + "expires_at": 1699077392, + "cancelled_at": null, + "failed_at": null, + "completed_at": null, + "required_action": null, + "last_error": null, + "model": "gpt-4-turbo", + "instructions": "You are a helpful assistant.", + "tools": [], + "tool_resources": {}, + "metadata": {}, + "temperature": 1.0, + "top_p": 1.0, + "max_completion_tokens": null, + "max_prompt_tokens": null, + "truncation_strategy": { + "type": "auto", + "last_messages": null + }, + "incomplete_details": null, + "usage": null, + "response_format": "auto", + "tool_choice": "auto" + } + + - title: Streaming + request: + curl: | + curl https://api.openai.com/v1/threads/runs \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "assistant_id": "asst_123", + "thread": { + "messages": [ + {"role": "user", "content": "Hello"} + ] + }, + "stream": true + }' + python: | + from openai import OpenAI + client = OpenAI() + + stream = client.beta.threads.create_and_run( + assistant_id="asst_123", + thread={ + "messages": [ + {"role": "user", "content": "Hello"} + ] + }, + stream=True + ) + + for event in stream: + print(event) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const stream = await openai.beta.threads.createAndRun({ + assistant_id: "asst_123", + thread: { + messages: [ + { role: "user", content: "Hello" }, + ], + }, + stream: true + }); + + for await (const event of stream) { + console.log(event); + } + } + + main(); + response: | + event: thread.created + data: {"id":"thread_123","object":"thread","created_at":1710348075,"metadata":{}} + + event: thread.run.created + data: {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710348675,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[],"tool_resources":{},"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto"} + + event: thread.run.queued + data: {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710348675,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[],"tool_resources":{},"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto"} + + event: thread.run.in_progress + data: {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"in_progress","started_at":null,"expires_at":1710348675,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[],"tool_resources":{},"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto"} + + event: thread.run.step.created + data: {"id":"step_001","object":"thread.run.step","created_at":1710348076,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710348675,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":null} + + event: thread.run.step.in_progress + data: {"id":"step_001","object":"thread.run.step","created_at":1710348076,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710348675,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":null} + + event: thread.message.created + data: {"id":"msg_001","object":"thread.message","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[], "metadata":{}} + + event: thread.message.in_progress + data: {"id":"msg_001","object":"thread.message","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[], "metadata":{}} + + event: thread.message.delta + data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"Hello","annotations":[]}}]}} + + ... + + event: thread.message.delta + data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":" today"}}]}} + + event: thread.message.delta + data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"?"}}]}} + + event: thread.message.completed + data: {"id":"msg_001","object":"thread.message","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"completed","incomplete_details":null,"incomplete_at":null,"completed_at":1710348077,"role":"assistant","content":[{"type":"text","text":{"value":"Hello! How can I assist you today?","annotations":[]}}], "metadata":{}} + + event: thread.run.step.completed + data: {"id":"step_001","object":"thread.run.step","created_at":1710348076,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"completed","cancelled_at":null,"completed_at":1710348077,"expires_at":1710348675,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":{"prompt_tokens":20,"completion_tokens":11,"total_tokens":31}} + + event: thread.run.completed + {"id":"run_123","object":"thread.run","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","status":"completed","started_at":1713226836,"expires_at":null,"cancelled_at":null,"failed_at":null,"completed_at":1713226837,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":{"prompt_tokens":345,"completion_tokens":11,"total_tokens":356},"response_format":"auto","tool_choice":"auto"} + + event: done + data: [DONE] + + - title: Streaming with Functions + request: + curl: | + curl https://api.openai.com/v1/threads/runs \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "assistant_id": "asst_abc123", + "thread": { + "messages": [ + {"role": "user", "content": "What is the weather like in San Francisco?"} + ] + }, + "tools": [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA" + }, + "unit": { + "type": "string", + "enum": ["celsius", "fahrenheit"] + } + }, + "required": ["location"] + } + } + } + ], + "stream": true + }' + python: | + from openai import OpenAI + client = OpenAI() + + tools = [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA", + }, + "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}, + }, + "required": ["location"], + }, + } + } + ] + + stream = client.beta.threads.create_and_run( + thread={ + "messages": [ + {"role": "user", "content": "What is the weather like in San Francisco?"} + ] + }, + assistant_id="asst_abc123", + tools=tools, + stream=True + ) + + for event in stream: + print(event) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + const tools = [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA", + }, + "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}, + }, + "required": ["location"], + }, + } + } + ]; + + async function main() { + const stream = await openai.beta.threads.createAndRun({ + assistant_id: "asst_123", + thread: { + messages: [ + { role: "user", content: "What is the weather like in San Francisco?" }, + ], + }, + tools: tools, + stream: true + }); + + for await (const event of stream) { + console.log(event); + } + } + + main(); + response: | + event: thread.created + data: {"id":"thread_123","object":"thread","created_at":1710351818,"metadata":{}} + + event: thread.run.created + data: {"id":"run_123","object":"thread.run","created_at":1710351818,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710352418,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto"}} + + event: thread.run.queued + data: {"id":"run_123","object":"thread.run","created_at":1710351818,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710352418,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto"}} + + event: thread.run.in_progress + data: {"id":"run_123","object":"thread.run","created_at":1710351818,"assistant_id":"asst_123","thread_id":"thread_123","status":"in_progress","started_at":1710351818,"expires_at":1710352418,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto"}} + + event: thread.run.step.created + data: {"id":"step_001","object":"thread.run.step","created_at":1710351819,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"tool_calls","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710352418,"failed_at":null,"last_error":null,"step_details":{"type":"tool_calls","tool_calls":[]},"usage":null} + + event: thread.run.step.in_progress + data: {"id":"step_001","object":"thread.run.step","created_at":1710351819,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"tool_calls","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710352418,"failed_at":null,"last_error":null,"step_details":{"type":"tool_calls","tool_calls":[]},"usage":null} + + event: thread.run.step.delta + data: {"id":"step_001","object":"thread.run.step.delta","delta":{"step_details":{"type":"tool_calls","tool_calls":[{"index":0,"id":"call_XXNp8YGaFrjrSjgqxtC8JJ1B","type":"function","function":{"name":"get_current_weather","arguments":"","output":null}}]}}} + + event: thread.run.step.delta + data: {"id":"step_001","object":"thread.run.step.delta","delta":{"step_details":{"type":"tool_calls","tool_calls":[{"index":0,"type":"function","function":{"arguments":"{\""}}]}}} + + event: thread.run.step.delta + data: {"id":"step_001","object":"thread.run.step.delta","delta":{"step_details":{"type":"tool_calls","tool_calls":[{"index":0,"type":"function","function":{"arguments":"location"}}]}}} + + ... + + event: thread.run.step.delta + data: {"id":"step_001","object":"thread.run.step.delta","delta":{"step_details":{"type":"tool_calls","tool_calls":[{"index":0,"type":"function","function":{"arguments":"ahrenheit"}}]}}} + + event: thread.run.step.delta + data: {"id":"step_001","object":"thread.run.step.delta","delta":{"step_details":{"type":"tool_calls","tool_calls":[{"index":0,"type":"function","function":{"arguments":"\"}"}}]}}} + + event: thread.run.requires_action + data: {"id":"run_123","object":"thread.run","created_at":1710351818,"assistant_id":"asst_123","thread_id":"thread_123","status":"requires_action","started_at":1710351818,"expires_at":1710352418,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":{"type":"submit_tool_outputs","submit_tool_outputs":{"tool_calls":[{"id":"call_XXNp8YGaFrjrSjgqxtC8JJ1B","type":"function","function":{"name":"get_current_weather","arguments":"{\"location\":\"San Francisco, CA\",\"unit\":\"fahrenheit\"}"}}]}},"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":{"prompt_tokens":345,"completion_tokens":11,"total_tokens":356},"response_format":"auto","tool_choice":"auto"}} + + event: done + data: [DONE] + + /threads/{thread_id}/runs: get: - operationId: getRun + operationId: listRuns tags: - Assistants - summary: Retrieves a run. + summary: Returns a list of runs belonging to a thread. parameters: - - in: path - name: thread_id + - name: thread_id + in: path required: true schema: type: string - description: The ID of the [thread](/docs/api-reference/threads) that was run. - - in: path - name: run_id - required: true + description: The ID of the thread the run belongs to. + - name: limit + in: query + description: *pagination_limit_param_description + required: false + schema: + type: integer + default: 20 + - name: order + in: query + description: *pagination_order_param_description + schema: + type: string + default: desc + enum: ["asc", "desc"] + - name: after + in: query + description: *pagination_after_param_description + schema: + type: string + - name: before + in: query + description: *pagination_before_param_description schema: type: string - description: The ID of the run to retrieve. responses: "200": description: OK content: application/json: schema: - $ref: "#/components/schemas/RunObject" + $ref: "#/components/schemas/ListRunsResponse" x-oaiMeta: - name: Retrieve run + name: List runs group: threads beta: true - returns: The [run](/docs/api-reference/runs/object) object matching the specified ID. + returns: A list of [run](/docs/api-reference/runs/object) objects. examples: request: curl: | - curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123 \ + curl https://api.openai.com/v1/threads/thread_abc123/runs \ -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v1" + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" python: | from openai import OpenAI client = OpenAI() - run = client.beta.threads.runs.retrieve( - thread_id="thread_abc123", - run_id="run_abc123" + runs = client.beta.threads.runs.list( + "thread_abc123" ) - print(run) + + print(runs) node.js: | import OpenAI from "openai"; const openai = new OpenAI(); async function main() { - const run = await openai.beta.threads.runs.retrieve( - "thread_abc123", - "run_abc123" + const runs = await openai.beta.threads.runs.list( + "thread_abc123" ); - console.log(run); + console.log(runs); } main(); response: | { - "id": "run_abc123", - "object": "thread.run", - "created_at": 1699075072, - "assistant_id": "asst_abc123", - "thread_id": "thread_abc123", - "status": "completed", - "started_at": 1699075072, - "expires_at": null, - "cancelled_at": null, - "failed_at": null, - "completed_at": 1699075073, - "last_error": null, - "model": "gpt-3.5-turbo", - "instructions": null, - "tools": [ + "object": "list", + "data": [ { - "type": "code_interpreter" - } - ], - "file_ids": [ - "file-abc123", - "file-abc456" - ], - "metadata": {}, - "usage": { - "prompt_tokens": 123, - "completion_tokens": 456, - "total_tokens": 579 - } + "id": "run_abc123", + "object": "thread.run", + "created_at": 1699075072, + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "status": "completed", + "started_at": 1699075072, + "expires_at": null, + "cancelled_at": null, + "failed_at": null, + "completed_at": 1699075073, + "last_error": null, + "model": "gpt-4-turbo", + "instructions": null, + "incomplete_details": null, + "tools": [ + { + "type": "code_interpreter" + } + ], + "tool_resources": { + "code_interpreter": { + "file_ids": [ + "file-abc123", + "file-abc456" + ] + } + }, + "metadata": {}, + "usage": { + "prompt_tokens": 123, + "completion_tokens": 456, + "total_tokens": 579 + }, + "temperature": 1.0, + "top_p": 1.0, + "max_prompt_tokens": 1000, + "max_completion_tokens": 1000, + "truncation_strategy": { + "type": "auto", + "last_messages": null + }, + "response_format": "auto", + "tool_choice": "auto" + }, + { + "id": "run_abc456", + "object": "thread.run", + "created_at": 1699063290, + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "status": "completed", + "started_at": 1699063290, + "expires_at": null, + "cancelled_at": null, + "failed_at": null, + "completed_at": 1699063291, + "last_error": null, + "model": "gpt-4-turbo", + "instructions": null, + "incomplete_details": null, + "tools": [ + { + "type": "code_interpreter" + } + ], + "tool_resources": { + "code_interpreter": { + "file_ids": [ + "file-abc123", + "file-abc456" + ] + } + }, + "metadata": {}, + "usage": { + "prompt_tokens": 123, + "completion_tokens": 456, + "total_tokens": 579 + }, + "temperature": 1.0, + "top_p": 1.0, + "max_prompt_tokens": 1000, + "max_completion_tokens": 1000, + "truncation_strategy": { + "type": "auto", + "last_messages": null + }, + "response_format": "auto", + "tool_choice": "auto" + } + ], + "first_id": "run_abc123", + "last_id": "run_abc456", + "has_more": false } post: - operationId: modifyRun + operationId: createRun tags: - Assistants - summary: Modifies a run. + summary: Create a run. parameters: - in: path name: thread_id required: true schema: type: string - description: The ID of the [thread](/docs/api-reference/threads) that was run. - - in: path - name: run_id - required: true - schema: - type: string - description: The ID of the run to modify. + description: The ID of the thread to run. requestBody: required: true content: application/json: schema: - $ref: "#/components/schemas/ModifyRunRequest" + $ref: "#/components/schemas/CreateRunRequest" responses: "200": description: OK @@ -4009,246 +4480,340 @@ paths: schema: $ref: "#/components/schemas/RunObject" x-oaiMeta: - name: Modify run + name: Create run group: threads beta: true - returns: The modified [run](/docs/api-reference/runs/object) object matching the specified ID. + returns: A [run](/docs/api-reference/runs/object) object. examples: - request: - curl: | - curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123 \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v1" \ - -d '{ - "metadata": { - "user_id": "user_abc123" - } - }' - python: | - from openai import OpenAI - client = OpenAI() + - title: Default + request: + curl: | + curl https://api.openai.com/v1/threads/thread_abc123/runs \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "assistant_id": "asst_abc123" + }' + python: | + from openai import OpenAI + client = OpenAI() - run = client.beta.threads.runs.update( - thread_id="thread_abc123", - run_id="run_abc123", - metadata={"user_id": "user_abc123"}, - ) - print(run) - node.js: | - import OpenAI from "openai"; + run = client.beta.threads.runs.create( + thread_id="thread_abc123", + assistant_id="asst_abc123" + ) - const openai = new OpenAI(); + print(run) + node.js: | + import OpenAI from "openai"; - async function main() { - const run = await openai.beta.threads.runs.update( - "thread_abc123", - "run_abc123", - { - metadata: { - user_id: "user_abc123", - }, - } - ); + const openai = new OpenAI(); - console.log(run); - } + async function main() { + const run = await openai.beta.threads.runs.create( + "thread_abc123", + { assistant_id: "asst_abc123" } + ); - main(); - response: | - { - "id": "run_abc123", - "object": "thread.run", - "created_at": 1699075072, - "assistant_id": "asst_abc123", - "thread_id": "thread_abc123", - "status": "completed", - "started_at": 1699075072, - "expires_at": null, - "cancelled_at": null, - "failed_at": null, - "completed_at": 1699075073, - "last_error": null, - "model": "gpt-3.5-turbo", - "instructions": null, - "tools": [ - { - "type": "code_interpreter" + console.log(run); } - ], - "file_ids": [ - "file-abc123", - "file-abc456" - ], - "metadata": { - "user_id": "user_abc123" - }, - "usage": { - "prompt_tokens": 123, - "completion_tokens": 456, - "total_tokens": 579 - } - } - - /threads/{thread_id}/runs/{run_id}/submit_tool_outputs: - post: - operationId: submitToolOuputsToRun - tags: - - Assistants - summary: | - When a run has the `status: "requires_action"` and `required_action.type` is `submit_tool_outputs`, this endpoint can be used to submit the outputs from the tool calls once they're all completed. All outputs must be submitted in a single request. - parameters: - - in: path - name: thread_id - required: true - schema: - type: string - description: The ID of the [thread](/docs/api-reference/threads) to which this run belongs. - - in: path - name: run_id - required: true - schema: - type: string - description: The ID of the run that requires the tool output submission. - requestBody: - required: true - content: - application/json: - schema: - $ref: "#/components/schemas/SubmitToolOutputsRunRequest" - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/RunObject" - x-oaiMeta: - name: Submit tool outputs to run - group: threads - beta: true - returns: The modified [run](/docs/api-reference/runs/object) object matching the specified ID. - examples: - request: - curl: | - curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123/submit_tool_outputs \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v1" \ - -d '{ - "tool_outputs": [ - { - "tool_call_id": "call_abc123", - "output": "28C" - } - ] - }' - python: | - from openai import OpenAI - client = OpenAI() - run = client.beta.threads.runs.submit_tool_outputs( - thread_id="thread_abc123", - run_id="run_abc123", - tool_outputs=[ + main(); + response: &run_object_example | + { + "id": "run_abc123", + "object": "thread.run", + "created_at": 1699063290, + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "status": "queued", + "started_at": 1699063290, + "expires_at": null, + "cancelled_at": null, + "failed_at": null, + "completed_at": 1699063291, + "last_error": null, + "model": "gpt-4-turbo", + "instructions": null, + "incomplete_details": null, + "tools": [ { - "tool_call_id": "call_abc123", - "output": "28C" + "type": "code_interpreter" } - ] - ) - print(run) - node.js: | - import OpenAI from "openai"; + ], + "metadata": {}, + "usage": null, + "temperature": 1.0, + "top_p": 1.0, + "max_prompt_tokens": 1000, + "max_completion_tokens": 1000, + "truncation_strategy": { + "type": "auto", + "last_messages": null + }, + "response_format": "auto", + "tool_choice": "auto" + } + - title: Streaming + request: + curl: | + curl https://api.openai.com/v1/threads/thread_123/runs \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "assistant_id": "asst_123", + "stream": true + }' + python: | + from openai import OpenAI + client = OpenAI() - const openai = new OpenAI(); + stream = client.beta.threads.runs.create( + thread_id="thread_123", + assistant_id="asst_123", + stream=True + ) - async function main() { - const run = await openai.beta.threads.runs.submitToolOutputs( - "thread_abc123", - "run_abc123", - { - tool_outputs: [ - { - tool_call_id: "call_abc123", - output: "28C", - }, - ], - } - ); + for event in stream: + print(event) + node.js: | + import OpenAI from "openai"; - console.log(run); - } + const openai = new OpenAI(); - main(); - response: | - { - "id": "run_abc123", - "object": "thread.run", - "created_at": 1699075592, - "assistant_id": "asst_abc123", - "thread_id": "thread_abc123", - "status": "queued", - "started_at": 1699075592, - "expires_at": 1699076192, - "cancelled_at": null, - "failed_at": null, - "completed_at": null, - "last_error": null, - "model": "gpt-4", - "instructions": "You tell the weather.", - "tools": [ - { - "type": "function", - "function": { - "name": "get_weather", - "description": "Determine weather in my location", - "parameters": { - "type": "object", - "properties": { - "location": { - "type": "string", - "description": "The city and state e.g. San Francisco, CA" - }, - "unit": { - "type": "string", - "enum": [ - "c", - "f" - ] + async function main() { + const stream = await openai.beta.threads.runs.create( + "thread_123", + { assistant_id: "asst_123", stream: true } + ); + + for await (const event of stream) { + console.log(event); + } + } + + main(); + response: | + event: thread.run.created + data: {"id":"run_123","object":"thread.run","created_at":1710330640,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710331240,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto"}} + + event: thread.run.queued + data: {"id":"run_123","object":"thread.run","created_at":1710330640,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710331240,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto"}} + + event: thread.run.in_progress + data: {"id":"run_123","object":"thread.run","created_at":1710330640,"assistant_id":"asst_123","thread_id":"thread_123","status":"in_progress","started_at":1710330641,"expires_at":1710331240,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto"}} + + event: thread.run.step.created + data: {"id":"step_001","object":"thread.run.step","created_at":1710330641,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710331240,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":null} + + event: thread.run.step.in_progress + data: {"id":"step_001","object":"thread.run.step","created_at":1710330641,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710331240,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":null} + + event: thread.message.created + data: {"id":"msg_001","object":"thread.message","created_at":1710330641,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[],"metadata":{}} + + event: thread.message.in_progress + data: {"id":"msg_001","object":"thread.message","created_at":1710330641,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[],"metadata":{}} + + event: thread.message.delta + data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"Hello","annotations":[]}}]}} + + ... + + event: thread.message.delta + data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":" today"}}]}} + + event: thread.message.delta + data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"?"}}]}} + + event: thread.message.completed + data: {"id":"msg_001","object":"thread.message","created_at":1710330641,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"completed","incomplete_details":null,"incomplete_at":null,"completed_at":1710330642,"role":"assistant","content":[{"type":"text","text":{"value":"Hello! How can I assist you today?","annotations":[]}}],"metadata":{}} + + event: thread.run.step.completed + data: {"id":"step_001","object":"thread.run.step","created_at":1710330641,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"completed","cancelled_at":null,"completed_at":1710330642,"expires_at":1710331240,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":{"prompt_tokens":20,"completion_tokens":11,"total_tokens":31}} + + event: thread.run.completed + data: {"id":"run_123","object":"thread.run","created_at":1710330640,"assistant_id":"asst_123","thread_id":"thread_123","status":"completed","started_at":1710330641,"expires_at":null,"cancelled_at":null,"failed_at":null,"completed_at":1710330642,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":{"prompt_tokens":20,"completion_tokens":11,"total_tokens":31},"response_format":"auto","tool_choice":"auto"}} + + event: done + data: [DONE] + + - title: Streaming with Functions + request: + curl: | + curl https://api.openai.com/v1/threads/thread_abc123/runs \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "assistant_id": "asst_abc123", + "tools": [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA" + }, + "unit": { + "type": "string", + "enum": ["celsius", "fahrenheit"] + } + }, + "required": ["location"] + } } + } + ], + "stream": true + }' + python: | + from openai import OpenAI + client = OpenAI() + + tools = [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA", + }, + "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}, + }, + "required": ["location"], }, - "required": [ - "location" - ] } } + ] + + stream = client.beta.threads.runs.create( + thread_id="thread_abc123", + assistant_id="asst_abc123", + tools=tools, + stream=True + ) + + for event in stream: + print(event) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + const tools = [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA", + }, + "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}, + }, + "required": ["location"], + }, + } + } + ]; + + async function main() { + const stream = await openai.beta.threads.runs.create( + "thread_abc123", + { + assistant_id: "asst_abc123", + tools: tools, + stream: true + } + ); + + for await (const event of stream) { + console.log(event); + } } - ], - "file_ids": [], - "metadata": {}, - "usage": null - } - /threads/{thread_id}/runs/{run_id}/cancel: - post: - operationId: cancelRun + main(); + response: | + event: thread.run.created + data: {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710348675,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto"}} + + event: thread.run.queued + data: {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710348675,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto"}} + + event: thread.run.in_progress + data: {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"in_progress","started_at":1710348075,"expires_at":1710348675,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto"}} + + event: thread.run.step.created + data: {"id":"step_001","object":"thread.run.step","created_at":1710348076,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710348675,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":null} + + event: thread.run.step.in_progress + data: {"id":"step_001","object":"thread.run.step","created_at":1710348076,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710348675,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":null} + + event: thread.message.created + data: {"id":"msg_001","object":"thread.message","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[],"metadata":{}} + + event: thread.message.in_progress + data: {"id":"msg_001","object":"thread.message","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[],"metadata":{}} + + event: thread.message.delta + data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"Hello","annotations":[]}}]}} + + ... + + event: thread.message.delta + data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":" today"}}]}} + + event: thread.message.delta + data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"?"}}]}} + + event: thread.message.completed + data: {"id":"msg_001","object":"thread.message","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"completed","incomplete_details":null,"incomplete_at":null,"completed_at":1710348077,"role":"assistant","content":[{"type":"text","text":{"value":"Hello! How can I assist you today?","annotations":[]}}],"metadata":{}} + + event: thread.run.step.completed + data: {"id":"step_001","object":"thread.run.step","created_at":1710348076,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"completed","cancelled_at":null,"completed_at":1710348077,"expires_at":1710348675,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":{"prompt_tokens":20,"completion_tokens":11,"total_tokens":31}} + + event: thread.run.completed + data: {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"completed","started_at":1710348075,"expires_at":null,"cancelled_at":null,"failed_at":null,"completed_at":1710348077,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":{"prompt_tokens":20,"completion_tokens":11,"total_tokens":31},"response_format":"auto","tool_choice":"auto"}} + + event: done + data: [DONE] + + /threads/{thread_id}/runs/{run_id}: + get: + operationId: getRun tags: - Assistants - summary: Cancels a run that is `in_progress`. + summary: Retrieves a run. parameters: - in: path name: thread_id required: true schema: type: string - description: The ID of the thread to which this run belongs. + description: The ID of the [thread](/docs/api-reference/threads) that was run. - in: path name: run_id required: true schema: type: string - description: The ID of the run to cancel. + description: The ID of the run to retrieve. responses: "200": description: OK @@ -4257,25 +4822,25 @@ paths: schema: $ref: "#/components/schemas/RunObject" x-oaiMeta: - name: Cancel a run + name: Retrieve run group: threads beta: true - returns: The modified [run](/docs/api-reference/runs/object) object matching the specified ID. + returns: The [run](/docs/api-reference/runs/object) object matching the specified ID. examples: request: curl: | - curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123/cancel \ + curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123 \ -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "OpenAI-Beta: assistants=v1" \ - -X POST + -H "OpenAI-Beta: assistants=v2" python: | from openai import OpenAI client = OpenAI() - run = client.beta.threads.runs.cancel( + run = client.beta.threads.runs.retrieve( thread_id="thread_abc123", run_id="run_abc123" ) + print(run) node.js: | import OpenAI from "openai"; @@ -4283,7 +4848,7 @@ paths: const openai = new OpenAI(); async function main() { - const run = await openai.beta.threads.runs.cancel( + const run = await openai.beta.threads.runs.retrieve( "thread_abc123", "run_abc123" ); @@ -4296,562 +4861,541 @@ paths: { "id": "run_abc123", "object": "thread.run", - "created_at": 1699076126, + "created_at": 1699075072, "assistant_id": "asst_abc123", "thread_id": "thread_abc123", - "status": "cancelling", - "started_at": 1699076126, - "expires_at": 1699076726, + "status": "completed", + "started_at": 1699075072, + "expires_at": null, "cancelled_at": null, "failed_at": null, - "completed_at": null, + "completed_at": 1699075073, "last_error": null, - "model": "gpt-4", - "instructions": "You summarize books.", + "model": "gpt-4-turbo", + "instructions": null, + "incomplete_details": null, "tools": [ { - "type": "retrieval" + "type": "code_interpreter" } ], - "file_ids": [], "metadata": {}, - "usage": null + "usage": { + "prompt_tokens": 123, + "completion_tokens": 456, + "total_tokens": 579 + }, + "temperature": 1.0, + "top_p": 1.0, + "max_prompt_tokens": 1000, + "max_completion_tokens": 1000, + "truncation_strategy": { + "type": "auto", + "last_messages": null + }, + "response_format": "auto", + "tool_choice": "auto" } - - /threads/{thread_id}/runs/{run_id}/steps: - get: - operationId: listRunSteps + post: + operationId: modifyRun tags: - Assistants - summary: Returns a list of run steps belonging to a run. + summary: Modifies a run. parameters: - - name: thread_id - in: path + - in: path + name: thread_id required: true schema: type: string - description: The ID of the thread the run and run steps belong to. - - name: run_id - in: path + description: The ID of the [thread](/docs/api-reference/threads) that was run. + - in: path + name: run_id required: true schema: type: string - description: The ID of the run the run steps belong to. - - name: limit - in: query - description: *pagination_limit_param_description - required: false - schema: - type: integer - default: 20 - - name: order - in: query - description: *pagination_order_param_description - schema: - type: string - default: desc - enum: ["asc", "desc"] - - name: after - in: query - description: *pagination_after_param_description - schema: - type: string - - name: before - in: query - description: *pagination_before_param_description - schema: - type: string + description: The ID of the run to modify. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/ModifyRunRequest" responses: "200": description: OK content: application/json: schema: - $ref: "#/components/schemas/ListRunStepsResponse" + $ref: "#/components/schemas/RunObject" x-oaiMeta: - name: List run steps + name: Modify run group: threads beta: true - returns: A list of [run step](/docs/api-reference/runs/step-object) objects. + returns: The modified [run](/docs/api-reference/runs/object) object matching the specified ID. examples: request: curl: | - curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123/steps \ + curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123 \ -H "Authorization: Bearer $OPENAI_API_KEY" \ -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v1" + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "metadata": { + "user_id": "user_abc123" + } + }' python: | from openai import OpenAI client = OpenAI() - run_steps = client.beta.threads.runs.steps.list( - thread_id="thread_abc123", - run_id="run_abc123" + run = client.beta.threads.runs.update( + thread_id="thread_abc123", + run_id="run_abc123", + metadata={"user_id": "user_abc123"}, ) - print(run_steps) - node.js: | - import OpenAI from "openai"; - const openai = new OpenAI(); - - async function main() { - const runStep = await openai.beta.threads.runs.steps.list( - "thread_abc123", - "run_abc123" - ); - console.log(runStep); - } - - main(); - response: | - { - "object": "list", - "data": [ - { - "id": "step_abc123", - "object": "thread.run.step", - "created_at": 1699063291, - "run_id": "run_abc123", - "assistant_id": "asst_abc123", - "thread_id": "thread_abc123", - "type": "message_creation", - "status": "completed", - "cancelled_at": null, - "completed_at": 1699063291, - "expired_at": null, - "failed_at": null, - "last_error": null, - "step_details": { - "type": "message_creation", - "message_creation": { - "message_id": "msg_abc123" - } - }, - "usage": { - "prompt_tokens": 123, - "completion_tokens": 456, - "total_tokens": 579 - } - } - ], - "first_id": "step_abc123", - "last_id": "step_abc456", - "has_more": false - } - - /threads/{thread_id}/runs/{run_id}/steps/{step_id}: - get: - operationId: getRunStep - tags: - - Assistants - summary: Retrieves a run step. - parameters: - - in: path - name: thread_id - required: true - schema: - type: string - description: The ID of the thread to which the run and run step belongs. - - in: path - name: run_id - required: true - schema: - type: string - description: The ID of the run to which the run step belongs. - - in: path - name: step_id - required: true - schema: - type: string - description: The ID of the run step to retrieve. - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/RunStepObject" - x-oaiMeta: - name: Retrieve run step - group: threads - beta: true - returns: The [run step](/docs/api-reference/runs/step-object) object matching the specified ID. - examples: - request: - curl: | - curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123/steps/step_abc123 \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v1" - python: | - from openai import OpenAI - client = OpenAI() - run_step = client.beta.threads.runs.steps.retrieve( - thread_id="thread_abc123", - run_id="run_abc123", - step_id="step_abc123" - ) - print(run_step) + print(run) node.js: | import OpenAI from "openai"; + const openai = new OpenAI(); async function main() { - const runStep = await openai.beta.threads.runs.steps.retrieve( + const run = await openai.beta.threads.runs.update( "thread_abc123", "run_abc123", - "step_abc123" + { + metadata: { + user_id: "user_abc123", + }, + } ); - console.log(runStep); + + console.log(run); } main(); - response: &run_step_object_example | + response: | { - "id": "step_abc123", - "object": "thread.run.step", - "created_at": 1699063291, - "run_id": "run_abc123", + "id": "run_abc123", + "object": "thread.run", + "created_at": 1699075072, "assistant_id": "asst_abc123", "thread_id": "thread_abc123", - "type": "message_creation", "status": "completed", + "started_at": 1699075072, + "expires_at": null, "cancelled_at": null, - "completed_at": 1699063291, - "expired_at": null, "failed_at": null, + "completed_at": 1699075073, "last_error": null, - "step_details": { - "type": "message_creation", - "message_creation": { - "message_id": "msg_abc123" + "model": "gpt-4-turbo", + "instructions": null, + "incomplete_details": null, + "tools": [ + { + "type": "code_interpreter" } + ], + "tool_resources": { + "code_interpreter": { + "file_ids": [ + "file-abc123", + "file-abc456" + ] + } + }, + "metadata": { + "user_id": "user_abc123" }, "usage": { "prompt_tokens": 123, "completion_tokens": 456, "total_tokens": 579 - } + }, + "temperature": 1.0, + "top_p": 1.0, + "max_prompt_tokens": 1000, + "max_completion_tokens": 1000, + "truncation_strategy": { + "type": "auto", + "last_messages": null + }, + "response_format": "auto", + "tool_choice": "auto" } - /assistants/{assistant_id}/files: - get: - operationId: listAssistantFiles + /threads/{thread_id}/runs/{run_id}/submit_tool_outputs: + post: + operationId: submitToolOuputsToRun tags: - Assistants - summary: Returns a list of assistant files. + summary: | + When a run has the `status: "requires_action"` and `required_action.type` is `submit_tool_outputs`, this endpoint can be used to submit the outputs from the tool calls once they're all completed. All outputs must be submitted in a single request. parameters: - - name: assistant_id - in: path - description: The ID of the assistant the file belongs to. + - in: path + name: thread_id required: true schema: type: string - - name: limit - in: query - description: *pagination_limit_param_description - required: false - schema: - type: integer - default: 20 - - name: order - in: query - description: *pagination_order_param_description - schema: - type: string - default: desc - enum: ["asc", "desc"] - - name: after - in: query - description: *pagination_after_param_description - schema: - type: string - - name: before - in: query - description: *pagination_before_param_description - schema: - type: string - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/ListAssistantFilesResponse" - x-oaiMeta: - name: List assistant files - group: assistants - beta: true - returns: A list of [assistant file](/docs/api-reference/assistants/file-object) objects. - examples: - request: - curl: | - curl https://api.openai.com/v1/assistants/asst_abc123/files \ - -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v1" - python: | - from openai import OpenAI - client = OpenAI() - - assistant_files = client.beta.assistants.files.list( - assistant_id="asst_abc123" - ) - print(assistant_files) - node.js: | - import OpenAI from "openai"; - const openai = new OpenAI(); - - async function main() { - const assistantFiles = await openai.beta.assistants.files.list( - "asst_abc123" - ); - console.log(assistantFiles); - } - - main(); - response: | - { - "object": "list", - "data": [ - { - "id": "file-abc123", - "object": "assistant.file", - "created_at": 1699060412, - "assistant_id": "asst_abc123" - }, - { - "id": "file-abc456", - "object": "assistant.file", - "created_at": 1699060412, - "assistant_id": "asst_abc123" - } - ], - "first_id": "file-abc123", - "last_id": "file-abc456", - "has_more": false - } - post: - operationId: createAssistantFile - tags: - - Assistants - summary: Create an assistant file by attaching a [File](/docs/api-reference/files) to an [assistant](/docs/api-reference/assistants). - parameters: + description: The ID of the [thread](/docs/api-reference/threads) to which this run belongs. - in: path - name: assistant_id + name: run_id required: true schema: type: string - example: file-abc123 - description: | - The ID of the assistant for which to create a File. + description: The ID of the run that requires the tool output submission. requestBody: required: true content: application/json: schema: - $ref: "#/components/schemas/CreateAssistantFileRequest" + $ref: "#/components/schemas/SubmitToolOutputsRunRequest" responses: "200": description: OK content: application/json: schema: - $ref: "#/components/schemas/AssistantFileObject" + $ref: "#/components/schemas/RunObject" x-oaiMeta: - name: Create assistant file - group: assistants + name: Submit tool outputs to run + group: threads beta: true - returns: An [assistant file](/docs/api-reference/assistants/file-object) object. + returns: The modified [run](/docs/api-reference/runs/object) object matching the specified ID. examples: - request: - curl: | - curl https://api.openai.com/v1/assistants/asst_abc123/files \ - -H 'Authorization: Bearer $OPENAI_API_KEY"' \ - -H 'Content-Type: application/json' \ - -H 'OpenAI-Beta: assistants=v1' \ + - title: Default + request: + curl: | + curl https://api.openai.com/v1/threads/thread_123/runs/run_123/submit_tool_outputs \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ -d '{ - "file_id": "file-abc123" + "tool_outputs": [ + { + "tool_call_id": "call_001", + "output": "70 degrees and sunny." + } + ] }' - python: | - from openai import OpenAI - client = OpenAI() - - assistant_file = client.beta.assistants.files.create( - assistant_id="asst_abc123", - file_id="file-abc123" - ) - print(assistant_file) - node.js: | - import OpenAI from "openai"; - const openai = new OpenAI(); + python: | + from openai import OpenAI + client = OpenAI() - async function main() { - const myAssistantFile = await openai.beta.assistants.files.create( - "asst_abc123", + run = client.beta.threads.runs.submit_tool_outputs( + thread_id="thread_123", + run_id="run_123", + tool_outputs=[ + { + "tool_call_id": "call_001", + "output": "70 degrees and sunny." + } + ] + ) + + print(run) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const run = await openai.beta.threads.runs.submitToolOutputs( + "thread_123", + "run_123", + { + tool_outputs: [ + { + tool_call_id: "call_001", + output: "70 degrees and sunny.", + }, + ], + } + ); + + console.log(run); + } + + main(); + response: | + { + "id": "run_123", + "object": "thread.run", + "created_at": 1699075592, + "assistant_id": "asst_123", + "thread_id": "thread_123", + "status": "queued", + "started_at": 1699075592, + "expires_at": 1699076192, + "cancelled_at": null, + "failed_at": null, + "completed_at": null, + "last_error": null, + "model": "gpt-4-turbo", + "instructions": null, + "tools": [ { - file_id: "file-abc123" + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA" + }, + "unit": { + "type": "string", + "enum": ["celsius", "fahrenheit"] + } + }, + "required": ["location"] + } + } } - ); - console.log(myAssistantFile); + ], + "metadata": {}, + "usage": null, + "temperature": 1.0, + "top_p": 1.0, + "max_prompt_tokens": 1000, + "max_completion_tokens": 1000, + "truncation_strategy": { + "type": "auto", + "last_messages": null + }, + "response_format": "auto", + "tool_choice": "auto" } - main(); - response: &assistant_file_object | - { - "id": "file-abc123", - "object": "assistant.file", - "created_at": 1699055364, - "assistant_id": "asst_abc123" - } + - title: Streaming + request: + curl: | + curl https://api.openai.com/v1/threads/thread_123/runs/run_123/submit_tool_outputs \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "tool_outputs": [ + { + "tool_call_id": "call_001", + "output": "70 degrees and sunny." + } + ], + "stream": true + }' + python: | + from openai import OpenAI + client = OpenAI() - /assistants/{assistant_id}/files/{file_id}: - get: - operationId: getAssistantFile - tags: - - Assistants - summary: Retrieves an AssistantFile. - parameters: - - in: path - name: assistant_id - required: true - schema: - type: string - description: The ID of the assistant who the file belongs to. - - in: path - name: file_id - required: true - schema: - type: string - description: The ID of the file we're getting. - responses: - "200": - description: OK - content: - application/json: - schema: - $ref: "#/components/schemas/AssistantFileObject" - x-oaiMeta: - name: Retrieve assistant file - group: assistants - beta: true - returns: The [assistant file](/docs/api-reference/assistants/file-object) object matching the specified ID. - examples: - request: - curl: | - curl https://api.openai.com/v1/assistants/asst_abc123/files/file-abc123 \ - -H 'Authorization: Bearer $OPENAI_API_KEY"' \ - -H 'Content-Type: application/json' \ - -H 'OpenAI-Beta: assistants=v1' - python: | - from openai import OpenAI - client = OpenAI() + stream = client.beta.threads.runs.submit_tool_outputs( + thread_id="thread_123", + run_id="run_123", + tool_outputs=[ + { + "tool_call_id": "call_001", + "output": "70 degrees and sunny." + } + ], + stream=True + ) - assistant_file = client.beta.assistants.files.retrieve( - assistant_id="asst_abc123", - file_id="file-abc123" - ) - print(assistant_file) - node.js: | - import OpenAI from "openai"; - const openai = new OpenAI(); + for event in stream: + print(event) + node.js: | + import OpenAI from "openai"; - async function main() { - const myAssistantFile = await openai.beta.assistants.files.retrieve( - "asst_abc123", - "file-abc123" - ); - console.log(myAssistantFile); - } + const openai = new OpenAI(); - main(); - response: *assistant_file_object - delete: - operationId: deleteAssistantFile + async function main() { + const stream = await openai.beta.threads.runs.submitToolOutputs( + "thread_123", + "run_123", + { + tool_outputs: [ + { + tool_call_id: "call_001", + output: "70 degrees and sunny.", + }, + ], + } + ); + + for await (const event of stream) { + console.log(event); + } + } + + main(); + response: | + event: thread.run.step.completed + data: {"id":"step_001","object":"thread.run.step","created_at":1710352449,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"tool_calls","status":"completed","cancelled_at":null,"completed_at":1710352475,"expires_at":1710353047,"failed_at":null,"last_error":null,"step_details":{"type":"tool_calls","tool_calls":[{"id":"call_iWr0kQ2EaYMaxNdl0v3KYkx7","type":"function","function":{"name":"get_current_weather","arguments":"{\"location\":\"San Francisco, CA\",\"unit\":\"fahrenheit\"}","output":"70 degrees and sunny."}}]},"usage":{"prompt_tokens":291,"completion_tokens":24,"total_tokens":315}} + + event: thread.run.queued + data: {"id":"run_123","object":"thread.run","created_at":1710352447,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":1710352448,"expires_at":1710353047,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto"}} + + event: thread.run.in_progress + data: {"id":"run_123","object":"thread.run","created_at":1710352447,"assistant_id":"asst_123","thread_id":"thread_123","status":"in_progress","started_at":1710352475,"expires_at":1710353047,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto"}} + + event: thread.run.step.created + data: {"id":"step_002","object":"thread.run.step","created_at":1710352476,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710353047,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_002"}},"usage":null} + + event: thread.run.step.in_progress + data: {"id":"step_002","object":"thread.run.step","created_at":1710352476,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710353047,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_002"}},"usage":null} + + event: thread.message.created + data: {"id":"msg_002","object":"thread.message","created_at":1710352476,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[],"metadata":{}} + + event: thread.message.in_progress + data: {"id":"msg_002","object":"thread.message","created_at":1710352476,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[],"metadata":{}} + + event: thread.message.delta + data: {"id":"msg_002","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"The","annotations":[]}}]}} + + event: thread.message.delta + data: {"id":"msg_002","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":" current"}}]}} + + event: thread.message.delta + data: {"id":"msg_002","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":" weather"}}]}} + + ... + + event: thread.message.delta + data: {"id":"msg_002","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":" sunny"}}]}} + + event: thread.message.delta + data: {"id":"msg_002","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"."}}]}} + + event: thread.message.completed + data: {"id":"msg_002","object":"thread.message","created_at":1710352476,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"completed","incomplete_details":null,"incomplete_at":null,"completed_at":1710352477,"role":"assistant","content":[{"type":"text","text":{"value":"The current weather in San Francisco, CA is 70 degrees Fahrenheit and sunny.","annotations":[]}}],"metadata":{}} + + event: thread.run.step.completed + data: {"id":"step_002","object":"thread.run.step","created_at":1710352476,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"completed","cancelled_at":null,"completed_at":1710352477,"expires_at":1710353047,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_002"}},"usage":{"prompt_tokens":329,"completion_tokens":18,"total_tokens":347}} + + event: thread.run.completed + data: {"id":"run_123","object":"thread.run","created_at":1710352447,"assistant_id":"asst_123","thread_id":"thread_123","status":"completed","started_at":1710352475,"expires_at":null,"cancelled_at":null,"failed_at":null,"completed_at":1710352477,"required_action":null,"last_error":null,"model":"gpt-4-turbo","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":{"prompt_tokens":20,"completion_tokens":11,"total_tokens":31},"response_format":"auto","tool_choice":"auto"}} + + event: done + data: [DONE] + + /threads/{thread_id}/runs/{run_id}/cancel: + post: + operationId: cancelRun tags: - Assistants - summary: Delete an assistant file. + summary: Cancels a run that is `in_progress`. parameters: - in: path - name: assistant_id + name: thread_id required: true schema: type: string - description: The ID of the assistant that the file belongs to. + description: The ID of the thread to which this run belongs. - in: path - name: file_id + name: run_id required: true schema: type: string - description: The ID of the file to delete. + description: The ID of the run to cancel. responses: "200": description: OK content: application/json: schema: - $ref: "#/components/schemas/DeleteAssistantFileResponse" + $ref: "#/components/schemas/RunObject" x-oaiMeta: - name: Delete assistant file - group: assistants + name: Cancel a run + group: threads beta: true - returns: Deletion status + returns: The modified [run](/docs/api-reference/runs/object) object matching the specified ID. examples: request: curl: | - curl https://api.openai.com/v1/assistants/asst_abc123/files/file-abc123 \ + curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123/cancel \ -H "Authorization: Bearer $OPENAI_API_KEY" \ - -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v1" \ - -X DELETE + -H "OpenAI-Beta: assistants=v2" \ + -X POST python: | from openai import OpenAI client = OpenAI() - deleted_assistant_file = client.beta.assistants.files.delete( - assistant_id="asst_abc123", - file_id="file-abc123" + run = client.beta.threads.runs.cancel( + thread_id="thread_abc123", + run_id="run_abc123" ) - print(deleted_assistant_file) + + print(run) node.js: | import OpenAI from "openai"; + const openai = new OpenAI(); async function main() { - const deletedAssistantFile = await openai.beta.assistants.files.del( - "asst_abc123", - "file-abc123" + const run = await openai.beta.threads.runs.cancel( + "thread_abc123", + "run_abc123" ); - console.log(deletedAssistantFile); + + console.log(run); } main(); response: | { - id: "file-abc123", - object: "assistant.file.deleted", - deleted: true + "id": "run_abc123", + "object": "thread.run", + "created_at": 1699076126, + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "status": "cancelling", + "started_at": 1699076126, + "expires_at": 1699076726, + "cancelled_at": null, + "failed_at": null, + "completed_at": null, + "last_error": null, + "model": "gpt-4-turbo", + "instructions": "You summarize books.", + "tools": [ + { + "type": "file_search" + } + ], + "tool_resources": { + "file_search": { + "vector_store_ids": ["vs_123"] + } + }, + "metadata": {}, + "usage": null, + "temperature": 1.0, + "top_p": 1.0, + "response_format": "auto" } - /threads/{thread_id}/messages/{message_id}/files: + /threads/{thread_id}/runs/{run_id}/steps: get: - operationId: listMessageFiles + operationId: listRunSteps tags: - Assistants - summary: Returns a list of message files. + summary: Returns a list of run steps belonging to a run. parameters: - name: thread_id in: path - description: The ID of the thread that the message and files belong to. required: true schema: type: string - - name: message_id + description: The ID of the thread the run and run steps belong to. + - name: run_id in: path - description: The ID of the message that the files belongs to. required: true schema: type: string + description: The ID of the run the run steps belong to. - name: limit in: query description: *pagination_limit_param_description @@ -4882,38 +5426,39 @@ paths: content: application/json: schema: - $ref: "#/components/schemas/ListMessageFilesResponse" + $ref: "#/components/schemas/ListRunStepsResponse" x-oaiMeta: - name: List message files + name: List run steps group: threads beta: true - returns: A list of [message file](/docs/api-reference/messages/file-object) objects. + returns: A list of [run step](/docs/api-reference/runs/step-object) objects. examples: request: curl: | - curl https://api.openai.com/v1/threads/thread_abc123/messages/msg_abc123/files \ + curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123/steps \ -H "Authorization: Bearer $OPENAI_API_KEY" \ -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v1" + -H "OpenAI-Beta: assistants=v2" python: | from openai import OpenAI client = OpenAI() - message_files = client.beta.threads.messages.files.list( - thread_id="thread_abc123", - message_id="msg_abc123" + run_steps = client.beta.threads.runs.steps.list( + thread_id="thread_abc123", + run_id="run_abc123" ) - print(message_files) + + print(run_steps) node.js: | import OpenAI from "openai"; const openai = new OpenAI(); async function main() { - const messageFiles = await openai.beta.threads.messages.files.list( + const runStep = await openai.beta.threads.runs.steps.list( "thread_abc123", - "msg_abc123" + "run_abc123" ); - console.log(messageFiles); + console.log(runStep); } main(); @@ -4922,265 +5467,2390 @@ paths: "object": "list", "data": [ { - "id": "file-abc123", - "object": "thread.message.file", - "created_at": 1699061776, - "message_id": "msg_abc123" - }, - { - "id": "file-abc123", - "object": "thread.message.file", - "created_at": 1699061776, - "message_id": "msg_abc123" - } - ], - "first_id": "file-abc123", - "last_id": "file-abc123", - "has_more": false - } - - /threads/{thread_id}/messages/{message_id}/files/{file_id}: - get: - operationId: getMessageFile - tags: - - Assistants - summary: Retrieves a message file. - parameters: - - in: path - name: thread_id - required: true - schema: - type: string - example: thread_abc123 - description: The ID of the thread to which the message and File belong. - - in: path - name: message_id - required: true - schema: - type: string - example: msg_abc123 - description: The ID of the message the file belongs to. - - in: path - name: file_id - required: true + "id": "step_abc123", + "object": "thread.run.step", + "created_at": 1699063291, + "run_id": "run_abc123", + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "type": "message_creation", + "status": "completed", + "cancelled_at": null, + "completed_at": 1699063291, + "expired_at": null, + "failed_at": null, + "last_error": null, + "step_details": { + "type": "message_creation", + "message_creation": { + "message_id": "msg_abc123" + } + }, + "usage": { + "prompt_tokens": 123, + "completion_tokens": 456, + "total_tokens": 579 + } + } + ], + "first_id": "step_abc123", + "last_id": "step_abc456", + "has_more": false + } + + /threads/{thread_id}/runs/{run_id}/steps/{step_id}: + get: + operationId: getRunStep + tags: + - Assistants + summary: Retrieves a run step. + parameters: + - in: path + name: thread_id + required: true schema: type: string - example: file-abc123 - description: The ID of the file being retrieved. + description: The ID of the thread to which the run and run step belongs. + - in: path + name: run_id + required: true + schema: + type: string + description: The ID of the run to which the run step belongs. + - in: path + name: step_id + required: true + schema: + type: string + description: The ID of the run step to retrieve. responses: "200": description: OK content: application/json: schema: - $ref: "#/components/schemas/MessageFileObject" + $ref: "#/components/schemas/RunStepObject" x-oaiMeta: - name: Retrieve message file + name: Retrieve run step group: threads beta: true - returns: The [message file](/docs/api-reference/messages/file-object) object. + returns: The [run step](/docs/api-reference/runs/step-object) object matching the specified ID. examples: request: curl: | - curl https://api.openai.com/v1/threads/thread_abc123/messages/msg_abc123/files/file-abc123 \ + curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123/steps/step_abc123 \ -H "Authorization: Bearer $OPENAI_API_KEY" \ -H "Content-Type: application/json" \ - -H "OpenAI-Beta: assistants=v1" + -H "OpenAI-Beta: assistants=v2" python: | from openai import OpenAI client = OpenAI() - message_files = client.beta.threads.messages.files.retrieve( + run_step = client.beta.threads.runs.steps.retrieve( thread_id="thread_abc123", - message_id="msg_abc123", - file_id="file-abc123" + run_id="run_abc123", + step_id="step_abc123" ) - print(message_files) + + print(run_step) node.js: | import OpenAI from "openai"; const openai = new OpenAI(); async function main() { - const messageFile = await openai.beta.threads.messages.files.retrieve( + const runStep = await openai.beta.threads.runs.steps.retrieve( "thread_abc123", - "msg_abc123", - "file-abc123" + "run_abc123", + "step_abc123" ); - console.log(messageFile); + console.log(runStep); } main(); - response: | + response: &run_step_object_example | { - "id": "file-abc123", - "object": "thread.message.file", - "created_at": 1699061776, - "message_id": "msg_abc123" + "id": "step_abc123", + "object": "thread.run.step", + "created_at": 1699063291, + "run_id": "run_abc123", + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "type": "message_creation", + "status": "completed", + "cancelled_at": null, + "completed_at": 1699063291, + "expired_at": null, + "failed_at": null, + "last_error": null, + "step_details": { + "type": "message_creation", + "message_creation": { + "message_id": "msg_abc123" + } + }, + "usage": { + "prompt_tokens": 123, + "completion_tokens": 456, + "total_tokens": 579 + } } -components: - securitySchemes: - ApiKeyAuth: - type: http - scheme: "bearer" - - schemas: - Error: - type: object - properties: - code: - type: string - nullable: true - message: - type: string - nullable: false - param: - type: string - nullable: true - type: - type: string - nullable: false - required: - - type - - message - - param - - code - ErrorResponse: - type: object - properties: - error: - $ref: "#/components/schemas/Error" - required: - - error - - ListModelsResponse: - type: object - properties: - object: - type: string - enum: [list] - data: - type: array - items: - $ref: "#/components/schemas/Model" - required: - - object - - data - DeleteModelResponse: - type: object - properties: - id: - type: string - deleted: - type: boolean - object: - type: string - required: - - id - - object - - deleted + /vector_stores: + get: + operationId: listVectorStores + tags: + - Vector Stores + summary: Returns a list of vector stores. + parameters: + - name: limit + in: query + description: *pagination_limit_param_description + required: false + schema: + type: integer + default: 20 + - name: order + in: query + description: *pagination_order_param_description + schema: + type: string + default: desc + enum: ["asc", "desc"] + - name: after + in: query + description: *pagination_after_param_description + schema: + type: string + - name: before + in: query + description: *pagination_before_param_description + schema: + type: string + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListVectorStoresResponse" + x-oaiMeta: + name: List vector stores + group: vector_stores + beta: true + returns: A list of [vector store](/docs/api-reference/vector-stores/object) objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() - CreateCompletionRequest: - type: object - properties: - model: - description: &model_description | - ID of the model to use. You can use the [List models](/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](/docs/models/overview) for descriptions of them. - anyOf: - - type: string - - type: string - enum: ["gpt-3.5-turbo-instruct", "davinci-002", "babbage-002"] - x-oaiTypeLabel: string - prompt: - description: &completions_prompt_description | - The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays. + vector_stores = client.beta.vector_stores.list() + print(vector_stores) + node.js: | + import OpenAI from "openai"; + const openai = new OpenAI(); - Note that <|endoftext|> is the document separator that the model sees during training, so if a prompt is not specified the model will generate as if from the beginning of a new document. - default: "<|endoftext|>" - nullable: true - oneOf: - - type: string - default: "" - example: "This is a test." - - type: array - items: - type: string - default: "" - example: "This is a test." - - type: array - minItems: 1 - items: - type: integer - example: "[1212, 318, 257, 1332, 13]" - - type: array - minItems: 1 - items: - type: array - minItems: 1 - items: - type: integer - example: "[[1212, 318, 257, 1332, 13]]" - best_of: - type: integer - default: 1 - minimum: 0 - maximum: 20 - nullable: true - description: &completions_best_of_description | - Generates `best_of` completions server-side and returns the "best" (the one with the highest log probability per token). Results cannot be streamed. + async function main() { + const vectorStores = await openai.beta.vectorStores.list(); + console.log(vectorStores); + } + + main(); + response: | + { + "object": "list", + "data": [ + { + "id": "vs_abc123", + "object": "vector_store", + "created_at": 1699061776, + "name": "Support FAQ", + "bytes": 139920, + "file_counts": { + "in_progress": 0, + "completed": 3, + "failed": 0, + "cancelled": 0, + "total": 3 + } + }, + { + "id": "vs_abc456", + "object": "vector_store", + "created_at": 1699061776, + "name": "Support FAQ v2", + "bytes": 139920, + "file_counts": { + "in_progress": 0, + "completed": 3, + "failed": 0, + "cancelled": 0, + "total": 3 + } + } + ], + "first_id": "vs_abc123", + "last_id": "vs_abc456", + "has_more": false + } + post: + operationId: createVectorStore + tags: + - Vector Stores + summary: Create a vector store. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateVectorStoreRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/VectorStoreObject" + x-oaiMeta: + name: Create vector store + group: vector_stores + beta: true + returns: A [vector store](/docs/api-reference/vector-stores/object) object. + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" + -d '{ + "name": "Support FAQ" + }' + python: | + from openai import OpenAI + client = OpenAI() + + vector_store = client.beta.vector_stores.create( + name="Support FAQ" + ) + print(vector_store) + node.js: | + import OpenAI from "openai"; + const openai = new OpenAI(); + + async function main() { + const vectorStore = await openai.beta.vectorStores.create({ + name: "Support FAQ" + }); + console.log(vectorStore); + } + + main(); + response: | + { + "id": "vs_abc123", + "object": "vector_store", + "created_at": 1699061776, + "name": "Support FAQ", + "bytes": 139920, + "file_counts": { + "in_progress": 0, + "completed": 3, + "failed": 0, + "cancelled": 0, + "total": 3 + } + } + + /vector_stores/{vector_store_id}: + get: + operationId: getVectorStore + tags: + - Vector Stores + summary: Retrieves a vector store. + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + description: The ID of the vector store to retrieve. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/VectorStoreObject" + x-oaiMeta: + name: Retrieve vector store + group: vector_stores + beta: true + returns: The [vector store](/docs/api-reference/vector-stores/object) object matching the specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores/vs_abc123 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + vector_store = client.beta.vector_stores.retrieve( + vector_store_id="vs_abc123" + ) + print(vector_store) + node.js: | + import OpenAI from "openai"; + const openai = new OpenAI(); + + async function main() { + const vectorStore = await openai.beta.vectorStores.retrieve( + "vs_abc123" + ); + console.log(vectorStore); + } + + main(); + response: | + { + "id": "vs_abc123", + "object": "vector_store", + "created_at": 1699061776 + } + post: + operationId: modifyVectorStore + tags: + - Vector Stores + summary: Modifies a vector store. + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + description: The ID of the vector store to modify. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/UpdateVectorStoreRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/VectorStoreObject" + x-oaiMeta: + name: Modify vector store + group: vector_stores + beta: true + returns: The modified [vector store](/docs/api-reference/vector-stores/object) object. + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores/vs_abc123 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" + -d '{ + "name": "Support FAQ" + }' + python: | + from openai import OpenAI + client = OpenAI() + + vector_store = client.beta.vector_stores.update( + vector_store_id="vs_abc123", + name="Support FAQ" + ) + print(vector_store) + node.js: | + import OpenAI from "openai"; + const openai = new OpenAI(); + + async function main() { + const vectorStore = await openai.beta.vectorStores.update( + "vs_abc123", + { + name: "Support FAQ" + } + ); + console.log(vectorStore); + } + + main(); + response: | + { + "id": "vs_abc123", + "object": "vector_store", + "created_at": 1699061776, + "name": "Support FAQ", + "bytes": 139920, + "file_counts": { + "in_progress": 0, + "completed": 3, + "failed": 0, + "cancelled": 0, + "total": 3 + } + } + + delete: + operationId: deleteVectorStore + tags: + - Vector Stores + summary: Delete a vector store. + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + description: The ID of the vector store to delete. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/DeleteVectorStoreResponse" + x-oaiMeta: + name: Delete vector store + group: vector_stores + beta: true + returns: Deletion status + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores/vs_abc123 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -X DELETE + python: | + from openai import OpenAI + client = OpenAI() + + deleted_vector_store = client.beta.vector_stores.delete( + vector_store_id="vs_abc123" + ) + print(deleted_vector_store) + node.js: | + import OpenAI from "openai"; + const openai = new OpenAI(); + + async function main() { + const deletedVectorStore = await openai.beta.vectorStores.del( + "vs_abc123" + ); + console.log(deletedVectorStore); + } + + main(); + response: | + { + id: "vs_abc123", + object: "vector_store.deleted", + deleted: true + } + + /vector_stores/{vector_store_id}/files: + get: + operationId: listVectorStoreFiles + tags: + - Vector Stores + summary: Returns a list of vector store files. + parameters: + - name: vector_store_id + in: path + description: The ID of the vector store that the files belong to. + required: true + schema: + type: string + - name: limit + in: query + description: *pagination_limit_param_description + required: false + schema: + type: integer + default: 20 + - name: order + in: query + description: *pagination_order_param_description + schema: + type: string + default: desc + enum: ["asc", "desc"] + - name: after + in: query + description: *pagination_after_param_description + schema: + type: string + - name: before + in: query + description: *pagination_before_param_description + schema: + type: string + - name: filter + in: query + description: "Filter by file status. One of `in_progress`, `completed`, `failed`, `cancelled`." + schema: + type: string + enum: ["in_progress", "completed", "failed", "cancelled"] + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListVectorStoreFilesResponse" + x-oaiMeta: + name: List vector store files + group: vector_stores + beta: true + returns: A list of [vector store file](/docs/api-reference/vector-stores-files/file-object) objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores/vs_abc123/files \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + vector_store_files = client.beta.vector_stores.files.list( + vector_store_id="vs_abc123" + ) + print(vector_store_files) + node.js: | + import OpenAI from "openai"; + const openai = new OpenAI(); + + async function main() { + const vectorStoreFiles = await openai.beta.vectorStores.files.list( + "vs_abc123" + ); + console.log(vectorStoreFiles); + } + + main(); + response: | + { + "object": "list", + "data": [ + { + "id": "file-abc123", + "object": "vector_store.file", + "created_at": 1699061776, + "vector_store_id": "vs_abc123" + }, + { + "id": "file-abc456", + "object": "vector_store.file", + "created_at": 1699061776, + "vector_store_id": "vs_abc123" + } + ], + "first_id": "file-abc123", + "last_id": "file-abc456", + "has_more": false + } + post: + operationId: createVectorStoreFile + tags: + - Vector Stores + summary: Create a vector store file by attaching a [File](/docs/api-reference/files) to a [vector store](/docs/api-reference/vector-stores/object). + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + example: vs_abc123 + description: | + The ID of the vector store for which to create a File. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateVectorStoreFileRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/VectorStoreFileObject" + x-oaiMeta: + name: Create vector store file + group: vector_stores + beta: true + returns: A [vector store file](/docs/api-reference/vector-stores-files/file-object) object. + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores/vs_abc123/files \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "file_id": "file-abc123" + }' + python: | + from openai import OpenAI + client = OpenAI() + + vector_store_file = client.beta.vector_stores.files.create( + vector_store_id="vs_abc123", + file_id="file-abc123" + ) + print(vector_store_file) + node.js: | + import OpenAI from "openai"; + const openai = new OpenAI(); + + async function main() { + const myVectorStoreFile = await openai.beta.vectorStores.files.create( + "vs_abc123", + { + file_id: "file-abc123" + } + ); + console.log(myVectorStoreFile); + } + + main(); + response: | + { + "id": "file-abc123", + "object": "vector_store.file", + "created_at": 1699061776, + "usage_bytes": 1234, + "vector_store_id": "vs_abcd", + "status": "completed", + "last_error": null + } + + /vector_stores/{vector_store_id}/files/{file_id}: + get: + operationId: getVectorStoreFile + tags: + - Vector Stores + summary: Retrieves a vector store file. + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + example: vs_abc123 + description: The ID of the vector store that the file belongs to. + - in: path + name: file_id + required: true + schema: + type: string + example: file-abc123 + description: The ID of the file being retrieved. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/VectorStoreFileObject" + x-oaiMeta: + name: Retrieve vector store file + group: vector_stores + beta: true + returns: The [vector store file](/docs/api-reference/vector-stores-files/file-object) object. + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores/vs_abc123/files/file-abc123 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + vector_store_file = client.beta.vector_stores.files.retrieve( + vector_store_id="vs_abc123", + file_id="file-abc123" + ) + print(vector_store_file) + node.js: | + import OpenAI from "openai"; + const openai = new OpenAI(); + + async function main() { + const vectorStoreFile = await openai.beta.vectorStores.files.retrieve( + "vs_abc123", + "file-abc123" + ); + console.log(vectorStoreFile); + } + + main(); + response: | + { + "id": "file-abc123", + "object": "vector_store.file", + "created_at": 1699061776, + "vector_store_id": "vs_abcd", + "status": "completed", + "last_error": null + } + delete: + operationId: deleteVectorStoreFile + tags: + - Vector Stores + summary: Delete a vector store file. This will remove the file from the vector store but the file itself will not be deleted. To delete the file, use the [delete file](/docs/api-reference/files/delete) endpoint. + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + description: The ID of the vector store that the file belongs to. + - in: path + name: file_id + required: true + schema: + type: string + description: The ID of the file to delete. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/DeleteVectorStoreFileResponse" + x-oaiMeta: + name: Delete vector store file + group: vector_stores + beta: true + returns: Deletion status + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores/vs_abc123/files/file-abc123 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -X DELETE + python: | + from openai import OpenAI + client = OpenAI() + + deleted_vector_store_file = client.beta.vector_stores.files.delete( + vector_store_id="vs_abc123", + file_id="file-abc123" + ) + print(deleted_vector_store_file) + node.js: | + import OpenAI from "openai"; + const openai = new OpenAI(); + + async function main() { + const deletedVectorStoreFile = await openai.beta.vectorStores.files.del( + "vs_abc123", + "file-abc123" + ); + console.log(deletedVectorStoreFile); + } + + main(); + response: | + { + id: "file-abc123", + object: "vector_store.file.deleted", + deleted: true + } + + /vector_stores/{vector_store_id}/file_batches: + post: + operationId: createVectorStoreFileBatch + tags: + - Vector Stores + summary: Create a vector store file batch. + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + example: vs_abc123 + description: | + The ID of the vector store for which to create a File Batch. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateVectorStoreFileBatchRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/VectorStoreFileBatchObject" + x-oaiMeta: + name: Create vector store file batch + group: vector_stores + beta: true + returns: A [vector store file batch](/docs/api-reference/vector-stores-file-batches/batch-object) object. + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores/vs_abc123/file_batches \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "file_ids": ["file-abc123", "file-abc456"] + }' + python: | + from openai import OpenAI + client = OpenAI() + + vector_store_file_batch = client.beta.vector_stores.file_batches.create( + vector_store_id="vs_abc123", + file_ids=["file-abc123", "file-abc456"] + ) + print(vector_store_file_batch) + node.js: | + import OpenAI from "openai"; + const openai = new OpenAI(); + + async function main() { + const myVectorStoreFileBatch = await openai.beta.vectorStores.fileBatches.create( + "vs_abc123", + { + file_ids: ["file-abc123", "file-abc456"] + } + ); + console.log(myVectorStoreFileBatch); + } + + main(); + response: | + { + "id": "vsfb_abc123", + "object": "vector_store.file_batch", + "created_at": 1699061776, + "vector_store_id": "vs_abc123", + "status": "in_progress", + "file_counts": { + "in_progress": 1, + "completed": 1, + "failed": 0, + "cancelled": 0, + "total": 0, + } + } + + /vector_stores/{vector_store_id}/file_batches/{batch_id}: + get: + operationId: getVectorStoreFileBatch + tags: + - Vector Stores + summary: Retrieves a vector store file batch. + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + example: vs_abc123 + description: The ID of the vector store that the file batch belongs to. + - in: path + name: batch_id + required: true + schema: + type: string + example: vsfb_abc123 + description: The ID of the file batch being retrieved. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/VectorStoreFileBatchObject" + x-oaiMeta: + name: Retrieve vector store file batch + group: vector_stores + beta: true + returns: The [vector store file batch](/docs/api-reference/vector-stores-file-batches/batch-object) object. + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores/vs_abc123/files_batches/vsfb_abc123 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + vector_store_file_batch = client.beta.vector_stores.file_batches.retrieve( + vector_store_id="vs_abc123", + batch_id="vsfb_abc123" + ) + print(vector_store_file_batch) + node.js: | + import OpenAI from "openai"; + const openai = new OpenAI(); + + async function main() { + const vectorStoreFileBatch = await openai.beta.vectorStores.fileBatches.retrieve( + "vs_abc123", + "vsfb_abc123" + ); + console.log(vectorStoreFileBatch); + } + + main(); + response: | + { + "id": "vsfb_abc123", + "object": "vector_store.file_batch", + "created_at": 1699061776, + "vector_store_id": "vs_abc123", + "status": "in_progress", + "file_counts": { + "in_progress": 1, + "completed": 1, + "failed": 0, + "cancelled": 0, + "total": 0, + } + } + + /vector_stores/{vector_store_id}/file_batches/{batch_id}/cancel: + post: + operationId: cancelVectorStoreFileBatch + tags: + - Vector Stores + summary: Cancel a vector store file batch. This attempts to cancel the processing of files in this batch as soon as possible. + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + description: The ID of the vector store that the file batch belongs to. + - in: path + name: batch_id + required: true + schema: + type: string + description: The ID of the file batch to cancel. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/VectorStoreFileBatchObject" + x-oaiMeta: + name: Cancel vector store file batch + group: vector_stores + beta: true + returns: The modified vector store file batch object. + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores/vs_abc123/files_batches/vsfb_abc123/cancel \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -X POST + python: | + from openai import OpenAI + client = OpenAI() + + deleted_vector_store_file_batch = client.beta.vector_stores.file_batches.cancel( + vector_store_id="vs_abc123", + file_batch_id="vsfb_abc123" + ) + print(deleted_vector_store_file_batch) + node.js: | + import OpenAI from "openai"; + const openai = new OpenAI(); + + async function main() { + const deletedVectorStoreFileBatch = await openai.vector_stores.fileBatches.cancel( + "vs_abc123", + "vsfb_abc123" + ); + console.log(deletedVectorStoreFileBatch); + } + + main(); + response: | + { + "id": "vsfb_abc123", + "object": "vector_store.file_batch", + "created_at": 1699061776, + "vector_store_id": "vs_abc123", + "status": "cancelling", + "file_counts": { + "in_progress": 12, + "completed": 3, + "failed": 0, + "cancelled": 0, + "total": 15, + } + } + + /vector_stores/{vector_store_id}/file_batches/{batch_id}/files: + get: + operationId: listFilesInVectorStoreBatch + tags: + - Vector Stores + summary: Returns a list of vector store files in a batch. + parameters: + - name: vector_store_id + in: path + description: The ID of the vector store that the files belong to. + required: true + schema: + type: string + - name: batch_id + in: path + description: The ID of the file batch that the files belong to. + required: true + schema: + type: string + - name: limit + in: query + description: *pagination_limit_param_description + required: false + schema: + type: integer + default: 20 + - name: order + in: query + description: *pagination_order_param_description + schema: + type: string + default: desc + enum: ["asc", "desc"] + - name: after + in: query + description: *pagination_after_param_description + schema: + type: string + - name: before + in: query + description: *pagination_before_param_description + schema: + type: string + - name: filter + in: query + description: "Filter by file status. One of `in_progress`, `completed`, `failed`, `cancelled`." + schema: + type: string + enum: ["in_progress", "completed", "failed", "cancelled"] + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListVectorStoreFilesResponse" + x-oaiMeta: + name: List vector store files in a batch + group: vector_stores + beta: true + returns: A list of [vector store file](/docs/api-reference/vector-stores-files/file-object) objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores/vs_abc123/files_batches/vsfb_abc123/files \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + vector_store_files = client.beta.vector_stores.file_batches.list_files( + vector_store_id="vs_abc123", + batch_id="vsfb_abc123" + ) + print(vector_store_files) + node.js: | + import OpenAI from "openai"; + const openai = new OpenAI(); + + async function main() { + const vectorStoreFiles = await openai.beta.vectorStores.fileBatches.listFiles( + "vs_abc123", + "vsfb_abc123" + ); + console.log(vectorStoreFiles); + } + + main(); + response: | + { + "object": "list", + "data": [ + { + "id": "file-abc123", + "object": "vector_store.file", + "created_at": 1699061776, + "vector_store_id": "vs_abc123" + }, + { + "id": "file-abc456", + "object": "vector_store.file", + "created_at": 1699061776, + "vector_store_id": "vs_abc123" + } + ], + "first_id": "file-abc123", + "last_id": "file-abc456", + "has_more": false + } + + /batches: + post: + summary: Creates and executes a batch from an uploaded file of requests + operationId: createBatch + tags: + - Batch + requestBody: + required: true + content: + application/json: + schema: + type: object + required: + - input_file_id + - endpoint + - completion_window + properties: + input_file_id: + type: string + description: | + The ID of an uploaded file that contains requests for the new batch. + + See [upload file](/docs/api-reference/files/create) for how to upload a file. + + Your input file must be formatted as a [JSONL file](/docs/api-reference/batch/requestInput), and must be uploaded with the purpose `batch`. The file can contain up to 50,000 requests, and can be up to 100 MB in size. + endpoint: + type: string + enum: ["/v1/chat/completions", "/v1/embeddings", "/v1/completions"] + description: The endpoint to be used for all requests in the batch. Currently `/v1/chat/completions`, `/v1/embeddings`, and `/v1/completions` are supported. Note that `/v1/embeddings` batches are also restricted to a maximum of 50,000 embedding inputs across all requests in the batch. + completion_window: + type: string + enum: ["24h"] + description: The time frame within which the batch should be processed. Currently only `24h` is supported. + metadata: + type: object + additionalProperties: + type: string + description: Optional custom metadata for the batch. + nullable: true + responses: + "200": + description: Batch created successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/Batch" + x-oaiMeta: + name: Create batch + group: batch + returns: The created [Batch](/docs/api-reference/batch/object) object. + examples: + request: + curl: | + curl https://api.openai.com/v1/batches \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "input_file_id": "file-abc123", + "endpoint": "/v1/chat/completions", + "completion_window": "24h" + }' + python: | + from openai import OpenAI + client = OpenAI() + + client.batches.create( + input_file_id="file-abc123", + endpoint="/v1/chat/completions", + completion_window="24h" + ) + node: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const batch = await openai.batches.create({ + input_file_id: "file-abc123", + endpoint: "/v1/chat/completions", + completion_window: "24h" + }); + + console.log(batch); + } + + main(); + response: | + { + "id": "batch_abc123", + "object": "batch", + "endpoint": "/v1/chat/completions", + "errors": null, + "input_file_id": "file-abc123", + "completion_window": "24h", + "status": "validating", + "output_file_id": null, + "error_file_id": null, + "created_at": 1711471533, + "in_progress_at": null, + "expires_at": null, + "finalizing_at": null, + "completed_at": null, + "failed_at": null, + "expired_at": null, + "cancelling_at": null, + "cancelled_at": null, + "request_counts": { + "total": 0, + "completed": 0, + "failed": 0 + }, + "metadata": { + "customer_id": "user_123456789", + "batch_description": "Nightly eval job", + } + } + get: + operationId: listBatches + tags: + - Batch + summary: List your organization's batches. + parameters: + - in: query + name: after + required: false + schema: + type: string + description: *pagination_after_param_description + - name: limit + in: query + description: *pagination_limit_param_description + required: false + schema: + type: integer + default: 20 + responses: + "200": + description: Batch listed successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ListBatchesResponse" + x-oaiMeta: + name: List batch + group: batch + returns: A list of paginated [Batch](/docs/api-reference/batch/object) objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/batches?limit=2 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" + python: | + from openai import OpenAI + client = OpenAI() + + client.batches.list() + node: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const list = await openai.batches.list(); + + for await (const batch of list) { + console.log(batch); + } + } + + main(); + response: | + { + "object": "list", + "data": [ + { + "id": "batch_abc123", + "object": "batch", + "endpoint": "/v1/chat/completions", + "errors": null, + "input_file_id": "file-abc123", + "completion_window": "24h", + "status": "completed", + "output_file_id": "file-cvaTdG", + "error_file_id": "file-HOWS94", + "created_at": 1711471533, + "in_progress_at": 1711471538, + "expires_at": 1711557933, + "finalizing_at": 1711493133, + "completed_at": 1711493163, + "failed_at": null, + "expired_at": null, + "cancelling_at": null, + "cancelled_at": null, + "request_counts": { + "total": 100, + "completed": 95, + "failed": 5 + }, + "metadata": { + "customer_id": "user_123456789", + "batch_description": "Nightly job", + } + }, + { ... }, + ], + "first_id": "batch_abc123", + "last_id": "batch_abc456", + "has_more": true + } + + /batches/{batch_id}: + get: + operationId: retrieveBatch + tags: + - Batch + summary: Retrieves a batch. + parameters: + - in: path + name: batch_id + required: true + schema: + type: string + description: The ID of the batch to retrieve. + responses: + "200": + description: Batch retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/Batch" + x-oaiMeta: + name: Retrieve batch + group: batch + returns: The [Batch](/docs/api-reference/batch/object) object matching the specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/batches/batch_abc123 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + python: | + from openai import OpenAI + client = OpenAI() + + client.batches.retrieve("batch_abc123") + node: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const batch = await openai.batches.retrieve("batch_abc123"); + + console.log(batch); + } + + main(); + response: &batch_object | + { + "id": "batch_abc123", + "object": "batch", + "endpoint": "/v1/completions", + "errors": null, + "input_file_id": "file-abc123", + "completion_window": "24h", + "status": "completed", + "output_file_id": "file-cvaTdG", + "error_file_id": "file-HOWS94", + "created_at": 1711471533, + "in_progress_at": 1711471538, + "expires_at": 1711557933, + "finalizing_at": 1711493133, + "completed_at": 1711493163, + "failed_at": null, + "expired_at": null, + "cancelling_at": null, + "cancelled_at": null, + "request_counts": { + "total": 100, + "completed": 95, + "failed": 5 + }, + "metadata": { + "customer_id": "user_123456789", + "batch_description": "Nightly eval job", + } + } + + /batches/{batch_id}/cancel: + post: + operationId: cancelBatch + tags: + - Batch + summary: Cancels an in-progress batch. + parameters: + - in: path + name: batch_id + required: true + schema: + type: string + description: The ID of the batch to cancel. + responses: + "200": + description: Batch is cancelling. Returns the cancelling batch's details. + content: + application/json: + schema: + $ref: "#/components/schemas/Batch" + x-oaiMeta: + name: Cancel batch + group: batch + returns: The [Batch](/docs/api-reference/batch/object) object matching the specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/batches/batch_abc123/cancel \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -X POST + python: | + from openai import OpenAI + client = OpenAI() + + client.batches.cancel("batch_abc123") + node: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const batch = await openai.batches.cancel("batch_abc123"); + + console.log(batch); + } + + main(); + response: | + { + "id": "batch_abc123", + "object": "batch", + "endpoint": "/v1/chat/completions", + "errors": null, + "input_file_id": "file-abc123", + "completion_window": "24h", + "status": "cancelling", + "output_file_id": null, + "error_file_id": null, + "created_at": 1711471533, + "in_progress_at": 1711471538, + "expires_at": 1711557933, + "finalizing_at": null, + "completed_at": null, + "failed_at": null, + "expired_at": null, + "cancelling_at": 1711475133, + "cancelled_at": null, + "request_counts": { + "total": 100, + "completed": 23, + "failed": 1 + }, + "metadata": { + "customer_id": "user_123456789", + "batch_description": "Nightly eval job", + } + } + +components: + securitySchemes: + ApiKeyAuth: + type: http + scheme: "bearer" + + schemas: + Error: + type: object + properties: + code: + type: string + nullable: true + message: + type: string + nullable: false + param: + type: string + nullable: true + type: + type: string + nullable: false + required: + - type + - message + - param + - code + ErrorResponse: + type: object + properties: + error: + $ref: "#/components/schemas/Error" + required: + - error + + ListModelsResponse: + type: object + properties: + object: + type: string + enum: [list] + data: + type: array + items: + $ref: "#/components/schemas/Model" + required: + - object + - data + DeleteModelResponse: + type: object + properties: + id: + type: string + deleted: + type: boolean + object: + type: string + required: + - id + - object + - deleted + + CreateCompletionRequest: + type: object + properties: + model: + description: &model_description | + ID of the model to use. You can use the [List models](/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](/docs/models/overview) for descriptions of them. + anyOf: + - type: string + - type: string + enum: ["gpt-3.5-turbo-instruct", "davinci-002", "babbage-002"] + x-oaiTypeLabel: string + prompt: + description: &completions_prompt_description | + The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays. + + Note that <|endoftext|> is the document separator that the model sees during training, so if a prompt is not specified the model will generate as if from the beginning of a new document. + default: "<|endoftext|>" + nullable: true + oneOf: + - type: string + default: "" + example: "This is a test." + - type: array + items: + type: string + default: "" + example: "This is a test." + - type: array + minItems: 1 + items: + type: integer + example: "[1212, 318, 257, 1332, 13]" + - type: array + minItems: 1 + items: + type: array + minItems: 1 + items: + type: integer + example: "[[1212, 318, 257, 1332, 13]]" + best_of: + type: integer + default: 1 + minimum: 0 + maximum: 20 + nullable: true + description: &completions_best_of_description | + Generates `best_of` completions server-side and returns the "best" (the one with the highest log probability per token). Results cannot be streamed. When used with `n`, `best_of` controls the number of candidate completions and `n` specifies how many to return – `best_of` must be greater than `n`. - **Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for `max_tokens` and `stop`. - echo: + **Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for `max_tokens` and `stop`. + echo: + type: boolean + default: false + nullable: true + description: &completions_echo_description > + Echo back the prompt in addition to the completion + frequency_penalty: + type: number + default: 0 + minimum: -2 + maximum: 2 + nullable: true + description: &completions_frequency_penalty_description | + Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. + + [See more information about frequency and presence penalties.](/docs/guides/text-generation/parameter-details) + logit_bias: &completions_logit_bias + type: object + x-oaiTypeLabel: map + default: null + nullable: true + additionalProperties: + type: integer + description: &completions_logit_bias_description | + Modify the likelihood of specified tokens appearing in the completion. + + Accepts a JSON object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this [tokenizer tool](/tokenizer?view=bpe) to convert text to token IDs. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. + + As an example, you can pass `{"50256": -100}` to prevent the <|endoftext|> token from being generated. + logprobs: &completions_logprobs_configuration + type: integer + minimum: 0 + maximum: 5 + default: null + nullable: true + description: &completions_logprobs_description | + Include the log probabilities on the `logprobs` most likely output tokens, as well the chosen tokens. For example, if `logprobs` is 5, the API will return a list of the 5 most likely tokens. The API will always return the `logprob` of the sampled token, so there may be up to `logprobs+1` elements in the response. + + The maximum value for `logprobs` is 5. + max_tokens: + type: integer + minimum: 0 + default: 16 + example: 16 + nullable: true + description: &completions_max_tokens_description | + The maximum number of [tokens](/tokenizer) that can be generated in the completion. + + The token count of your prompt plus `max_tokens` cannot exceed the model's context length. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens. + n: + type: integer + minimum: 1 + maximum: 128 + default: 1 + example: 1 + nullable: true + description: &completions_completions_description | + How many completions to generate for each prompt. + + **Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for `max_tokens` and `stop`. + presence_penalty: + type: number + default: 0 + minimum: -2 + maximum: 2 + nullable: true + description: &completions_presence_penalty_description | + Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. + + [See more information about frequency and presence penalties.](/docs/guides/text-generation/parameter-details) + seed: &completions_seed_param + type: integer + minimum: -9223372036854775808 + maximum: 9223372036854775807 + nullable: true + description: | + If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result. + + Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend. + stop: + description: &completions_stop_description > + Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence. + default: null + nullable: true + oneOf: + - type: string + default: <|endoftext|> + example: "\n" + nullable: true + - type: array + minItems: 1 + maxItems: 4 + items: + type: string + example: '["\n"]' + stream: + description: > + Whether to stream back partial progress. If set, tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) + as they become available, with the stream terminated by a `data: [DONE]` message. [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions). + type: boolean + nullable: true + default: false + stream_options: + $ref: "#/components/schemas/ChatCompletionStreamOptions" + suffix: + description: | + The suffix that comes after a completion of inserted text. + + This parameter is only supported for `gpt-3.5-turbo-instruct`. + default: null + nullable: true + type: string + example: "test." + temperature: + type: number + minimum: 0 + maximum: 2 + default: 1 + example: 1 + nullable: true + description: &completions_temperature_description | + What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. + + We generally recommend altering this or `top_p` but not both. + top_p: + type: number + minimum: 0 + maximum: 1 + default: 1 + example: 1 + nullable: true + description: &completions_top_p_description | + An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. + + We generally recommend altering this or `temperature` but not both. + user: &end_user_param_configuration + type: string + example: user-1234 + description: | + A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices/end-user-ids). + required: + - model + - prompt + + CreateCompletionResponse: + type: object + description: | + Represents a completion response from the API. Note: both the streamed and non-streamed response objects share the same shape (unlike the chat endpoint). + properties: + id: + type: string + description: A unique identifier for the completion. + choices: + type: array + description: The list of completion choices the model generated for the input prompt. + items: + type: object + required: + - finish_reason + - index + - logprobs + - text + properties: + finish_reason: + type: string + description: &completion_finish_reason_description | + The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, + `length` if the maximum number of tokens specified in the request was reached, + or `content_filter` if content was omitted due to a flag from our content filters. + enum: ["stop", "length", "content_filter"] + index: + type: integer + logprobs: + type: object + nullable: true + properties: + text_offset: + type: array + items: + type: integer + token_logprobs: + type: array + items: + type: number + tokens: + type: array + items: + type: string + top_logprobs: + type: array + items: + type: object + additionalProperties: + type: number + text: + type: string + created: + type: integer + description: The Unix timestamp (in seconds) of when the completion was created. + model: + type: string + description: The model used for completion. + system_fingerprint: + type: string + description: | + This fingerprint represents the backend configuration that the model runs with. + + Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism. + object: + type: string + description: The object type, which is always "text_completion" + enum: [text_completion] + usage: + $ref: "#/components/schemas/CompletionUsage" + required: + - id + - object + - created + - model + - choices + x-oaiMeta: + name: The completion object + legacy: true + example: | + { + "id": "cmpl-uqkvlQyYK7bGYrRHQ0eXlWi7", + "object": "text_completion", + "created": 1589478378, + "model": "gpt-4-turbo", + "choices": [ + { + "text": "\n\nThis is indeed a test", + "index": 0, + "logprobs": null, + "finish_reason": "length" + } + ], + "usage": { + "prompt_tokens": 5, + "completion_tokens": 7, + "total_tokens": 12 + } + } + + ChatCompletionRequestMessageContentPart: + oneOf: + - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartText" + - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartImage" + x-oaiExpandable: true + + ChatCompletionRequestMessageContentPartImage: + type: object + title: Image content part + properties: + type: + type: string + enum: ["image_url"] + description: The type of the content part. + image_url: + type: object + properties: + url: + type: string + description: Either a URL of the image or the base64 encoded image data. + format: uri + detail: + type: string + description: Specifies the detail level of the image. Learn more in the [Vision guide](/docs/guides/vision/low-or-high-fidelity-image-understanding). + enum: ["auto", "low", "high"] + default: "auto" + required: + - url + required: + - type + - image_url + + ChatCompletionRequestMessageContentPartText: + type: object + title: Text content part + properties: + type: + type: string + enum: ["text"] + description: The type of the content part. + text: + type: string + description: The text content. + required: + - type + - text + + ChatCompletionRequestMessage: + oneOf: + - $ref: "#/components/schemas/ChatCompletionRequestSystemMessage" + - $ref: "#/components/schemas/ChatCompletionRequestUserMessage" + - $ref: "#/components/schemas/ChatCompletionRequestAssistantMessage" + - $ref: "#/components/schemas/ChatCompletionRequestToolMessage" + - $ref: "#/components/schemas/ChatCompletionRequestFunctionMessage" + x-oaiExpandable: true + + ChatCompletionRequestSystemMessage: + type: object + title: System message + properties: + content: + description: The contents of the system message. + type: string + role: + type: string + enum: ["system"] + description: The role of the messages author, in this case `system`. + name: + type: string + description: An optional name for the participant. Provides the model information to differentiate between participants of the same role. + required: + - content + - role + + ChatCompletionRequestUserMessage: + type: object + title: User message + properties: + content: + description: | + The contents of the user message. + oneOf: + - type: string + description: The text contents of the message. + title: Text content + - type: array + description: An array of content parts with a defined type, each can be of type `text` or `image_url` when passing in images. You can pass multiple images by adding multiple `image_url` content parts. Image input is only supported when using the `gpt-4-visual-preview` model. + title: Array of content parts + items: + $ref: "#/components/schemas/ChatCompletionRequestMessageContentPart" + minItems: 1 + x-oaiExpandable: true + role: + type: string + enum: ["user"] + description: The role of the messages author, in this case `user`. + name: + type: string + description: An optional name for the participant. Provides the model information to differentiate between participants of the same role. + required: + - content + - role + + ChatCompletionRequestAssistantMessage: + type: object + title: Assistant message + properties: + content: + nullable: true + type: string + description: | + The contents of the assistant message. Required unless `tool_calls` or `function_call` is specified. + role: + type: string + enum: ["assistant"] + description: The role of the messages author, in this case `assistant`. + name: + type: string + description: An optional name for the participant. Provides the model information to differentiate between participants of the same role. + tool_calls: + $ref: "#/components/schemas/ChatCompletionMessageToolCalls" + function_call: + type: object + deprecated: true + description: "Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model." + properties: + arguments: + type: string + description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. + name: + type: string + description: The name of the function to call. + required: + - arguments + - name + required: + - role + + ChatCompletionRequestToolMessage: + type: object + title: Tool message + properties: + role: + type: string + enum: ["tool"] + description: The role of the messages author, in this case `tool`. + content: + type: string + description: The contents of the tool message. + tool_call_id: + type: string + description: Tool call that this message is responding to. + required: + - role + - content + - tool_call_id + + ChatCompletionRequestFunctionMessage: + type: object + title: Function message + deprecated: true + properties: + role: + type: string + enum: ["function"] + description: The role of the messages author, in this case `function`. + content: + nullable: true + type: string + description: The contents of the function message. + name: + type: string + description: The name of the function to call. + required: + - role + - content + - name + + FunctionParameters: + type: object + description: "The parameters the functions accepts, described as a JSON Schema object. See the [guide](/docs/guides/text-generation/function-calling) for examples, and the [JSON Schema reference](https://json-schema.org/understanding-json-schema/) for documentation about the format. \n\nOmitting `parameters` defines a function with an empty parameter list." + additionalProperties: true + + ChatCompletionFunctions: + type: object + deprecated: true + properties: + description: + type: string + description: A description of what the function does, used by the model to choose when and how to call the function. + name: + type: string + description: The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. + parameters: + $ref: "#/components/schemas/FunctionParameters" + required: + - name + + ChatCompletionFunctionCallOption: + type: object + description: > + Specifying a particular function via `{"name": "my_function"}` forces the model to call that function. + properties: + name: + type: string + description: The name of the function to call. + required: + - name + + ChatCompletionTool: + type: object + properties: + type: + type: string + enum: ["function"] + description: The type of the tool. Currently, only `function` is supported. + function: + $ref: "#/components/schemas/FunctionObject" + required: + - type + - function + + FunctionObject: + type: object + properties: + description: + type: string + description: A description of what the function does, used by the model to choose when and how to call the function. + name: + type: string + description: The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. + parameters: + $ref: "#/components/schemas/FunctionParameters" + required: + - name + + ChatCompletionToolChoiceOption: + description: | + Controls which (if any) tool is called by the model. + `none` means the model will not call any tool and instead generates a message. + `auto` means the model can pick between generating a message or calling one or more tools. + `required` means the model must call one or more tools. + Specifying a particular tool via `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that tool. + + `none` is the default when no tools are present. `auto` is the default if tools are present. + oneOf: + - type: string + description: > + `none` means the model will not call any tool and instead generates a message. + `auto` means the model can pick between generating a message or calling one or more tools. + `required` means the model must call one or more tools. + enum: [none, auto, required] + - $ref: "#/components/schemas/ChatCompletionNamedToolChoice" + x-oaiExpandable: true + + ChatCompletionNamedToolChoice: + type: object + description: Specifies a tool the model should use. Use to force the model to call a specific function. + properties: + type: + type: string + enum: ["function"] + description: The type of the tool. Currently, only `function` is supported. + function: + type: object + properties: + name: + type: string + description: The name of the function to call. + required: + - name + required: + - type + - function + + ChatCompletionMessageToolCalls: + type: array + description: The tool calls generated by the model, such as function calls. + items: + $ref: "#/components/schemas/ChatCompletionMessageToolCall" + + ChatCompletionMessageToolCall: + type: object + properties: + # TODO: index included when streaming + id: + type: string + description: The ID of the tool call. + type: + type: string + enum: ["function"] + description: The type of the tool. Currently, only `function` is supported. + function: + type: object + description: The function that the model called. + properties: + name: + type: string + description: The name of the function to call. + arguments: + type: string + description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. + required: + - name + - arguments + required: + - id + - type + - function + + ChatCompletionMessageToolCallChunk: + type: object + properties: + index: + type: integer + id: + type: string + description: The ID of the tool call. + type: + type: string + enum: ["function"] + description: The type of the tool. Currently, only `function` is supported. + function: + type: object + properties: + name: + type: string + description: The name of the function to call. + arguments: + type: string + description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. + required: + - index + + # Note, this isn't referenced anywhere, but is kept as a convenience to record all possible roles in one place. + ChatCompletionRole: + type: string + description: The role of the author of a message + enum: + - system + - user + - assistant + - tool + - function + + ChatCompletionStreamOptions: + description: | + Options for streaming response. Only set this when you set `stream: true`. + type: object + nullable: true + default: null + properties: + include_usage: type: boolean - default: false + description: | + If set, an additional chunk will be streamed before the `data: [DONE]` message. The `usage` field on this chunk shows the token usage statistics for the entire request, and the `choices` field will always be an empty array. All other chunks will also include a `usage` field, but with a null value. + + ChatCompletionResponseMessage: + type: object + description: A chat completion message generated by the model. + properties: + content: + type: string + description: The contents of the message. nullable: true - description: &completions_echo_description > - Echo back the prompt in addition to the completion + tool_calls: + $ref: "#/components/schemas/ChatCompletionMessageToolCalls" + role: + type: string + enum: ["assistant"] + description: The role of the author of this message. + function_call: + type: object + deprecated: true + description: "Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model." + properties: + arguments: + type: string + description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. + name: + type: string + description: The name of the function to call. + required: + - name + - arguments + required: + - role + - content + + ChatCompletionStreamResponseDelta: + type: object + description: A chat completion delta generated by streamed model responses. + properties: + content: + type: string + description: The contents of the chunk message. + nullable: true + function_call: + deprecated: true + type: object + description: "Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model." + properties: + arguments: + type: string + description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. + name: + type: string + description: The name of the function to call. + tool_calls: + type: array + items: + $ref: "#/components/schemas/ChatCompletionMessageToolCallChunk" + role: + type: string + enum: ["system", "user", "assistant", "tool"] + description: The role of the author of this message. + + CreateChatCompletionRequest: + type: object + properties: + messages: + description: A list of messages comprising the conversation so far. [Example Python code](https://cookbook.openai.com/examples/how_to_format_inputs_to_chatgpt_models). + type: array + minItems: 1 + items: + $ref: "#/components/schemas/ChatCompletionRequestMessage" + model: + description: ID of the model to use. See the [model endpoint compatibility](/docs/models/model-endpoint-compatibility) table for details on which models work with the Chat API. + example: "gpt-4-turbo" + anyOf: + - type: string + - type: string + enum: + [ + "gpt-4o", + "gpt-4o-2024-05-13", + "gpt-4-turbo", + "gpt-4-turbo-2024-04-09", + "gpt-4-0125-preview", + "gpt-4-turbo-preview", + "gpt-4-1106-preview", + "gpt-4-vision-preview", + "gpt-4", + "gpt-4-0314", + "gpt-4-0613", + "gpt-4-32k", + "gpt-4-32k-0314", + "gpt-4-32k-0613", + "gpt-3.5-turbo", + "gpt-3.5-turbo-16k", + "gpt-3.5-turbo-0301", + "gpt-3.5-turbo-0613", + "gpt-3.5-turbo-1106", + "gpt-3.5-turbo-0125", + "gpt-3.5-turbo-16k-0613", + ] + x-oaiTypeLabel: string frequency_penalty: type: number default: 0 minimum: -2 maximum: 2 nullable: true - description: &completions_frequency_penalty_description | - Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. - - [See more information about frequency and presence penalties.](/docs/guides/text-generation/parameter-details) - logit_bias: &completions_logit_bias + description: *completions_frequency_penalty_description + logit_bias: type: object x-oaiTypeLabel: map default: null nullable: true additionalProperties: type: integer - description: &completions_logit_bias_description | + description: | Modify the likelihood of specified tokens appearing in the completion. - Accepts a JSON object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this [tokenizer tool](/tokenizer?view=bpe) to convert text to token IDs. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. - - As an example, you can pass `{"50256": -100}` to prevent the <|endoftext|> token from being generated. - logprobs: &completions_logprobs_configuration + Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. + logprobs: + description: Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the `content` of `message`. + type: boolean + default: false + nullable: true + top_logprobs: + description: An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. `logprobs` must be set to `true` if this parameter is used. type: integer minimum: 0 - maximum: 5 - default: null + maximum: 20 nullable: true - description: &completions_logprobs_description | - Include the log probabilities on the `logprobs` most likely output tokens, as well the chosen tokens. For example, if `logprobs` is 5, the API will return a list of the 5 most likely tokens. The API will always return the `logprob` of the sampled token, so there may be up to `logprobs+1` elements in the response. - - The maximum value for `logprobs` is 5. max_tokens: + description: | + The maximum number of [tokens](/tokenizer) that can be generated in the chat completion. + + The total length of input tokens and generated tokens is limited by the model's context length. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens. type: integer - minimum: 0 - default: 16 - example: 16 nullable: true - description: &completions_max_tokens_description | - The maximum number of [tokens](/tokenizer) that can be generated in the completion. - - The token count of your prompt plus `max_tokens` cannot exceed the model's context length. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens. n: type: integer minimum: 1 @@ -5188,2150 +7858,3153 @@ components: default: 1 example: 1 nullable: true - description: &completions_completions_description | - How many completions to generate for each prompt. - - **Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for `max_tokens` and `stop`. + description: How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep `n` as `1` to minimize costs. presence_penalty: type: number default: 0 minimum: -2 maximum: 2 nullable: true - description: &completions_presence_penalty_description | - Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. + description: *completions_presence_penalty_description + response_format: + type: object + description: | + An object specifying the format that the model must output. Compatible with [GPT-4 Turbo](/docs/models/gpt-4-and-gpt-4-turbo) and all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`. - [See more information about frequency and presence penalties.](/docs/guides/text-generation/parameter-details) - seed: &completions_seed_param + Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the message the model generates is valid JSON. + + **Important:** when using JSON mode, you **must** also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if `finish_reason="length"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length. + properties: + type: + type: string + enum: ["text", "json_object"] + example: "json_object" + default: "text" + description: Must be one of `text` or `json_object`. + seed: type: integer minimum: -9223372036854775808 maximum: 9223372036854775807 nullable: true description: | + This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result. - Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend. + x-oaiMeta: + beta: true stop: - description: &completions_stop_description > - Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence. + description: | + Up to 4 sequences where the API will stop generating further tokens. default: null - nullable: true oneOf: - type: string - default: <|endoftext|> - example: "\n" nullable: true - type: array minItems: 1 maxItems: 4 items: type: string - example: '["\n"]' stream: description: > - Whether to stream back partial progress. If set, tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) + If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]` message. [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions). type: boolean nullable: true default: false - suffix: - description: The suffix that comes after a completion of inserted text. - default: null + stream_options: + $ref: "#/components/schemas/ChatCompletionStreamOptions" + temperature: + type: number + minimum: 0 + maximum: 2 + default: 1 + example: 1 + nullable: true + description: *completions_temperature_description + top_p: + type: number + minimum: 0 + maximum: 1 + default: 1 + example: 1 nullable: true + description: *completions_top_p_description + tools: + type: array + description: > + A list of tools the model may call. Currently, only functions are supported as a tool. + Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported. + items: + $ref: "#/components/schemas/ChatCompletionTool" + tool_choice: + $ref: "#/components/schemas/ChatCompletionToolChoiceOption" + user: *end_user_param_configuration + function_call: + deprecated: true + description: | + Deprecated in favor of `tool_choice`. + + Controls which (if any) function is called by the model. + `none` means the model will not call a function and instead generates a message. + `auto` means the model can pick between generating a message or calling a function. + Specifying a particular function via `{"name": "my_function"}` forces the model to call that function. + + `none` is the default when no functions are present. `auto` is the default if functions are present. + oneOf: + - type: string + description: > + `none` means the model will not call a function and instead generates a message. + `auto` means the model can pick between generating a message or calling a function. + enum: [none, auto] + - $ref: "#/components/schemas/ChatCompletionFunctionCallOption" + x-oaiExpandable: true + functions: + deprecated: true + description: | + Deprecated in favor of `tools`. + + A list of functions the model may generate JSON inputs for. + type: array + minItems: 1 + maxItems: 128 + items: + $ref: "#/components/schemas/ChatCompletionFunctions" + + required: + - model + - messages + + CreateChatCompletionResponse: + type: object + description: Represents a chat completion response returned by model, based on the provided input. + properties: + id: + type: string + description: A unique identifier for the chat completion. + choices: + type: array + description: A list of chat completion choices. Can be more than one if `n` is greater than 1. + items: + type: object + required: + - finish_reason + - index + - message + - logprobs + properties: + finish_reason: + type: string + description: &chat_completion_finish_reason_description | + The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, + `length` if the maximum number of tokens specified in the request was reached, + `content_filter` if content was omitted due to a flag from our content filters, + `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function. + enum: + [ + "stop", + "length", + "tool_calls", + "content_filter", + "function_call", + ] + index: + type: integer + description: The index of the choice in the list of choices. + message: + $ref: "#/components/schemas/ChatCompletionResponseMessage" + logprobs: &chat_completion_response_logprobs + description: Log probability information for the choice. + type: object + nullable: true + properties: + content: + description: A list of message content tokens with log probability information. + type: array + items: + $ref: "#/components/schemas/ChatCompletionTokenLogprob" + nullable: true + required: + - content + created: + type: integer + description: The Unix timestamp (in seconds) of when the chat completion was created. + model: + type: string + description: The model used for the chat completion. + system_fingerprint: + type: string + description: | + This fingerprint represents the backend configuration that the model runs with. + + Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism. + object: + type: string + description: The object type, which is always `chat.completion`. + enum: [chat.completion] + usage: + $ref: "#/components/schemas/CompletionUsage" + required: + - choices + - created + - id + - model + - object + x-oaiMeta: + name: The chat completion object + group: chat + example: *chat_completion_example + + CreateChatCompletionFunctionResponse: + type: object + description: Represents a chat completion response returned by model, based on the provided input. + properties: + id: + type: string + description: A unique identifier for the chat completion. + choices: + type: array + description: A list of chat completion choices. Can be more than one if `n` is greater than 1. + items: + type: object + required: + - finish_reason + - index + - message + - logprobs + properties: + finish_reason: + type: string + description: + &chat_completion_function_finish_reason_description | + The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, `length` if the maximum number of tokens specified in the request was reached, `content_filter` if content was omitted due to a flag from our content filters, or `function_call` if the model called a function. + enum: ["stop", "length", "function_call", "content_filter"] + index: + type: integer + description: The index of the choice in the list of choices. + message: + $ref: "#/components/schemas/ChatCompletionResponseMessage" + created: + type: integer + description: The Unix timestamp (in seconds) of when the chat completion was created. + model: + type: string + description: The model used for the chat completion. + system_fingerprint: + type: string + description: | + This fingerprint represents the backend configuration that the model runs with. + + Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism. + object: type: string - example: "test." - temperature: - type: number - minimum: 0 - maximum: 2 - default: 1 - example: 1 - nullable: true - description: &completions_temperature_description | - What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. + description: The object type, which is always `chat.completion`. + enum: [chat.completion] + usage: + $ref: "#/components/schemas/CompletionUsage" + required: + - choices + - created + - id + - model + - object + x-oaiMeta: + name: The chat completion object + group: chat + example: *chat_completion_function_example - We generally recommend altering this or `top_p` but not both. - top_p: + ChatCompletionTokenLogprob: + type: object + properties: + token: &chat_completion_response_logprobs_token + description: The token. + type: string + logprob: &chat_completion_response_logprobs_token_logprob + description: The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value `-9999.0` is used to signify that the token is very unlikely. type: number - minimum: 0 - maximum: 1 - default: 1 - example: 1 + bytes: &chat_completion_response_logprobs_bytes + description: A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be `null` if there is no bytes representation for the token. + type: array + items: + type: integer nullable: true - description: &completions_top_p_description | - An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. + top_logprobs: + description: List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested `top_logprobs` returned. + type: array + items: + type: object + properties: + token: *chat_completion_response_logprobs_token + logprob: *chat_completion_response_logprobs_token_logprob + bytes: *chat_completion_response_logprobs_bytes + required: + - token + - logprob + - bytes + required: + - token + - logprob + - bytes + - top_logprobs - We generally recommend altering this or `temperature` but not both. - user: &end_user_param_configuration + ListPaginatedFineTuningJobsResponse: + type: object + properties: + data: + type: array + items: + $ref: "#/components/schemas/FineTuningJob" + has_more: + type: boolean + object: type: string - example: user-1234 - description: | - A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices/end-user-ids). + enum: [list] required: - - model - - prompt + - object + - data + - has_more - CreateCompletionResponse: + CreateChatCompletionStreamResponse: type: object - description: | - Represents a completion response from the API. Note: both the streamed and non-streamed response objects share the same shape (unlike the chat endpoint). + description: Represents a streamed chunk of a chat completion response returned by model, based on the provided input. properties: id: type: string - description: A unique identifier for the completion. + description: A unique identifier for the chat completion. Each chunk has the same ID. choices: type: array - description: The list of completion choices the model generated for the input prompt. + description: | + A list of chat completion choices. Can contain more than one elements if `n` is greater than 1. Can also be empty for the + last chunk if you set `stream_options: {"include_usage": true}`. items: type: object required: + - delta - finish_reason - index - - logprobs - - text properties: + delta: + $ref: "#/components/schemas/ChatCompletionStreamResponseDelta" + logprobs: *chat_completion_response_logprobs finish_reason: type: string - description: &completion_finish_reason_description | - The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, - `length` if the maximum number of tokens specified in the request was reached, - or `content_filter` if content was omitted due to a flag from our content filters. - enum: ["stop", "length", "content_filter"] + description: *chat_completion_finish_reason_description + enum: + [ + "stop", + "length", + "tool_calls", + "content_filter", + "function_call", + ] + nullable: true index: type: integer - logprobs: - type: object - nullable: true - properties: - text_offset: - type: array - items: - type: integer - token_logprobs: - type: array - items: - type: number - tokens: - type: array - items: - type: string - top_logprobs: - type: array - items: - type: object - additionalProperties: - type: number - text: - type: string + description: The index of the choice in the list of choices. created: type: integer - description: The Unix timestamp (in seconds) of when the completion was created. + description: The Unix timestamp (in seconds) of when the chat completion was created. Each chunk has the same timestamp. model: type: string - description: The model used for completion. + description: The model to generate the completion. system_fingerprint: type: string description: | This fingerprint represents the backend configuration that the model runs with. - Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism. object: type: string - description: The object type, which is always "text_completion" - enum: [text_completion] - usage: - $ref: "#/components/schemas/CompletionUsage" - required: - - id - - object - - created - - model - - choices + description: The object type, which is always `chat.completion.chunk`. + enum: [chat.completion.chunk] + usage: + type: object + description: | + An optional field that will only be present when you set `stream_options: {"include_usage": true}` in your request. + When present, it contains a null value except for the last chunk which contains the token usage statistics for the entire request. + properties: + completion_tokens: + type: integer + description: Number of tokens in the generated completion. + prompt_tokens: + type: integer + description: Number of tokens in the prompt. + total_tokens: + type: integer + description: Total number of tokens used in the request (prompt + completion). + required: + - prompt_tokens + - completion_tokens + - total_tokens + required: + - choices + - created + - id + - model + - object + x-oaiMeta: + name: The chat completion chunk object + group: chat + example: *chat_completion_chunk_example + + CreateChatCompletionImageResponse: + type: object + description: Represents a streamed chunk of a chat completion response returned by model, based on the provided input. + x-oaiMeta: + name: The chat completion chunk object + group: chat + example: *chat_completion_image_example + + CreateImageRequest: + type: object + properties: + prompt: + description: A text description of the desired image(s). The maximum length is 1000 characters for `dall-e-2` and 4000 characters for `dall-e-3`. + type: string + example: "A cute baby sea otter" + model: + anyOf: + - type: string + - type: string + enum: ["dall-e-2", "dall-e-3"] + x-oaiTypeLabel: string + default: "dall-e-2" + example: "dall-e-3" + nullable: true + description: The model to use for image generation. + n: &images_n + type: integer + minimum: 1 + maximum: 10 + default: 1 + example: 1 + nullable: true + description: The number of images to generate. Must be between 1 and 10. For `dall-e-3`, only `n=1` is supported. + quality: + type: string + enum: ["standard", "hd"] + default: "standard" + example: "standard" + description: The quality of the image that will be generated. `hd` creates images with finer details and greater consistency across the image. This param is only supported for `dall-e-3`. + response_format: &images_response_format + type: string + enum: ["url", "b64_json"] + default: "url" + example: "url" + nullable: true + description: The format in which the generated images are returned. Must be one of `url` or `b64_json`. URLs are only valid for 60 minutes after the image has been generated. + size: &images_size + type: string + enum: ["256x256", "512x512", "1024x1024", "1792x1024", "1024x1792"] + default: "1024x1024" + example: "1024x1024" + nullable: true + description: The size of the generated images. Must be one of `256x256`, `512x512`, or `1024x1024` for `dall-e-2`. Must be one of `1024x1024`, `1792x1024`, or `1024x1792` for `dall-e-3` models. + style: + type: string + enum: ["vivid", "natural"] + default: "vivid" + example: "vivid" + nullable: true + description: The style of the generated images. Must be one of `vivid` or `natural`. Vivid causes the model to lean towards generating hyper-real and dramatic images. Natural causes the model to produce more natural, less hyper-real looking images. This param is only supported for `dall-e-3`. + user: *end_user_param_configuration + required: + - prompt + + ImagesResponse: + properties: + created: + type: integer + data: + type: array + items: + $ref: "#/components/schemas/Image" + required: + - created + - data + + Image: + type: object + description: Represents the url or the content of an image generated by the OpenAI API. + properties: + b64_json: + type: string + description: The base64-encoded JSON of the generated image, if `response_format` is `b64_json`. + url: + type: string + description: The URL of the generated image, if `response_format` is `url` (default). + revised_prompt: + type: string + description: The prompt that was used to generate the image, if there was any revision to the prompt. x-oaiMeta: - name: The completion object - legacy: true + name: The image object example: | { - "id": "cmpl-uqkvlQyYK7bGYrRHQ0eXlWi7", - "object": "text_completion", - "created": 1589478378, - "model": "gpt-3.5-turbo", - "choices": [ - { - "text": "\n\nThis is indeed a test", - "index": 0, - "logprobs": null, - "finish_reason": "length" - } - ], - "usage": { - "prompt_tokens": 5, - "completion_tokens": 7, - "total_tokens": 12 - } + "url": "...", + "revised_prompt": "..." } - ChatCompletionRequestMessageContentPart: - oneOf: - - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartText" - - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartImage" - x-oaiExpandable: true + CreateImageEditRequest: + type: object + properties: + image: + description: The image to edit. Must be a valid PNG file, less than 4MB, and square. If mask is not provided, image must have transparency, which will be used as the mask. + type: string + format: binary + prompt: + description: A text description of the desired image(s). The maximum length is 1000 characters. + type: string + example: "A cute baby sea otter wearing a beret" + mask: + description: An additional image whose fully transparent areas (e.g. where alpha is zero) indicate where `image` should be edited. Must be a valid PNG file, less than 4MB, and have the same dimensions as `image`. + type: string + format: binary + model: + anyOf: + - type: string + - type: string + enum: ["dall-e-2"] + x-oaiTypeLabel: string + default: "dall-e-2" + example: "dall-e-2" + nullable: true + description: The model to use for image generation. Only `dall-e-2` is supported at this time. + n: + type: integer + minimum: 1 + maximum: 10 + default: 1 + example: 1 + nullable: true + description: The number of images to generate. Must be between 1 and 10. + size: &dalle2_images_size + type: string + enum: ["256x256", "512x512", "1024x1024"] + default: "1024x1024" + example: "1024x1024" + nullable: true + description: The size of the generated images. Must be one of `256x256`, `512x512`, or `1024x1024`. + response_format: *images_response_format + user: *end_user_param_configuration + required: + - prompt + - image - ChatCompletionRequestMessageContentPartImage: + CreateImageVariationRequest: type: object - title: Image content part properties: - type: + image: + description: The image to use as the basis for the variation(s). Must be a valid PNG file, less than 4MB, and square. type: string - enum: ["image_url"] - description: The type of the content part. - image_url: - type: object - properties: - url: - type: string - description: Either a URL of the image or the base64 encoded image data. - format: uri - detail: - type: string - description: Specifies the detail level of the image. Learn more in the [Vision guide](/docs/guides/vision/low-or-high-fidelity-image-understanding). - enum: ["auto", "low", "high"] - default: "auto" - required: - - url + format: binary + model: + anyOf: + - type: string + - type: string + enum: ["dall-e-2"] + x-oaiTypeLabel: string + default: "dall-e-2" + example: "dall-e-2" + nullable: true + description: The model to use for image generation. Only `dall-e-2` is supported at this time. + n: *images_n + response_format: *images_response_format + size: *dalle2_images_size + user: *end_user_param_configuration required: - - type - - image_url + - image - ChatCompletionRequestMessageContentPartText: + CreateModerationRequest: type: object - title: Text content part properties: - type: + input: + description: The input text to classify + oneOf: + - type: string + default: "" + example: "I want to kill them." + - type: array + items: + type: string + default: "" + example: "I want to kill them." + model: + description: | + Two content moderations models are available: `text-moderation-stable` and `text-moderation-latest`. + + The default is `text-moderation-latest` which will be automatically upgraded over time. This ensures you are always using our most accurate model. If you use `text-moderation-stable`, we will provide advanced notice before updating the model. Accuracy of `text-moderation-stable` may be slightly lower than for `text-moderation-latest`. + nullable: false + default: "text-moderation-latest" + example: "text-moderation-stable" + anyOf: + - type: string + - type: string + enum: ["text-moderation-latest", "text-moderation-stable"] + x-oaiTypeLabel: string + required: + - input + + CreateModerationResponse: + type: object + description: Represents if a given text input is potentially harmful. + properties: + id: type: string - enum: ["text"] - description: The type of the content part. - text: + description: The unique identifier for the moderation request. + model: type: string - description: The text content. + description: The model used to generate the moderation results. + results: + type: array + description: A list of moderation objects. + items: + type: object + properties: + flagged: + type: boolean + description: Whether any of the below categories are flagged. + categories: + type: object + description: A list of the categories, and whether they are flagged or not. + properties: + hate: + type: boolean + description: Content that expresses, incites, or promotes hate based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste. Hateful content aimed at non-protected groups (e.g., chess players) is harassment. + hate/threatening: + type: boolean + description: Hateful content that also includes violence or serious harm towards the targeted group based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste. + harassment: + type: boolean + description: Content that expresses, incites, or promotes harassing language towards any target. + harassment/threatening: + type: boolean + description: Harassment content that also includes violence or serious harm towards any target. + self-harm: + type: boolean + description: Content that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders. + self-harm/intent: + type: boolean + description: Content where the speaker expresses that they are engaging or intend to engage in acts of self-harm, such as suicide, cutting, and eating disorders. + self-harm/instructions: + type: boolean + description: Content that encourages performing acts of self-harm, such as suicide, cutting, and eating disorders, or that gives instructions or advice on how to commit such acts. + sexual: + type: boolean + description: Content meant to arouse sexual excitement, such as the description of sexual activity, or that promotes sexual services (excluding sex education and wellness). + sexual/minors: + type: boolean + description: Sexual content that includes an individual who is under 18 years old. + violence: + type: boolean + description: Content that depicts death, violence, or physical injury. + violence/graphic: + type: boolean + description: Content that depicts death, violence, or physical injury in graphic detail. + required: + - hate + - hate/threatening + - harassment + - harassment/threatening + - self-harm + - self-harm/intent + - self-harm/instructions + - sexual + - sexual/minors + - violence + - violence/graphic + category_scores: + type: object + description: A list of the categories along with their scores as predicted by model. + properties: + hate: + type: number + description: The score for the category 'hate'. + hate/threatening: + type: number + description: The score for the category 'hate/threatening'. + harassment: + type: number + description: The score for the category 'harassment'. + harassment/threatening: + type: number + description: The score for the category 'harassment/threatening'. + self-harm: + type: number + description: The score for the category 'self-harm'. + self-harm/intent: + type: number + description: The score for the category 'self-harm/intent'. + self-harm/instructions: + type: number + description: The score for the category 'self-harm/instructions'. + sexual: + type: number + description: The score for the category 'sexual'. + sexual/minors: + type: number + description: The score for the category 'sexual/minors'. + violence: + type: number + description: The score for the category 'violence'. + violence/graphic: + type: number + description: The score for the category 'violence/graphic'. + required: + - hate + - hate/threatening + - harassment + - harassment/threatening + - self-harm + - self-harm/intent + - self-harm/instructions + - sexual + - sexual/minors + - violence + - violence/graphic + required: + - flagged + - categories + - category_scores required: - - type - - text - - ChatCompletionRequestMessage: - oneOf: - - $ref: "#/components/schemas/ChatCompletionRequestSystemMessage" - - $ref: "#/components/schemas/ChatCompletionRequestUserMessage" - - $ref: "#/components/schemas/ChatCompletionRequestAssistantMessage" - - $ref: "#/components/schemas/ChatCompletionRequestToolMessage" - - $ref: "#/components/schemas/ChatCompletionRequestFunctionMessage" - x-oaiExpandable: true + - id + - model + - results + x-oaiMeta: + name: The moderation object + example: *moderation_example - ChatCompletionRequestSystemMessage: + ListFilesResponse: type: object - title: System message properties: - content: - description: The contents of the system message. - type: string - role: - type: string - enum: ["system"] - description: The role of the messages author, in this case `system`. - name: + data: + type: array + items: + $ref: "#/components/schemas/OpenAIFile" + object: type: string - description: An optional name for the participant. Provides the model information to differentiate between participants of the same role. + enum: [list] required: - - content - - role + - object + - data - ChatCompletionRequestUserMessage: + CreateFileRequest: type: object - title: User message + additionalProperties: false properties: - content: + file: description: | - The contents of the user message. - oneOf: - - type: string - description: The text contents of the message. - title: Text content - - type: array - description: An array of content parts with a defined type, each can be of type `text` or `image_url` when passing in images. You can pass multiple images by adding multiple `image_url` content parts. Image input is only supported when using the `gpt-4-visual-preview` model. - title: Array of content parts - items: - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPart" - minItems: 1 - x-oaiExpandable: true - role: - type: string - enum: ["user"] - description: The role of the messages author, in this case `user`. - name: - type: string - description: An optional name for the participant. Provides the model information to differentiate between participants of the same role. - required: - - content - - role - - ChatCompletionRequestAssistantMessage: - type: object - title: Assistant message - properties: - content: - nullable: true + The File object (not file name) to be uploaded. type: string + format: binary + purpose: description: | - The contents of the assistant message. Required unless `tool_calls` or `function_call` is specified. - role: - type: string - enum: ["assistant"] - description: The role of the messages author, in this case `assistant`. - name: - type: string - description: An optional name for the participant. Provides the model information to differentiate between participants of the same role. - tool_calls: - $ref: "#/components/schemas/ChatCompletionMessageToolCalls" - function_call: - type: object - deprecated: true - description: "Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model." - properties: - arguments: - type: string - description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. - name: - type: string - description: The name of the function to call. - required: - - arguments - - name - required: - - role + The intended purpose of the uploaded file. - ChatCompletionRequestToolMessage: - type: object - title: Tool message - properties: - role: - type: string - enum: ["tool"] - description: The role of the messages author, in this case `tool`. - content: - type: string - description: The contents of the tool message. - tool_call_id: + Use "assistants" for [Assistants](/docs/api-reference/assistants) and [Message](/docs/api-reference/messages) files, "vision" for Assistants image file inputs, "batch" for [Batch API](/docs/guides/batch), and "fine-tune" for [Fine-tuning](/docs/api-reference/fine-tuning). type: string - description: Tool call that this message is responding to. + enum: ["assistants", "batch", "fine-tune"] required: - - role - - content - - tool_call_id + - file + - purpose - ChatCompletionRequestFunctionMessage: + DeleteFileResponse: type: object - title: Function message - deprecated: true properties: - role: - type: string - enum: ["function"] - description: The role of the messages author, in this case `function`. - content: - nullable: true + id: type: string - description: The contents of the function message. - name: + object: type: string - description: The name of the function to call. + enum: [file] + deleted: + type: boolean required: - - role - - content - - name - - FunctionParameters: - type: object - description: "The parameters the functions accepts, described as a JSON Schema object. See the [guide](/docs/guides/text-generation/function-calling) for examples, and the [JSON Schema reference](https://json-schema.org/understanding-json-schema/) for documentation about the format. \n\nOmitting `parameters` defines a function with an empty parameter list." - additionalProperties: true + - id + - object + - deleted - ChatCompletionFunctions: + CreateFineTuningJobRequest: type: object - deprecated: true properties: - description: - type: string - description: A description of what the function does, used by the model to choose when and how to call the function. - name: - type: string - description: The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. - parameters: - $ref: "#/components/schemas/FunctionParameters" - required: - - name + model: + description: | + The name of the model to fine-tune. You can select one of the + [supported models](/docs/guides/fine-tuning/what-models-can-be-fine-tuned). + example: "gpt-3.5-turbo" + anyOf: + - type: string + - type: string + enum: ["babbage-002", "davinci-002", "gpt-3.5-turbo"] + x-oaiTypeLabel: string + training_file: + description: | + The ID of an uploaded file that contains training data. - ChatCompletionFunctionCallOption: - type: object - description: > - Specifying a particular function via `{"name": "my_function"}` forces the model to call that function. - properties: - name: - type: string - description: The name of the function to call. - required: - - name + See [upload file](/docs/api-reference/files/create) for how to upload a file. - ChatCompletionTool: - type: object - properties: - type: + Your dataset must be formatted as a JSONL file. Additionally, you must upload your file with the purpose `fine-tune`. + + See the [fine-tuning guide](/docs/guides/fine-tuning) for more details. type: string - enum: ["function"] - description: The type of the tool. Currently, only `function` is supported. - function: - $ref: "#/components/schemas/FunctionObject" - required: - - type - - function + example: "file-abc123" + hyperparameters: + type: object + description: The hyperparameters used for the fine-tuning job. + properties: + batch_size: + description: | + Number of examples in each batch. A larger batch size means that model parameters + are updated less frequently, but with lower variance. + oneOf: + - type: string + enum: [auto] + - type: integer + minimum: 1 + maximum: 256 + default: auto + learning_rate_multiplier: + description: | + Scaling factor for the learning rate. A smaller learning rate may be useful to avoid + overfitting. + oneOf: + - type: string + enum: [auto] + - type: number + minimum: 0 + exclusiveMinimum: true + default: auto + n_epochs: + description: | + The number of epochs to train the model for. An epoch refers to one full cycle + through the training dataset. + oneOf: + - type: string + enum: [auto] + - type: integer + minimum: 1 + maximum: 50 + default: auto + suffix: + description: | + A string of up to 18 characters that will be added to your fine-tuned model name. - FunctionObject: - type: object - properties: - description: - type: string - description: A description of what the function does, used by the model to choose when and how to call the function. - name: + For example, a `suffix` of "custom-model-name" would produce a model name like `ft:gpt-3.5-turbo:openai:custom-model-name:7p4lURel`. type: string - description: The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. - parameters: - $ref: "#/components/schemas/FunctionParameters" - required: - - name + minLength: 1 + maxLength: 40 + default: null + nullable: true + validation_file: + description: | + The ID of an uploaded file that contains validation data. - ChatCompletionToolChoiceOption: - description: | - Controls which (if any) function is called by the model. - `none` means the model will not call a function and instead generates a message. - `auto` means the model can pick between generating a message or calling a function. - Specifying a particular function via `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that function. + If you provide this file, the data is used to generate validation + metrics periodically during fine-tuning. These metrics can be viewed in + the fine-tuning results file. + The same data should not be present in both train and validation files. - `none` is the default when no functions are present. `auto` is the default if functions are present. - oneOf: - - type: string - description: > - `none` means the model will not call a function and instead generates a message. - `auto` means the model can pick between generating a message or calling a function. - enum: [none, auto] - - $ref: "#/components/schemas/ChatCompletionNamedToolChoice" - x-oaiExpandable: true + Your dataset must be formatted as a JSONL file. You must upload your file with the purpose `fine-tune`. - ChatCompletionNamedToolChoice: - type: object - description: Specifies a tool the model should use. Use to force the model to call a specific function. - properties: - type: + See the [fine-tuning guide](/docs/guides/fine-tuning) for more details. type: string - enum: ["function"] - description: The type of the tool. Currently, only `function` is supported. - function: - type: object - properties: - name: - type: string - description: The name of the function to call. - required: - - name - required: - - type - - function + nullable: true + example: "file-abc123" + integrations: + type: array + description: A list of integrations to enable for your fine-tuning job. + nullable: true + items: + type: object + required: + - type + - wandb + properties: + type: + description: | + The type of integration to enable. Currently, only "wandb" (Weights and Biases) is supported. + oneOf: + - type: string + enum: [wandb] + wandb: + type: object + description: | + The settings for your integration with Weights and Biases. This payload specifies the project that + metrics will be sent to. Optionally, you can set an explicit display name for your run, add tags + to your run, and set a default entity (team, username, etc) to be associated with your run. + required: + - project + properties: + project: + description: | + The name of the project that the new run will be created under. + type: string + example: "my-wandb-project" + name: + description: | + A display name to set for the run. If not set, we will use the Job ID as the name. + nullable: true + type: string + entity: + description: | + The entity to use for the run. This allows you to set the team or username of the WandB user that you would + like associated with the run. If not set, the default entity for the registered WandB API key is used. + nullable: true + type: string + tags: + description: | + A list of tags to be attached to the newly created run. These tags are passed through directly to WandB. Some + default tags are generated by OpenAI: "openai/finetune", "openai/{base-model}", "openai/{ftjob-abcdef}". + type: array + items: + type: string + example: "custom-tag" - ChatCompletionMessageToolCalls: - type: array - description: The tool calls generated by the model, such as function calls. - items: - $ref: "#/components/schemas/ChatCompletionMessageToolCall" + seed: + description: | + The seed controls the reproducibility of the job. Passing in the same seed and job parameters should produce the same results, but may differ in rare cases. + If a seed is not specified, one will be generated for you. + type: integer + nullable: true + minimum: 0 + maximum: 2147483647 + example: 42 + required: + - model + - training_file - ChatCompletionMessageToolCall: + ListFineTuningJobEventsResponse: type: object properties: - # TODO: index included when streaming - id: - type: string - description: The ID of the tool call. - type: + data: + type: array + items: + $ref: "#/components/schemas/FineTuningJobEvent" + object: type: string - enum: ["function"] - description: The type of the tool. Currently, only `function` is supported. - function: - type: object - description: The function that the model called. - properties: - name: - type: string - description: The name of the function to call. - arguments: - type: string - description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. - required: - - name - - arguments + enum: [list] required: - - id - - type - - function + - object + - data - ChatCompletionMessageToolCallChunk: + ListFineTuningJobCheckpointsResponse: type: object properties: - index: - type: integer - id: + data: + type: array + items: + $ref: "#/components/schemas/FineTuningJobCheckpoint" + object: type: string - description: The ID of the tool call. - type: + enum: [list] + first_id: type: string - enum: ["function"] - description: The type of the tool. Currently, only `function` is supported. - function: - type: object - properties: - name: - type: string - description: The name of the function to call. - arguments: - type: string - description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. + nullable: true + last_id: + type: string + nullable: true + has_more: + type: boolean required: - - index - - # Note, this isn't referenced anywhere, but is kept as a convenience to record all possible roles in one place. - ChatCompletionRole: - type: string - description: The role of the author of a message - enum: - - system - - user - - assistant - - tool - - function + - object + - data + - has_more - ChatCompletionResponseMessage: + CreateEmbeddingRequest: type: object - description: A chat completion message generated by the model. + additionalProperties: false properties: - content: - type: string - description: The contents of the message. - nullable: true - tool_calls: - $ref: "#/components/schemas/ChatCompletionMessageToolCalls" - role: + input: + description: | + Input text to embed, encoded as a string or array of tokens. To embed multiple inputs in a single request, pass an array of strings or array of token arrays. The input must not exceed the max input tokens for the model (8192 tokens for `text-embedding-ada-002`), cannot be an empty string, and any array must be 2048 dimensions or less. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens. + example: "The quick brown fox jumped over the lazy dog" + oneOf: + - type: string + title: string + description: The string that will be turned into an embedding. + default: "" + example: "This is a test." + - type: array + title: array + description: The array of strings that will be turned into an embedding. + minItems: 1 + maxItems: 2048 + items: + type: string + default: "" + example: "['This is a test.']" + - type: array + title: array + description: The array of integers that will be turned into an embedding. + minItems: 1 + maxItems: 2048 + items: + type: integer + example: "[1212, 318, 257, 1332, 13]" + - type: array + title: array + description: The array of arrays containing integers that will be turned into an embedding. + minItems: 1 + maxItems: 2048 + items: + type: array + minItems: 1 + items: + type: integer + example: "[[1212, 318, 257, 1332, 13]]" + x-oaiExpandable: true + model: + description: *model_description + example: "text-embedding-3-small" + anyOf: + - type: string + - type: string + enum: + [ + "text-embedding-ada-002", + "text-embedding-3-small", + "text-embedding-3-large", + ] + x-oaiTypeLabel: string + encoding_format: + description: "The format to return the embeddings in. Can be either `float` or [`base64`](https://pypi.org/project/pybase64/)." + example: "float" + default: "float" type: string - enum: ["assistant"] - description: The role of the author of this message. - function_call: - type: object - deprecated: true - description: "Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model." - properties: - arguments: - type: string - description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. - name: - type: string - description: The name of the function to call. - required: - - name - - arguments + enum: ["float", "base64"] + dimensions: + description: | + The number of dimensions the resulting output embeddings should have. Only supported in `text-embedding-3` and later models. + type: integer + minimum: 1 + user: *end_user_param_configuration required: - - role - - content + - model + - input - ChatCompletionStreamResponseDelta: + CreateEmbeddingResponse: type: object - description: A chat completion delta generated by streamed model responses. properties: - content: - type: string - description: The contents of the chunk message. - nullable: true - function_call: - deprecated: true - type: object - description: "Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model." - properties: - arguments: - type: string - description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. - name: - type: string - description: The name of the function to call. - tool_calls: + data: type: array + description: The list of embeddings generated by the model. items: - $ref: "#/components/schemas/ChatCompletionMessageToolCallChunk" - role: + $ref: "#/components/schemas/Embedding" + model: type: string - enum: ["system", "user", "assistant", "tool"] - description: The role of the author of this message. + description: The name of the model used to generate the embedding. + object: + type: string + description: The object type, which is always "list". + enum: [list] + usage: + type: object + description: The usage information for the request. + properties: + prompt_tokens: + type: integer + description: The number of tokens used by the prompt. + total_tokens: + type: integer + description: The total number of tokens used by the request. + required: + - prompt_tokens + - total_tokens + required: + - object + - model + - data + - usage - CreateChatCompletionRequest: + CreateTranscriptionRequest: type: object + additionalProperties: false properties: - messages: - description: A list of messages comprising the conversation so far. [Example Python code](https://cookbook.openai.com/examples/how_to_format_inputs_to_chatgpt_models). - type: array - minItems: 1 - items: - $ref: "#/components/schemas/ChatCompletionRequestMessage" + file: + description: | + The audio file object (not file name) to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm. + type: string + x-oaiTypeLabel: file + format: binary model: - description: ID of the model to use. See the [model endpoint compatibility](/docs/models/model-endpoint-compatibility) table for details on which models work with the Chat API. - example: "gpt-3.5-turbo" + description: | + ID of the model to use. Only `whisper-1` (which is powered by our open source Whisper V2 model) is currently available. + example: whisper-1 anyOf: - type: string - type: string - enum: - [ - "gpt-4-0125-preview", - "gpt-4-turbo-preview", - "gpt-4-1106-preview", - "gpt-4-vision-preview", - "gpt-4", - "gpt-4-0314", - "gpt-4-0613", - "gpt-4-32k", - "gpt-4-32k-0314", - "gpt-4-32k-0613", - "gpt-3.5-turbo", - "gpt-3.5-turbo-16k", - "gpt-3.5-turbo-0301", - "gpt-3.5-turbo-0613", - "gpt-3.5-turbo-1106", - "gpt-3.5-turbo-0125", - "gpt-3.5-turbo-16k-0613", - ] + enum: ["whisper-1"] x-oaiTypeLabel: string - frequency_penalty: - type: number - default: 0 - minimum: -2 - maximum: 2 - nullable: true - description: *completions_frequency_penalty_description - logit_bias: - type: object - x-oaiTypeLabel: map - default: null - nullable: true - additionalProperties: - type: integer + language: description: | - Modify the likelihood of specified tokens appearing in the completion. - - Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. - logprobs: - description: Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the `content` of `message`. This option is currently not available on the `gpt-4-vision-preview` model. - type: boolean - default: false - nullable: true - top_logprobs: - description: An integer between 0 and 5 specifying the number of most likely tokens to return at each token position, each with an associated log probability. `logprobs` must be set to `true` if this parameter is used. - type: integer - minimum: 0 - maximum: 5 - nullable: true - max_tokens: + The language of the input audio. Supplying the input language in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) format will improve accuracy and latency. + type: string + prompt: description: | - The maximum number of [tokens](/tokenizer) that can be generated in the chat completion. - - The total length of input tokens and generated tokens is limited by the model's context length. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens. - type: integer - nullable: true - n: - type: integer - minimum: 1 - maximum: 128 - default: 1 - example: 1 - nullable: true - description: How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep `n` as `1` to minimize costs. - presence_penalty: + An optional text to guide the model's style or continue a previous audio segment. The [prompt](/docs/guides/speech-to-text/prompting) should match the audio language. + type: string + response_format: + description: | + The format of the transcript output, in one of these options: `json`, `text`, `srt`, `verbose_json`, or `vtt`. + type: string + enum: + - json + - text + - srt + - verbose_json + - vtt + default: json + temperature: + description: | + The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use [log probability](https://en.wikipedia.org/wiki/Log_probability) to automatically increase the temperature until certain thresholds are hit. type: number default: 0 - minimum: -2 - maximum: 2 - nullable: true - description: *completions_presence_penalty_description - response_format: - type: object + timestamp_granularities[]: description: | - An object specifying the format that the model must output. Compatible with [GPT-4 Turbo](/docs/models/gpt-4-and-gpt-4-turbo) and all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`. + The timestamp granularities to populate for this transcription. `response_format` must be set `verbose_json` to use timestamp granularities. Either or both of these options are supported: `word`, or `segment`. Note: There is no additional latency for segment timestamps, but generating word timestamps incurs additional latency. + type: array + items: + type: string + enum: + - word + - segment + default: [segment] + required: + - file + - model - Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the message the model generates is valid JSON. + # Note: This does not currently support the non-default response format types. + CreateTranscriptionResponseJson: + type: object + description: Represents a transcription response returned by model, based on the provided input. + properties: + text: + type: string + description: The transcribed text. + required: + - text + x-oaiMeta: + name: The transcription object + group: audio + example: *basic_transcription_response_example - **Important:** when using JSON mode, you **must** also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if `finish_reason="length"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length. - properties: - type: - type: string - enum: ["text", "json_object"] - example: "json_object" - default: "text" - description: Must be one of `text` or `json_object`. - seed: + TranscriptionSegment: + type: object + properties: + id: type: integer - minimum: -9223372036854775808 - maximum: 9223372036854775807 - nullable: true - description: | - This feature is in Beta. - If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result. - Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend. - x-oaiMeta: - beta: true - stop: - description: | - Up to 4 sequences where the API will stop generating further tokens. - default: null - oneOf: - - type: string - nullable: true - - type: array - minItems: 1 - maxItems: 4 - items: - type: string - stream: - description: > - If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) - as they become available, with the stream terminated by a `data: [DONE]` message. [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions). - type: boolean - nullable: true - default: false - temperature: + description: Unique identifier of the segment. + seek: + type: integer + description: Seek offset of the segment. + start: type: number - minimum: 0 - maximum: 2 - default: 1 - example: 1 - nullable: true - description: *completions_temperature_description - top_p: + format: float + description: Start time of the segment in seconds. + end: type: number - minimum: 0 - maximum: 1 - default: 1 - example: 1 - nullable: true - description: *completions_top_p_description - tools: + format: float + description: End time of the segment in seconds. + text: + type: string + description: Text content of the segment. + tokens: type: array - description: > - A list of tools the model may call. Currently, only functions are supported as a tool. - Use this to provide a list of functions the model may generate JSON inputs for. items: - $ref: "#/components/schemas/ChatCompletionTool" - tool_choice: - $ref: "#/components/schemas/ChatCompletionToolChoiceOption" - user: *end_user_param_configuration - function_call: - deprecated: true - description: | - Deprecated in favor of `tool_choice`. - - Controls which (if any) function is called by the model. - `none` means the model will not call a function and instead generates a message. - `auto` means the model can pick between generating a message or calling a function. - Specifying a particular function via `{"name": "my_function"}` forces the model to call that function. + type: integer + description: Array of token IDs for the text content. + temperature: + type: number + format: float + description: Temperature parameter used for generating the segment. + avg_logprob: + type: number + format: float + description: Average logprob of the segment. If the value is lower than -1, consider the logprobs failed. + compression_ratio: + type: number + format: float + description: Compression ratio of the segment. If the value is greater than 2.4, consider the compression failed. + no_speech_prob: + type: number + format: float + description: Probability of no speech in the segment. If the value is higher than 1.0 and the `avg_logprob` is below -1, consider this segment silent. + required: + - id + - seek + - start + - end + - text + - tokens + - temperature + - avg_logprob + - compression_ratio + - no_speech_prob - `none` is the default when no functions are present. `auto` is the default if functions are present. - oneOf: - - type: string - description: > - `none` means the model will not call a function and instead generates a message. - `auto` means the model can pick between generating a message or calling a function. - enum: [none, auto] - - $ref: "#/components/schemas/ChatCompletionFunctionCallOption" - x-oaiExpandable: true - functions: - deprecated: true - description: | - Deprecated in favor of `tools`. + TranscriptionWord: + type: object + properties: + word: + type: string + description: The text content of the word. + start: + type: number + format: float + description: Start time of the word in seconds. + end: + type: number + format: float + description: End time of the word in seconds. + required: [word, start, end] - A list of functions the model may generate JSON inputs for. + CreateTranscriptionResponseVerboseJson: + type: object + description: Represents a verbose json transcription response returned by model, based on the provided input. + properties: + language: + type: string + description: The language of the input audio. + duration: + type: string + description: The duration of the input audio. + text: + type: string + description: The transcribed text. + words: type: array - minItems: 1 - maxItems: 128 + description: Extracted words and their corresponding timestamps. items: - $ref: "#/components/schemas/ChatCompletionFunctions" + $ref: "#/components/schemas/TranscriptionWord" + segments: + type: array + description: Segments of the transcribed text and their corresponding details. + items: + $ref: "#/components/schemas/TranscriptionSegment" + required: [language, duration, text] + x-oaiMeta: + name: The transcription object + group: audio + example: *verbose_transcription_response_example + CreateTranslationRequest: + type: object + additionalProperties: false + properties: + file: + description: | + The audio file object (not file name) translate, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm. + type: string + x-oaiTypeLabel: file + format: binary + model: + description: | + ID of the model to use. Only `whisper-1` (which is powered by our open source Whisper V2 model) is currently available. + example: whisper-1 + anyOf: + - type: string + - type: string + enum: ["whisper-1"] + x-oaiTypeLabel: string + prompt: + description: | + An optional text to guide the model's style or continue a previous audio segment. The [prompt](/docs/guides/speech-to-text/prompting) should be in English. + type: string + response_format: + description: | + The format of the transcript output, in one of these options: `json`, `text`, `srt`, `verbose_json`, or `vtt`. + type: string + default: json + temperature: + description: | + The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use [log probability](https://en.wikipedia.org/wiki/Log_probability) to automatically increase the temperature until certain thresholds are hit. + type: number + default: 0 required: + - file - model - - messages - CreateChatCompletionResponse: + # Note: This does not currently support the non-default response format types. + CreateTranslationResponseJson: type: object - description: Represents a chat completion response returned by model, based on the provided input. properties: - id: + text: type: string - description: A unique identifier for the chat completion. - choices: + required: + - text + + CreateTranslationResponseVerboseJson: + type: object + properties: + language: + type: string + description: The language of the output translation (always `english`). + duration: + type: string + description: The duration of the input audio. + text: + type: string + description: The translated text. + segments: type: array - description: A list of chat completion choices. Can be more than one if `n` is greater than 1. + description: Segments of the translated text and their corresponding details. items: - type: object - required: - - finish_reason - - index - - message - - logprobs - properties: - finish_reason: - type: string - description: &chat_completion_finish_reason_description | - The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, - `length` if the maximum number of tokens specified in the request was reached, - `content_filter` if content was omitted due to a flag from our content filters, - `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function. - enum: - [ - "stop", - "length", - "tool_calls", - "content_filter", - "function_call", - ] - index: - type: integer - description: The index of the choice in the list of choices. - message: - $ref: "#/components/schemas/ChatCompletionResponseMessage" - logprobs: &chat_completion_response_logprobs - description: Log probability information for the choice. - type: object - nullable: true - properties: - content: - description: A list of message content tokens with log probability information. - type: array - items: - $ref: "#/components/schemas/ChatCompletionTokenLogprob" - nullable: true - required: - - content - created: - type: integer - description: The Unix timestamp (in seconds) of when the chat completion was created. + $ref: "#/components/schemas/TranscriptionSegment" + required: [language, duration, text] + + CreateSpeechRequest: + type: object + additionalProperties: false + properties: model: + description: | + One of the available [TTS models](/docs/models/tts): `tts-1` or `tts-1-hd` + anyOf: + - type: string + - type: string + enum: ["tts-1", "tts-1-hd"] + x-oaiTypeLabel: string + input: type: string - description: The model used for the chat completion. - system_fingerprint: + description: The text to generate audio for. The maximum length is 4096 characters. + maxLength: 4096 + voice: + description: The voice to use when generating the audio. Supported voices are `alloy`, `echo`, `fable`, `onyx`, `nova`, and `shimmer`. Previews of the voices are available in the [Text to speech guide](/docs/guides/text-to-speech/voice-options). type: string - description: | - This fingerprint represents the backend configuration that the model runs with. + enum: ["alloy", "echo", "fable", "onyx", "nova", "shimmer"] + response_format: + description: "The format to audio in. Supported formats are `mp3`, `opus`, `aac`, `flac`, `wav`, and `pcm`." + default: "mp3" + type: string + enum: ["mp3", "opus", "aac", "flac", "wav", "pcm"] + speed: + description: "The speed of the generated audio. Select a value from `0.25` to `4.0`. `1.0` is the default." + type: number + default: 1.0 + minimum: 0.25 + maximum: 4.0 + required: + - model + - input + - voice - Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism. + Model: + title: Model + description: Describes an OpenAI model offering that can be used with the API. + properties: + id: + type: string + description: The model identifier, which can be referenced in the API endpoints. + created: + type: integer + description: The Unix timestamp (in seconds) when the model was created. object: type: string - description: The object type, which is always `chat.completion`. - enum: [chat.completion] - usage: - $ref: "#/components/schemas/CompletionUsage" + description: The object type, which is always "model". + enum: [model] + owned_by: + type: string + description: The organization that owns the model. required: - - choices - - created - id - - model - object + - created + - owned_by x-oaiMeta: - name: The chat completion object - group: chat - example: *chat_completion_example + name: The model object + example: *retrieve_model_response - CreateChatCompletionFunctionResponse: - type: object - description: Represents a chat completion response returned by model, based on the provided input. + OpenAIFile: + title: OpenAIFile + description: The `File` object represents a document that has been uploaded to OpenAI. properties: id: type: string - description: A unique identifier for the chat completion. - choices: - type: array - description: A list of chat completion choices. Can be more than one if `n` is greater than 1. - items: - type: object - required: - - finish_reason - - index - - message - - logprobs - properties: - finish_reason: - type: string - description: - &chat_completion_function_finish_reason_description | - The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, `length` if the maximum number of tokens specified in the request was reached, `content_filter` if content was omitted due to a flag from our content filters, or `function_call` if the model called a function. - enum: ["stop", "length", "function_call", "content_filter"] - index: - type: integer - description: The index of the choice in the list of choices. - message: - $ref: "#/components/schemas/ChatCompletionResponseMessage" - created: + description: The file identifier, which can be referenced in the API endpoints. + bytes: type: integer - description: The Unix timestamp (in seconds) of when the chat completion was created. - model: + description: The size of the file, in bytes. + created_at: + type: integer + description: The Unix timestamp (in seconds) for when the file was created. + filename: type: string - description: The model used for the chat completion. - system_fingerprint: + description: The name of the file. + object: + type: string + description: The object type, which is always `file`. + enum: ["file"] + purpose: + type: string + description: The intended purpose of the file. Supported values are `assistants`, `assistants_output`, `batch`, `batch_output`, `fine-tune`, `fine-tune-results` and `vision`. + enum: + [ + "assistants", + "assistants_output", + "batch", + "batch_output", + "fine-tune", + "fine-tune-results", + "vision" + ] + status: type: string - description: | - This fingerprint represents the backend configuration that the model runs with. - - Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism. - object: + deprecated: true + description: Deprecated. The current status of the file, which can be either `uploaded`, `processed`, or `error`. + enum: ["uploaded", "processed", "error"] + status_details: type: string - description: The object type, which is always `chat.completion`. - enum: [chat.completion] - usage: - $ref: "#/components/schemas/CompletionUsage" + deprecated: true + description: Deprecated. For details on why a fine-tuning training file failed validation, see the `error` field on `fine_tuning.job`. required: - - choices - - created - id - - model - object - x-oaiMeta: - name: The chat completion object - group: chat - example: *chat_completion_function_example - - ChatCompletionTokenLogprob: - type: object - properties: - token: &chat_completion_response_logprobs_token - description: The token. - type: string - logprob: &chat_completion_response_logprobs_token_logprob - description: The log probability of this token. - type: number - bytes: &chat_completion_response_logprobs_bytes - description: A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be `null` if there is no bytes representation for the token. - type: array - items: - type: integer - nullable: true - top_logprobs: - description: List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested `top_logprobs` returned. - type: array - items: - type: object - properties: - token: *chat_completion_response_logprobs_token - logprob: *chat_completion_response_logprobs_token_logprob - bytes: *chat_completion_response_logprobs_bytes - required: - - token - - logprob - - bytes - required: - - token - - logprob - bytes - - top_logprobs - - ListPaginatedFineTuningJobsResponse: + - created_at + - filename + - purpose + - status + x-oaiMeta: + name: The file object + example: | + { + "id": "file-abc123", + "object": "file", + "bytes": 120000, + "created_at": 1677610602, + "filename": "salesOverview.pdf", + "purpose": "assistants", + } + Embedding: type: object + description: | + Represents an embedding vector returned by embedding endpoint. properties: - data: + index: + type: integer + description: The index of the embedding in the list of embeddings. + embedding: type: array + description: | + The embedding vector, which is a list of floats. The length of vector depends on the model as listed in the [embedding guide](/docs/guides/embeddings). items: - $ref: "#/components/schemas/FineTuningJob" - has_more: - type: boolean + type: number object: type: string - enum: [list] + description: The object type, which is always "embedding". + enum: [embedding] required: + - index - object - - data - - has_more + - embedding + x-oaiMeta: + name: The embedding object + example: | + { + "object": "embedding", + "embedding": [ + 0.0023064255, + -0.009327292, + .... (1536 floats total for ada-002) + -0.0028842222, + ], + "index": 0 + } - CreateChatCompletionStreamResponse: + FineTuningJob: type: object - description: Represents a streamed chunk of a chat completion response returned by model, based on the provided input. + title: FineTuningJob + description: | + The `fine_tuning.job` object represents a fine-tuning job that has been created through the API. properties: id: type: string - description: A unique identifier for the chat completion. Each chunk has the same ID. - choices: - type: array - description: A list of chat completion choices. Can be more than one if `n` is greater than 1. - items: - type: object - required: - - delta - - finish_reason - - index - properties: - delta: - $ref: "#/components/schemas/ChatCompletionStreamResponseDelta" - logprobs: *chat_completion_response_logprobs - finish_reason: - type: string - description: *chat_completion_finish_reason_description - enum: - [ - "stop", - "length", - "tool_calls", - "content_filter", - "function_call", - ] - nullable: true - index: - type: integer - description: The index of the choice in the list of choices. - created: + description: The object identifier, which can be referenced in the API endpoints. + created_at: type: integer - description: The Unix timestamp (in seconds) of when the chat completion was created. Each chunk has the same timestamp. - model: + description: The Unix timestamp (in seconds) for when the fine-tuning job was created. + error: + type: object + nullable: true + description: For fine-tuning jobs that have `failed`, this will contain more information on the cause of the failure. + properties: + code: + type: string + description: A machine-readable error code. + message: + type: string + description: A human-readable error message. + param: + type: string + description: The parameter that was invalid, usually `training_file` or `validation_file`. This field will be null if the failure was not parameter-specific. + nullable: true + required: + - code + - message + - param + fine_tuned_model: type: string - description: The model to generate the completion. - system_fingerprint: + nullable: true + description: The name of the fine-tuned model that is being created. The value will be null if the fine-tuning job is still running. + finished_at: + type: integer + nullable: true + description: The Unix timestamp (in seconds) for when the fine-tuning job was finished. The value will be null if the fine-tuning job is still running. + hyperparameters: + type: object + description: The hyperparameters used for the fine-tuning job. See the [fine-tuning guide](/docs/guides/fine-tuning) for more details. + properties: + n_epochs: + oneOf: + - type: string + enum: [auto] + - type: integer + minimum: 1 + maximum: 50 + default: auto + description: + The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset. + + "auto" decides the optimal number of epochs based on the size of the dataset. If setting the number manually, we support any number between 1 and 50 epochs. + required: + - n_epochs + model: type: string - description: | - This fingerprint represents the backend configuration that the model runs with. - Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism. + description: The base model that is being fine-tuned. object: type: string - description: The object type, which is always `chat.completion.chunk`. - enum: [chat.completion.chunk] - required: - - choices - - created - - id - - model - - object - x-oaiMeta: - name: The chat completion chunk object - group: chat - example: *chat_completion_chunk_example - - CreateChatCompletionImageResponse: - type: object - description: Represents a streamed chunk of a chat completion response returned by model, based on the provided input. - x-oaiMeta: - name: The chat completion chunk object - group: chat - example: *chat_completion_image_example - - CreateImageRequest: - type: object - properties: - prompt: - description: A text description of the desired image(s). The maximum length is 1000 characters for `dall-e-2` and 4000 characters for `dall-e-3`. + description: The object type, which is always "fine_tuning.job". + enum: [fine_tuning.job] + organization_id: type: string - example: "A cute baby sea otter" - model: - anyOf: - - type: string - - type: string - enum: ["dall-e-2", "dall-e-3"] - x-oaiTypeLabel: string - default: "dall-e-2" - example: "dall-e-3" - nullable: true - description: The model to use for image generation. - n: &images_n + description: The organization that owns the fine-tuning job. + result_files: + type: array + description: The compiled results file ID(s) for the fine-tuning job. You can retrieve the results with the [Files API](/docs/api-reference/files/retrieve-contents). + items: + type: string + example: file-abc123 + status: + type: string + description: The current status of the fine-tuning job, which can be either `validating_files`, `queued`, `running`, `succeeded`, `failed`, or `cancelled`. + enum: + [ + "validating_files", + "queued", + "running", + "succeeded", + "failed", + "cancelled", + ] + trained_tokens: type: integer - minimum: 1 - maximum: 10 - default: 1 - example: 1 nullable: true - description: The number of images to generate. Must be between 1 and 10. For `dall-e-3`, only `n=1` is supported. - quality: + description: The total number of billable tokens processed by this fine-tuning job. The value will be null if the fine-tuning job is still running. + training_file: type: string - enum: ["standard", "hd"] - default: "standard" - example: "standard" - description: The quality of the image that will be generated. `hd` creates images with finer details and greater consistency across the image. This param is only supported for `dall-e-3`. - response_format: &images_response_format + description: The file ID used for training. You can retrieve the training data with the [Files API](/docs/api-reference/files/retrieve-contents). + validation_file: type: string - enum: ["url", "b64_json"] - default: "url" - example: "url" nullable: true - description: The format in which the generated images are returned. Must be one of `url` or `b64_json`. - size: &images_size - type: string - enum: ["256x256", "512x512", "1024x1024", "1792x1024", "1024x1792"] - default: "1024x1024" - example: "1024x1024" + description: The file ID used for validation. You can retrieve the validation results with the [Files API](/docs/api-reference/files/retrieve-contents). + integrations: + type: array nullable: true - description: The size of the generated images. Must be one of `256x256`, `512x512`, or `1024x1024` for `dall-e-2`. Must be one of `1024x1024`, `1792x1024`, or `1024x1792` for `dall-e-3` models. - style: - type: string - enum: ["vivid", "natural"] - default: "vivid" - example: "vivid" + description: A list of integrations to enable for this fine-tuning job. + maxItems: 5 + items: + oneOf: + - $ref: "#/components/schemas/FineTuningIntegration" + x-oaiExpandable: true + seed: + type: integer + description: The seed used for the fine-tuning job. + estimated_finish: + type: integer nullable: true - description: The style of the generated images. Must be one of `vivid` or `natural`. Vivid causes the model to lean towards generating hyper-real and dramatic images. Natural causes the model to produce more natural, less hyper-real looking images. This param is only supported for `dall-e-3`. - user: *end_user_param_configuration + description: The Unix timestamp (in seconds) for when the fine-tuning job is estimated to finish. The value will be null if the fine-tuning job is not running. required: - - prompt + - created_at + - error + - finished_at + - fine_tuned_model + - hyperparameters + - id + - model + - object + - organization_id + - result_files + - status + - trained_tokens + - training_file + - validation_file + - seed + x-oaiMeta: + name: The fine-tuning job object + example: *fine_tuning_example - ImagesResponse: - properties: - created: - type: integer - data: - type: array - items: - $ref: "#/components/schemas/Image" + FineTuningIntegration: + type: object + title: Fine-Tuning Job Integration required: - - created - - data + - type + - wandb + properties: + type: + type: string + description: "The type of the integration being enabled for the fine-tuning job" + enum: ["wandb"] + wandb: + type: object + description: | + The settings for your integration with Weights and Biases. This payload specifies the project that + metrics will be sent to. Optionally, you can set an explicit display name for your run, add tags + to your run, and set a default entity (team, username, etc) to be associated with your run. + required: + - project + properties: + project: + description: | + The name of the project that the new run will be created under. + type: string + example: "my-wandb-project" + name: + description: | + A display name to set for the run. If not set, we will use the Job ID as the name. + nullable: true + type: string + entity: + description: | + The entity to use for the run. This allows you to set the team or username of the WandB user that you would + like associated with the run. If not set, the default entity for the registered WandB API key is used. + nullable: true + type: string + tags: + description: | + A list of tags to be attached to the newly created run. These tags are passed through directly to WandB. Some + default tags are generated by OpenAI: "openai/finetune", "openai/{base-model}", "openai/{ftjob-abcdef}". + type: array + items: + type: string + example: "custom-tag" - Image: + FineTuningJobEvent: type: object - description: Represents the url or the content of an image generated by the OpenAI API. + description: Fine-tuning job event object properties: - b64_json: + id: type: string - description: The base64-encoded JSON of the generated image, if `response_format` is `b64_json`. - url: + created_at: + type: integer + level: type: string - description: The URL of the generated image, if `response_format` is `url` (default). - revised_prompt: + enum: ["info", "warn", "error"] + message: type: string - description: The prompt that was used to generate the image, if there was any revision to the prompt. + object: + type: string + enum: [fine_tuning.job.event] + required: + - id + - object + - created_at + - level + - message x-oaiMeta: - name: The image object + name: The fine-tuning job event object example: | { - "url": "...", - "revised_prompt": "..." + "object": "fine_tuning.job.event", + "id": "ftevent-abc123" + "created_at": 1677610602, + "level": "info", + "message": "Created fine-tuning job" } - CreateImageEditRequest: + FineTuningJobCheckpoint: type: object + title: FineTuningJobCheckpoint + description: | + The `fine_tuning.job.checkpoint` object represents a model checkpoint for a fine-tuning job that is ready to use. properties: - image: - description: The image to edit. Must be a valid PNG file, less than 4MB, and square. If mask is not provided, image must have transparency, which will be used as the mask. - type: string - format: binary - prompt: - description: A text description of the desired image(s). The maximum length is 1000 characters. + id: type: string - example: "A cute baby sea otter wearing a beret" - mask: - description: An additional image whose fully transparent areas (e.g. where alpha is zero) indicate where `image` should be edited. Must be a valid PNG file, less than 4MB, and have the same dimensions as `image`. + description: The checkpoint identifier, which can be referenced in the API endpoints. + created_at: + type: integer + description: The Unix timestamp (in seconds) for when the checkpoint was created. + fine_tuned_model_checkpoint: type: string - format: binary - model: - anyOf: - - type: string - - type: string - enum: ["dall-e-2"] - x-oaiTypeLabel: string - default: "dall-e-2" - example: "dall-e-2" - nullable: true - description: The model to use for image generation. Only `dall-e-2` is supported at this time. - n: + description: The name of the fine-tuned checkpoint model that is created. + step_number: type: integer - minimum: 1 - maximum: 10 - default: 1 - example: 1 - nullable: true - description: The number of images to generate. Must be between 1 and 10. - size: &dalle2_images_size + description: The step number that the checkpoint was created at. + metrics: + type: object + description: Metrics at the step number during the fine-tuning job. + properties: + step: + type: number + train_loss: + type: number + train_mean_token_accuracy: + type: number + valid_loss: + type: number + valid_mean_token_accuracy: + type: number + full_valid_loss: + type: number + full_valid_mean_token_accuracy: + type: number + fine_tuning_job_id: + type: string + description: The name of the fine-tuning job that this checkpoint was created from. + object: type: string - enum: ["256x256", "512x512", "1024x1024"] - default: "1024x1024" - example: "1024x1024" - nullable: true - description: The size of the generated images. Must be one of `256x256`, `512x512`, or `1024x1024`. - response_format: *images_response_format - user: *end_user_param_configuration + description: The object type, which is always "fine_tuning.job.checkpoint". + enum: [fine_tuning.job.checkpoint] required: - - prompt - - image + - created_at + - fine_tuning_job_id + - fine_tuned_model_checkpoint + - id + - metrics + - object + - step_number + x-oaiMeta: + name: The fine-tuning job checkpoint object + example: | + { + "object": "fine_tuning.job.checkpoint", + "id": "ftckpt_qtZ5Gyk4BLq1SfLFWp3RtO3P", + "created_at": 1712211699, + "fine_tuned_model_checkpoint": "ft:gpt-3.5-turbo-0125:my-org:custom_suffix:9ABel2dg:ckpt-step-88", + "fine_tuning_job_id": "ftjob-fpbNQ3H1GrMehXRf8cO97xTN", + "metrics": { + "step": 88, + "train_loss": 0.478, + "train_mean_token_accuracy": 0.924, + "valid_loss": 10.112, + "valid_mean_token_accuracy": 0.145, + "full_valid_loss": 0.567, + "full_valid_mean_token_accuracy": 0.944 + }, + "step_number": 88 + } - CreateImageVariationRequest: + CompletionUsage: type: object + description: Usage statistics for the completion request. properties: - image: - description: The image to use as the basis for the variation(s). Must be a valid PNG file, less than 4MB, and square. - type: string - format: binary - model: - anyOf: - - type: string - - type: string - enum: ["dall-e-2"] - x-oaiTypeLabel: string - default: "dall-e-2" - example: "dall-e-2" - nullable: true - description: The model to use for image generation. Only `dall-e-2` is supported at this time. - n: *images_n - response_format: *images_response_format - size: *dalle2_images_size - user: *end_user_param_configuration + completion_tokens: + type: integer + description: Number of tokens in the generated completion. + prompt_tokens: + type: integer + description: Number of tokens in the prompt. + total_tokens: + type: integer + description: Total number of tokens used in the request (prompt + completion). required: - - image + - prompt_tokens + - completion_tokens + - total_tokens + + RunCompletionUsage: + type: object + description: Usage statistics related to the run. This value will be `null` if the run is not in a terminal state (i.e. `in_progress`, `queued`, etc.). + properties: + completion_tokens: + type: integer + description: Number of completion tokens used over the course of the run. + prompt_tokens: + type: integer + description: Number of prompt tokens used over the course of the run. + total_tokens: + type: integer + description: Total number of tokens used (prompt + completion). + required: + - prompt_tokens + - completion_tokens + - total_tokens + nullable: true + + RunStepCompletionUsage: + type: object + description: Usage statistics related to the run step. This value will be `null` while the run step's status is `in_progress`. + properties: + completion_tokens: + type: integer + description: Number of completion tokens used over the course of the run step. + prompt_tokens: + type: integer + description: Number of prompt tokens used over the course of the run step. + total_tokens: + type: integer + description: Total number of tokens used (prompt + completion). + required: + - prompt_tokens + - completion_tokens + - total_tokens + nullable: true + + AssistantsApiResponseFormatOption: + description: | + Specifies the format that the model must output. Compatible with [GPT-4o](/docs/models/gpt-4o), [GPT-4 Turbo](/docs/models/gpt-4-turbo-and-gpt-4), and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`. + + Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the message the model generates is valid JSON. + + **Important:** when using JSON mode, you **must** also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if `finish_reason="length"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length. + oneOf: + - type: string + description: > + `auto` is the default value + enum: [none, auto] + - $ref: "#/components/schemas/AssistantsApiResponseFormat" + x-oaiExpandable: true - CreateModerationRequest: + AssistantsApiResponseFormat: type: object + description: | + An object describing the expected output of the model. If `json_object` only `function` type `tools` are allowed to be passed to the Run. If `text` the model can return text or any value needed. properties: - input: - description: The input text to classify - oneOf: - - type: string - default: "" - example: "I want to kill them." - - type: array - items: - type: string - default: "" - example: "I want to kill them." - model: - description: | - Two content moderations models are available: `text-moderation-stable` and `text-moderation-latest`. - - The default is `text-moderation-latest` which will be automatically upgraded over time. This ensures you are always using our most accurate model. If you use `text-moderation-stable`, we will provide advanced notice before updating the model. Accuracy of `text-moderation-stable` may be slightly lower than for `text-moderation-latest`. - nullable: false - default: "text-moderation-latest" - example: "text-moderation-stable" - anyOf: - - type: string - - type: string - enum: ["text-moderation-latest", "text-moderation-stable"] - x-oaiTypeLabel: string - required: - - input + type: + type: string + enum: ["text", "json_object"] + example: "json_object" + default: "text" + description: Must be one of `text` or `json_object`. - CreateModerationResponse: + AssistantObject: type: object - description: Represents policy compliance report by OpenAI's content moderation model against a given input. + title: Assistant + description: Represents an `assistant` that can call the model and use tools. properties: id: + description: The identifier, which can be referenced in API endpoints. type: string - description: The unique identifier for the moderation request. + object: + description: The object type, which is always `assistant`. + type: string + enum: [assistant] + created_at: + description: The Unix timestamp (in seconds) for when the assistant was created. + type: integer + name: + description: &assistant_name_param_description | + The name of the assistant. The maximum length is 256 characters. + type: string + maxLength: 256 + nullable: true + description: + description: &assistant_description_param_description | + The description of the assistant. The maximum length is 512 characters. + type: string + maxLength: 512 + nullable: true model: + description: *model_description type: string - description: The model used to generate the moderation results. - results: + instructions: + description: &assistant_instructions_param_description | + The system instructions that the assistant uses. The maximum length is 256,000 characters. + type: string + maxLength: 256000 + nullable: true + tools: + description: &assistant_tools_param_description | + A list of tool enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types `code_interpreter`, `file_search`, or `function`. + default: [] type: array - description: A list of moderation objects. + maxItems: 128 items: - type: object - properties: - flagged: - type: boolean - description: Whether the content violates [OpenAI's usage policies](/policies/usage-policies). - categories: - type: object - description: A list of the categories, and whether they are flagged or not. - properties: - hate: - type: boolean - description: Content that expresses, incites, or promotes hate based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste. Hateful content aimed at non-protected groups (e.g., chess players) is harassment. - hate/threatening: - type: boolean - description: Hateful content that also includes violence or serious harm towards the targeted group based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste. - harassment: - type: boolean - description: Content that expresses, incites, or promotes harassing language towards any target. - harassment/threatening: - type: boolean - description: Harassment content that also includes violence or serious harm towards any target. - self-harm: - type: boolean - description: Content that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders. - self-harm/intent: - type: boolean - description: Content where the speaker expresses that they are engaging or intend to engage in acts of self-harm, such as suicide, cutting, and eating disorders. - self-harm/instructions: - type: boolean - description: Content that encourages performing acts of self-harm, such as suicide, cutting, and eating disorders, or that gives instructions or advice on how to commit such acts. - sexual: - type: boolean - description: Content meant to arouse sexual excitement, such as the description of sexual activity, or that promotes sexual services (excluding sex education and wellness). - sexual/minors: - type: boolean - description: Sexual content that includes an individual who is under 18 years old. - violence: - type: boolean - description: Content that depicts death, violence, or physical injury. - violence/graphic: - type: boolean - description: Content that depicts death, violence, or physical injury in graphic detail. - required: - - hate - - hate/threatening - - harassment - - harassment/threatening - - self-harm - - self-harm/intent - - self-harm/instructions - - sexual - - sexual/minors - - violence - - violence/graphic - category_scores: - type: object - description: A list of the categories along with their scores as predicted by model. - properties: - hate: - type: number - description: The score for the category 'hate'. - hate/threatening: - type: number - description: The score for the category 'hate/threatening'. - harassment: - type: number - description: The score for the category 'harassment'. - harassment/threatening: - type: number - description: The score for the category 'harassment/threatening'. - self-harm: - type: number - description: The score for the category 'self-harm'. - self-harm/intent: - type: number - description: The score for the category 'self-harm/intent'. - self-harm/instructions: - type: number - description: The score for the category 'self-harm/instructions'. - sexual: - type: number - description: The score for the category 'sexual'. - sexual/minors: - type: number - description: The score for the category 'sexual/minors'. - violence: - type: number - description: The score for the category 'violence'. - violence/graphic: - type: number - description: The score for the category 'violence/graphic'. - required: - - hate - - hate/threatening - - harassment - - harassment/threatening - - self-harm - - self-harm/intent - - self-harm/instructions - - sexual - - sexual/minors - - violence - - violence/graphic - required: - - flagged - - categories - - category_scores + oneOf: + - $ref: "#/components/schemas/AssistantToolsCode" + - $ref: "#/components/schemas/AssistantToolsFileSearch" + - $ref: "#/components/schemas/AssistantToolsFunction" + x-oaiExpandable: true + tool_resources: + type: object + description: | + A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs. + properties: + code_interpreter: + type: object + properties: + file_ids: + type: array + description: | + A list of [file](/docs/api-reference/files) IDs made available to the `code_interpreter`` tool. There can be a maximum of 20 files associated with the tool. + default: [] + maxItems: 20 + items: + type: string + file_search: + type: object + properties: + vector_store_ids: + type: array + description: | + The ID of the [vector store](/docs/api-reference/vector-stores/object) attached to this assistant. There can be a maximum of 1 vector store attached to the assistant. + maxItems: 1 + items: + type: string + nullable: true + metadata: + description: &metadata_description | + Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long. + type: object + x-oaiTypeLabel: map + nullable: true + temperature: + description: &run_temperature_description | + What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. + type: number + minimum: 0 + maximum: 2 + default: 1 + example: 1 + nullable: true + top_p: + type: number + minimum: 0 + maximum: 1 + default: 1 + example: 1 + nullable: true + description: &run_top_p_description | + An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. + + We generally recommend altering this or temperature but not both. + response_format: + $ref: "#/components/schemas/AssistantsApiResponseFormatOption" + nullable: true required: - id + - object + - created_at + - name + - description - model - - results + - instructions + - tools + - metadata x-oaiMeta: - name: The moderation object - example: *moderation_example + name: The assistant object + beta: true + example: *create_assistants_example - ListFilesResponse: + CreateAssistantRequest: type: object + additionalProperties: false properties: - data: + model: + description: *model_description + example: "gpt-4-turbo" + anyOf: + - type: string + - type: string + enum: + [ + "gpt-4o", + "gpt-4o-2024-05-13", + "gpt-4-turbo", + "gpt-4-turbo-2024-04-09", + "gpt-4-0125-preview", + "gpt-4-turbo-preview", + "gpt-4-1106-preview", + "gpt-4-vision-preview", + "gpt-4", + "gpt-4-0314", + "gpt-4-0613", + "gpt-4-32k", + "gpt-4-32k-0314", + "gpt-4-32k-0613", + "gpt-3.5-turbo", + "gpt-3.5-turbo-16k", + "gpt-3.5-turbo-0613", + "gpt-3.5-turbo-1106", + "gpt-3.5-turbo-0125", + "gpt-3.5-turbo-16k-0613", + ] + x-oaiTypeLabel: string + name: + description: *assistant_name_param_description + type: string + nullable: true + maxLength: 256 + description: + description: *assistant_description_param_description + type: string + nullable: true + maxLength: 512 + instructions: + description: *assistant_instructions_param_description + type: string + nullable: true + maxLength: 256000 + tools: + description: *assistant_tools_param_description + default: [] type: array + maxItems: 128 items: - $ref: "#/components/schemas/OpenAIFile" - object: - type: string - enum: [list] + oneOf: + - $ref: "#/components/schemas/AssistantToolsCode" + - $ref: "#/components/schemas/AssistantToolsFileSearch" + - $ref: "#/components/schemas/AssistantToolsFunction" + x-oaiExpandable: true + tool_resources: + type: object + description: | + A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs. + properties: + code_interpreter: + type: object + properties: + file_ids: + type: array + description: | + A list of [file](/docs/api-reference/files) IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool. + default: [] + maxItems: 20 + items: + type: string + file_search: + type: object + properties: + vector_store_ids: + type: array + description: | + The [vector store](/docs/api-reference/vector-stores/object) attached to this assistant. There can be a maximum of 1 vector store attached to the assistant. + maxItems: 1 + items: + type: string + vector_stores: + type: array + description: | + A helper to create a [vector store](/docs/api-reference/vector-stores/object) with file_ids and attach it to this assistant. There can be a maximum of 1 vector store attached to the assistant. + maxItems: 1 + items: + type: object + properties: + file_ids: + type: array + description: | + A list of [file](/docs/api-reference/files) IDs to add to the vector store. There can be a maximum of 10000 files in a vector store. + maxItems: 10000 + items: + type: string + metadata: + type: object + description: | + Set of 16 key-value pairs that can be attached to a vector store. This can be useful for storing additional information about the vector store in a structured format. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long. + x-oaiTypeLabel: map + oneOf: + - required: [vector_store_ids] + - required: [vector_stores] + nullable: true + metadata: + description: *metadata_description + type: object + x-oaiTypeLabel: map + nullable: true + temperature: + description: &run_temperature_description | + What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. + type: number + minimum: 0 + maximum: 2 + default: 1 + example: 1 + nullable: true + top_p: + type: number + minimum: 0 + maximum: 1 + default: 1 + example: 1 + nullable: true + description: &run_top_p_description | + An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. + + We generally recommend altering this or temperature but not both. + response_format: + $ref: "#/components/schemas/AssistantsApiResponseFormatOption" + nullable: true required: - - object - - data + - model - CreateFileRequest: + ModifyAssistantRequest: type: object additionalProperties: false properties: - file: - description: | - The File object (not file name) to be uploaded. + model: + description: *model_description + anyOf: + - type: string + name: + description: *assistant_name_param_description type: string - format: binary - purpose: + nullable: true + maxLength: 256 + description: + description: *assistant_description_param_description + type: string + nullable: true + maxLength: 512 + instructions: + description: *assistant_instructions_param_description + type: string + nullable: true + maxLength: 256000 + tools: + description: *assistant_tools_param_description + default: [] + type: array + maxItems: 128 + items: + oneOf: + - $ref: "#/components/schemas/AssistantToolsCode" + - $ref: "#/components/schemas/AssistantToolsFileSearch" + - $ref: "#/components/schemas/AssistantToolsFunction" + x-oaiExpandable: true + tool_resources: + type: object description: | - The intended purpose of the uploaded file. + A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs. + properties: + code_interpreter: + type: object + properties: + file_ids: + type: array + description: | + Overrides the list of [file](/docs/api-reference/files) IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool. + default: [] + maxItems: 20 + items: + type: string + file_search: + type: object + properties: + vector_store_ids: + type: array + description: | + Overrides the [vector store](/docs/api-reference/vector-stores/object) attached to this assistant. There can be a maximum of 1 vector store attached to the assistant. + maxItems: 1 + items: + type: string + nullable: true + metadata: + description: *metadata_description + type: object + x-oaiTypeLabel: map + nullable: true + temperature: + description: *run_temperature_description + type: number + minimum: 0 + maximum: 2 + default: 1 + example: 1 + nullable: true + top_p: + type: number + minimum: 0 + maximum: 1 + default: 1 + example: 1 + nullable: true + description: &run_top_p_description | + An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. - Use "fine-tune" for [Fine-tuning](/docs/api-reference/fine-tuning) and "assistants" for [Assistants](/docs/api-reference/assistants) and [Messages](/docs/api-reference/messages). This allows us to validate the format of the uploaded file is correct for fine-tuning. - type: string - enum: ["fine-tune", "assistants"] - required: - - file - - purpose + We generally recommend altering this or temperature but not both. + response_format: + $ref: "#/components/schemas/AssistantsApiResponseFormatOption" + nullable: true - DeleteFileResponse: + DeleteAssistantResponse: type: object properties: id: type: string - object: - type: string - enum: [file] deleted: type: boolean + object: + type: string + enum: [assistant.deleted] required: - id - object - deleted - CreateFineTuningJobRequest: + ListAssistantsResponse: type: object properties: - model: - description: | - The name of the model to fine-tune. You can select one of the - [supported models](/docs/guides/fine-tuning/what-models-can-be-fine-tuned). - example: "gpt-3.5-turbo" - anyOf: - - type: string - - type: string - enum: ["babbage-002", "davinci-002", "gpt-3.5-turbo"] - x-oaiTypeLabel: string - training_file: - description: | - The ID of an uploaded file that contains training data. - - See [upload file](/docs/api-reference/files/upload) for how to upload a file. - - Your dataset must be formatted as a JSONL file. Additionally, you must upload your file with the purpose `fine-tune`. - - See the [fine-tuning guide](/docs/guides/fine-tuning) for more details. + object: type: string - example: "file-abc123" - hyperparameters: - type: object - description: The hyperparameters used for the fine-tuning job. - properties: - batch_size: - description: | - Number of examples in each batch. A larger batch size means that model parameters - are updated less frequently, but with lower variance. - oneOf: - - type: string - enum: [auto] - - type: integer - minimum: 1 - maximum: 256 - default: auto - learning_rate_multiplier: - description: | - Scaling factor for the learning rate. A smaller learning rate may be useful to avoid - overfitting. - oneOf: - - type: string - enum: [auto] - - type: number - minimum: 0 - exclusiveMinimum: true - default: auto - n_epochs: - description: | - The number of epochs to train the model for. An epoch refers to one full cycle - through the training dataset. - oneOf: - - type: string - enum: [auto] - - type: integer - minimum: 1 - maximum: 50 - default: auto - suffix: - description: | - A string of up to 18 characters that will be added to your fine-tuned model name. - - For example, a `suffix` of "custom-model-name" would produce a model name like `ft:gpt-3.5-turbo:openai:custom-model-name:7p4lURel`. + example: "list" + data: + type: array + items: + $ref: "#/components/schemas/AssistantObject" + first_id: type: string - minLength: 1 - maxLength: 40 - default: null - nullable: true - validation_file: - description: | - The ID of an uploaded file that contains validation data. - - If you provide this file, the data is used to generate validation - metrics periodically during fine-tuning. These metrics can be viewed in - the fine-tuning results file. - The same data should not be present in both train and validation files. + example: "asst_abc123" + last_id: + type: string + example: "asst_abc456" + has_more: + type: boolean + example: false + required: + - object + - data + - first_id + - last_id + - has_more + x-oaiMeta: + name: List assistants response object + group: chat + example: *list_assistants_example - Your dataset must be formatted as a JSONL file. You must upload your file with the purpose `fine-tune`. + AssistantToolsCode: + type: object + title: Code interpreter tool + properties: + type: + type: string + description: "The type of tool being defined: `code_interpreter`" + enum: ["code_interpreter"] + required: + - type - See the [fine-tuning guide](/docs/guides/fine-tuning) for more details. + AssistantToolsFileSearch: + type: object + title: FileSearch tool + properties: + type: type: string - nullable: true - example: "file-abc123" + description: "The type of tool being defined: `file_search`" + enum: ["file_search"] required: - - model - - training_file + - type - ListFineTuningJobEventsResponse: + AssistantToolsFunction: type: object + title: Function tool properties: - data: - type: array - items: - $ref: "#/components/schemas/FineTuningJobEvent" - object: + type: type: string - enum: [list] + description: "The type of tool being defined: `function`" + enum: ["function"] + function: + $ref: "#/components/schemas/FunctionObject" required: - - object - - data + - type + - function - CreateEmbeddingRequest: + TruncationObject: type: object - additionalProperties: false + title: Thread Truncation Controls + description: Controls for how a thread will be truncated prior to the run. Use this to control the intial context window of the run. properties: - input: - description: | - Input text to embed, encoded as a string or array of tokens. To embed multiple inputs in a single request, pass an array of strings or array of token arrays. The input must not exceed the max input tokens for the model (8192 tokens for `text-embedding-ada-002`), cannot be an empty string, and any array must be 2048 dimensions or less. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens. - example: "The quick brown fox jumped over the lazy dog" - oneOf: - - type: string - title: string - description: The string that will be turned into an embedding. - default: "" - example: "This is a test." - - type: array - title: array - description: The array of strings that will be turned into an embedding. - minItems: 1 - maxItems: 2048 - items: - type: string - default: "" - example: "['This is a test.']" - - type: array - title: array - description: The array of integers that will be turned into an embedding. - minItems: 1 - maxItems: 2048 - items: - type: integer - example: "[1212, 318, 257, 1332, 13]" - - type: array - title: array - description: The array of arrays containing integers that will be turned into an embedding. - minItems: 1 - maxItems: 2048 - items: - type: array - minItems: 1 - items: - type: integer - example: "[[1212, 318, 257, 1332, 13]]" - x-oaiExpandable: true - model: - description: *model_description - example: "text-embedding-3-small" - anyOf: - - type: string - - type: string - enum: ["text-embedding-ada-002", "text-embedding-3-small", "text-embedding-3-large"] - x-oaiTypeLabel: string - encoding_format: - description: "The format to return the embeddings in. Can be either `float` or [`base64`](https://pypi.org/project/pybase64/)." - example: "float" - default: "float" + type: type: string - enum: ["float", "base64"] - dimensions: - description: | - The number of dimensions the resulting output embeddings should have. Only supported in `text-embedding-3` and later models. + description: The truncation strategy to use for the thread. The default is `auto`. If set to `last_messages`, the thread will be truncated to the n most recent messages in the thread. When set to `auto`, messages in the middle of the thread will be dropped to fit the context length of the model, `max_prompt_tokens`. + enum: ["auto", "last_messages"] + last_messages: type: integer + description: The number of most recent messages from the thread when constructing the context for the run. minimum: 1 - user: *end_user_param_configuration + nullable: true required: - - model - - input + - type - CreateEmbeddingResponse: + AssistantsApiToolChoiceOption: + description: | + Controls which (if any) tool is called by the model. + `none` means the model will not call any tools and instead generates a message. + `auto` is the default value and means the model can pick between generating a message or calling one or more tools. + `required` means the model must call one or more tools before responding to the user. + Specifying a particular tool like `{"type": "file_search"}` or `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that tool. + + oneOf: + - type: string + description: > + `none` means the model will not call any tools and instead generates a message. + `auto` means the model can pick between generating a message or calling one or more tools. + `required` means the model must call one or more tools before responding to the user. + enum: [none, auto, required] + - $ref: "#/components/schemas/AssistantsNamedToolChoice" + x-oaiExpandable: true + + AssistantsNamedToolChoice: type: object + description: Specifies a tool the model should use. Use to force the model to call a specific tool. properties: - data: - type: array - description: The list of embeddings generated by the model. - items: - $ref: "#/components/schemas/Embedding" - model: - type: string - description: The name of the model used to generate the embedding. - object: + type: type: string - description: The object type, which is always "list". - enum: [list] - usage: + enum: ["function", "code_interpreter", "file_search"] + description: The type of the tool. If type is `function`, the function name must be set + function: type: object - description: The usage information for the request. properties: - prompt_tokens: - type: integer - description: The number of tokens used by the prompt. - total_tokens: - type: integer - description: The total number of tokens used by the request. + name: + type: string + description: The name of the function to call. required: - - prompt_tokens - - total_tokens + - name required: - - object - - model - - data - - usage + - type - CreateTranscriptionRequest: + RunObject: type: object - additionalProperties: false + title: A run on a thread + description: Represents an execution run on a [thread](/docs/api-reference/threads). properties: - file: - description: | - The audio file object (not file name) to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm. + id: + description: The identifier, which can be referenced in API endpoints. type: string - x-oaiTypeLabel: file - format: binary - model: - description: | - ID of the model to use. Only `whisper-1` is currently available. - example: whisper-1 - anyOf: - - type: string - - type: string - enum: ["whisper-1"] - x-oaiTypeLabel: string - language: - description: | - The language of the input audio. Supplying the input language in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) format will improve accuracy and latency. + object: + description: The object type, which is always `thread.run`. type: string - prompt: - description: | - An optional text to guide the model's style or continue a previous audio segment. The [prompt](/docs/guides/speech-to-text/prompting) should match the audio language. + enum: ["thread.run"] + created_at: + description: The Unix timestamp (in seconds) for when the run was created. + type: integer + thread_id: + description: The ID of the [thread](/docs/api-reference/threads) that was executed on as a part of this run. type: string - response_format: - description: | - The format of the transcript output, in one of these options: `json`, `text`, `srt`, `verbose_json`, or `vtt`. + assistant_id: + description: The ID of the [assistant](/docs/api-reference/assistants) used for execution of this run. + type: string + status: + description: The status of the run, which can be either `queued`, `in_progress`, `requires_action`, `cancelling`, `cancelled`, `failed`, `completed`, `incomplete`, or `expired`. type: string enum: - - json - - text - - srt - - verbose_json - - vtt - default: json + [ + "queued", + "in_progress", + "requires_action", + "cancelling", + "cancelled", + "failed", + "completed", + "incomplete", + "expired", + ] + required_action: + type: object + description: Details on the action required to continue the run. Will be `null` if no action is required. + nullable: true + properties: + type: + description: For now, this is always `submit_tool_outputs`. + type: string + enum: ["submit_tool_outputs"] + submit_tool_outputs: + type: object + description: Details on the tool outputs needed for this run to continue. + properties: + tool_calls: + type: array + description: A list of the relevant tool calls. + items: + $ref: "#/components/schemas/RunToolCallObject" + required: + - tool_calls + required: + - type + - submit_tool_outputs + last_error: + type: object + description: The last error associated with this run. Will be `null` if there are no errors. + nullable: true + properties: + code: + type: string + description: One of `server_error`, `rate_limit_exceeded`, or `invalid_prompt`. + enum: ["server_error", "rate_limit_exceeded", "invalid_prompt"] + message: + type: string + description: A human-readable description of the error. + required: + - code + - message + expires_at: + description: The Unix timestamp (in seconds) for when the run will expire. + type: integer + nullable: true + started_at: + description: The Unix timestamp (in seconds) for when the run was started. + type: integer + nullable: true + cancelled_at: + description: The Unix timestamp (in seconds) for when the run was cancelled. + type: integer + nullable: true + failed_at: + description: The Unix timestamp (in seconds) for when the run failed. + type: integer + nullable: true + completed_at: + description: The Unix timestamp (in seconds) for when the run was completed. + type: integer + nullable: true + incomplete_details: + description: Details on why the run is incomplete. Will be `null` if the run is not incomplete. + type: object + nullable: true + properties: + reason: + description: The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run. + type: string + enum: ["max_completion_tokens", "max_prompt_tokens"] + model: + description: The model that the [assistant](/docs/api-reference/assistants) used for this run. + type: string + instructions: + description: The instructions that the [assistant](/docs/api-reference/assistants) used for this run. + type: string + tools: + description: The list of tools that the [assistant](/docs/api-reference/assistants) used for this run. + default: [] + type: array + maxItems: 20 + items: + oneOf: + - $ref: "#/components/schemas/AssistantToolsCode" + - $ref: "#/components/schemas/AssistantToolsFileSearch" + - $ref: "#/components/schemas/AssistantToolsFunction" + x-oaiExpandable: true + metadata: + description: *metadata_description + type: object + x-oaiTypeLabel: map + nullable: true + usage: + $ref: "#/components/schemas/RunCompletionUsage" temperature: - description: | - The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use [log probability](https://en.wikipedia.org/wiki/Log_probability) to automatically increase the temperature until certain thresholds are hit. + description: The sampling temperature used for this run. If not set, defaults to 1. type: number - default: 0 - timestamp_granularities[]: + nullable: true + top_p: + description: The nucleus sampling value used for this run. If not set, defaults to 1. + type: number + nullable: true + max_prompt_tokens: + type: integer + nullable: true description: | - The timestamp granularities to populate for this transcription. Any of these options: `word`, or `segment`. Note: There is no additional latency for segment timestamps, but generating word timestamps incurs additional latency. - type: array - items: - type: string - enum: - - word - - segment - default: [segment] + The maximum number of prompt tokens specified to have been used over the course of the run. + minimum: 256 + max_completion_tokens: + type: integer + nullable: true + description: | + The maximum number of completion tokens specified to have been used over the course of the run. + minimum: 256 + truncation_strategy: + $ref: "#/components/schemas/TruncationObject" + nullable: true + tool_choice: + $ref: "#/components/schemas/AssistantsApiToolChoiceOption" + nullable: true + response_format: + $ref: "#/components/schemas/AssistantsApiResponseFormatOption" + nullable: true required: - - file + - id + - object + - created_at + - thread_id + - assistant_id + - status + - required_action + - last_error + - expires_at + - started_at + - cancelled_at + - failed_at + - completed_at - model - - # Note: This does not currently support the non-default response format types. - CreateTranscriptionResponse: - type: object - properties: - text: - type: string - required: - - text - - CreateTranslationRequest: + - instructions + - tools + - metadata + - usage + - incomplete_details + - max_prompt_tokens + - max_completion_tokens + - truncation_strategy + - tool_choice + - response_format + x-oaiMeta: + name: The run object + beta: true + example: | + { + "id": "run_abc123", + "object": "thread.run", + "created_at": 1698107661, + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "status": "completed", + "started_at": 1699073476, + "expires_at": null, + "cancelled_at": null, + "failed_at": null, + "completed_at": 1699073498, + "last_error": null, + "model": "gpt-4-turbo", + "instructions": null, + "tools": [{"type": "file_search"}, {"type": "code_interpreter"}], + "metadata": {}, + "incomplete_details": null, + "usage": { + "prompt_tokens": 123, + "completion_tokens": 456, + "total_tokens": 579 + }, + "temperature": 1.0, + "top_p": 1.0, + "max_prompt_tokens": 1000, + "max_completion_tokens": 1000, + "truncation_strategy": { + "type": "auto", + "last_messages": null + }, + "response_format": "auto", + "tool_choice": "auto" + } + CreateRunRequest: type: object additionalProperties: false properties: - file: - description: | - The audio file object (not file name) translate, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm. + assistant_id: + description: The ID of the [assistant](/docs/api-reference/assistants) to use to execute this run. type: string - x-oaiTypeLabel: file - format: binary model: - description: | - ID of the model to use. Only `whisper-1` is currently available. - example: whisper-1 + description: The ID of the [Model](/docs/api-reference/models) to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used. + example: "gpt-4-turbo" anyOf: - type: string - type: string - enum: ["whisper-1"] + enum: + [ + "gpt-4o", + "gpt-4o-2024-05-13", + "gpt-4-turbo", + "gpt-4-turbo-2024-04-09", + "gpt-4-0125-preview", + "gpt-4-turbo-preview", + "gpt-4-1106-preview", + "gpt-4-vision-preview", + "gpt-4", + "gpt-4-0314", + "gpt-4-0613", + "gpt-4-32k", + "gpt-4-32k-0314", + "gpt-4-32k-0613", + "gpt-3.5-turbo", + "gpt-3.5-turbo-16k", + "gpt-3.5-turbo-0613", + "gpt-3.5-turbo-1106", + "gpt-3.5-turbo-0125", + "gpt-3.5-turbo-16k-0613", + ] x-oaiTypeLabel: string - prompt: - description: | - An optional text to guide the model's style or continue a previous audio segment. The [prompt](/docs/guides/speech-to-text/prompting) should be in English. + nullable: true + instructions: + description: Overrides the [instructions](/docs/api-reference/assistants/createAssistant) of the assistant. This is useful for modifying the behavior on a per-run basis. type: string - response_format: - description: | - The format of the transcript output, in one of these options: `json`, `text`, `srt`, `verbose_json`, or `vtt`. + nullable: true + additional_instructions: + description: Appends additional instructions at the end of the instructions for the run. This is useful for modifying the behavior on a per-run basis without overriding other instructions. type: string - default: json + nullable: true + additional_messages: + description: Adds additional messages to the thread before creating the run. + type: array + items: + $ref: "#/components/schemas/CreateMessageRequest" + nullable: true + tools: + description: Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis. + nullable: true + type: array + maxItems: 20 + items: + oneOf: + - $ref: "#/components/schemas/AssistantToolsCode" + - $ref: "#/components/schemas/AssistantToolsFileSearch" + - $ref: "#/components/schemas/AssistantToolsFunction" + x-oaiExpandable: true + metadata: + description: *metadata_description + type: object + x-oaiTypeLabel: map + nullable: true temperature: - description: | - The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use [log probability](https://en.wikipedia.org/wiki/Log_probability) to automatically increase the temperature until certain thresholds are hit. type: number - default: 0 - required: - - file - - model - - # Note: This does not currently support the non-default response format types. - CreateTranslationResponse: - type: object - properties: - text: - type: string - required: - - text - - CreateSpeechRequest: - type: object - additionalProperties: false - properties: - model: - description: | - One of the available [TTS models](/docs/models/tts): `tts-1` or `tts-1-hd` - anyOf: - - type: string - - type: string - enum: ["tts-1", "tts-1-hd"] - x-oaiTypeLabel: string - input: - type: string - description: The text to generate audio for. The maximum length is 4096 characters. - maxLength: 4096 - voice: - description: The voice to use when generating the audio. Supported voices are `alloy`, `echo`, `fable`, `onyx`, `nova`, and `shimmer`. Previews of the voices are available in the [Text to speech guide](/docs/guides/text-to-speech/voice-options). - type: string - enum: ["alloy", "echo", "fable", "onyx", "nova", "shimmer"] - response_format: - description: |- - The format to return audio in. - Supported formats are `mp3`, `opus`, `aac`, `flac`, `pcm`, and `wav`. - - The `pcm` audio format, similar to `wav` but without a header, utilizes a 24kHz sample rate, mono channel, and 16-bit depth in signed little-endian format. - default: "mp3" - type: string - enum: ["mp3", "opus", "aac", "flac", "pcm", "wav"] - speed: - description: "The speed of the generated audio. Select a value from `0.25` to `4.0`. `1.0` is the default." + minimum: 0 + maximum: 2 + default: 1 + example: 1 + nullable: true + description: *run_temperature_description + top_p: type: number - default: 1.0 - minimum: 0.25 - maximum: 4.0 - required: - - model - - input - - voice - - Model: - title: Model - description: Describes an OpenAI model offering that can be used with the API. - properties: - id: - type: string - description: The model identifier, which can be referenced in the API endpoints. - created: - type: integer - description: The Unix timestamp (in seconds) when the model was created. - object: - type: string - description: The object type, which is always "model". - enum: [model] - owned_by: - type: string - description: The organization that owns the model. - required: - - id - - object - - created - - owned_by - x-oaiMeta: - name: The model object - example: *retrieve_model_response + minimum: 0 + maximum: 1 + default: 1 + example: 1 + nullable: true + description: &run_top_p_description | + An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. - OpenAIFile: - title: OpenAIFile - description: The `File` object represents a document that has been uploaded to OpenAI. - properties: - id: - type: string - description: The file identifier, which can be referenced in the API endpoints. - bytes: + We generally recommend altering this or temperature but not both. + stream: + type: boolean + nullable: true + description: | + If `true`, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a `data: [DONE]` message. + max_prompt_tokens: type: integer - description: The size of the file, in bytes. - created_at: + nullable: true + description: | + The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status `incomplete`. See `incomplete_details` for more info. + minimum: 256 + max_completion_tokens: type: integer - description: The Unix timestamp (in seconds) for when the file was created. - filename: - type: string - description: The name of the file. + nullable: true + description: | + The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status `incomplete`. See `incomplete_details` for more info. + minimum: 256 + truncation_strategy: + $ref: "#/components/schemas/TruncationObject" + nullable: true + tool_choice: + $ref: "#/components/schemas/AssistantsApiToolChoiceOption" + nullable: true + response_format: + $ref: "#/components/schemas/AssistantsApiResponseFormatOption" + nullable: true + required: + - thread_id + - assistant_id + ListRunsResponse: + type: object + properties: object: type: string - description: The object type, which is always `file`. - enum: ["file"] - purpose: - type: string - description: The intended purpose of the file. Supported values are `fine-tune`, `fine-tune-results`, `assistants`, and `assistants_output`. - enum: - [ - "fine-tune", - "fine-tune-results", - "assistants", - "assistants_output", - ] - status: + example: "list" + data: + type: array + items: + $ref: "#/components/schemas/RunObject" + first_id: type: string - deprecated: true - description: Deprecated. The current status of the file, which can be either `uploaded`, `processed`, or `error`. - enum: ["uploaded", "processed", "error"] - status_details: + example: "run_abc123" + last_id: type: string - deprecated: true - description: Deprecated. For details on why a fine-tuning training file failed validation, see the `error` field on `fine_tuning.job`. + example: "run_abc456" + has_more: + type: boolean + example: false required: - - id - object - - bytes - - created_at - - filename - - purpose - - status - x-oaiMeta: - name: The file object - example: | - { - "id": "file-abc123", - "object": "file", - "bytes": 120000, - "created_at": 1677610602, - "filename": "salesOverview.pdf", - "purpose": "assistants", - } - Embedding: + - data + - first_id + - last_id + - has_more + ModifyRunRequest: type: object - description: | - Represents an embedding vector returned by embedding endpoint. + additionalProperties: false properties: - index: - type: integer - description: The index of the embedding in the list of embeddings. - embedding: + metadata: + description: *metadata_description + type: object + x-oaiTypeLabel: map + nullable: true + SubmitToolOutputsRunRequest: + type: object + additionalProperties: false + properties: + tool_outputs: + description: A list of tools for which the outputs are being submitted. type: array - description: | - The embedding vector, which is a list of floats. The length of vector depends on the model as listed in the [embedding guide](/docs/guides/embeddings). items: - type: number - object: - type: string - description: The object type, which is always "embedding". - enum: [embedding] + type: object + properties: + tool_call_id: + type: string + description: The ID of the tool call in the `required_action` object within the run object the output is being submitted for. + output: + type: string + description: The output of the tool call to be submitted to continue the run. + stream: + type: boolean + nullable: true + description: | + If `true`, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a `data: [DONE]` message. required: - - index - - object - - embedding - x-oaiMeta: - name: The embedding object - example: | - { - "object": "embedding", - "embedding": [ - 0.0023064255, - -0.009327292, - .... (1536 floats total for ada-002) - -0.0028842222, - ], - "index": 0 - } + - tool_outputs - FineTuningJob: + RunToolCallObject: type: object - title: FineTuningJob - description: | - The `fine_tuning.job` object represents a fine-tuning job that has been created through the API. + description: Tool call objects properties: id: type: string - description: The object identifier, which can be referenced in the API endpoints. - created_at: - type: integer - description: The Unix timestamp (in seconds) for when the fine-tuning job was created. - error: + description: The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the [Submit tool outputs to run](/docs/api-reference/runs/submitToolOutputs) endpoint. + type: + type: string + description: The type of tool call the output is required for. For now, this is always `function`. + enum: ["function"] + function: type: object - nullable: true - description: For fine-tuning jobs that have `failed`, this will contain more information on the cause of the failure. + description: The function definition. properties: - code: - type: string - description: A machine-readable error code. - message: + name: type: string - description: A human-readable error message. - param: + description: The name of the function. + arguments: type: string - description: The parameter that was invalid, usually `training_file` or `validation_file`. This field will be null if the failure was not parameter-specific. - nullable: true + description: The arguments that the model expects you to pass to the function. required: - - code - - message - - param - fine_tuned_model: + - name + - arguments + required: + - id + - type + - function + + CreateThreadAndRunRequest: + type: object + additionalProperties: false + properties: + assistant_id: + description: The ID of the [assistant](/docs/api-reference/assistants) to use to execute this run. + type: string + thread: + $ref: "#/components/schemas/CreateThreadRequest" + description: If no thread is provided, an empty thread will be created. + model: + description: The ID of the [Model](/docs/api-reference/models) to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used. + example: "gpt-4-turbo" + anyOf: + - type: string + - type: string + enum: + [ + "gpt-4o", + "gpt-4o-2024-05-13", + "gpt-4-turbo", + "gpt-4-turbo-2024-04-09", + "gpt-4-0125-preview", + "gpt-4-turbo-preview", + "gpt-4-1106-preview", + "gpt-4-vision-preview", + "gpt-4", + "gpt-4-0314", + "gpt-4-0613", + "gpt-4-32k", + "gpt-4-32k-0314", + "gpt-4-32k-0613", + "gpt-3.5-turbo", + "gpt-3.5-turbo-16k", + "gpt-3.5-turbo-0613", + "gpt-3.5-turbo-1106", + "gpt-3.5-turbo-0125", + "gpt-3.5-turbo-16k-0613", + ] + x-oaiTypeLabel: string + nullable: true + instructions: + description: Override the default system message of the assistant. This is useful for modifying the behavior on a per-run basis. type: string nullable: true - description: The name of the fine-tuned model that is being created. The value will be null if the fine-tuning job is still running. - finished_at: + tools: + description: Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis. + nullable: true + type: array + maxItems: 20 + items: + oneOf: + - $ref: "#/components/schemas/AssistantToolsCode" + - $ref: "#/components/schemas/AssistantToolsFileSearch" + - $ref: "#/components/schemas/AssistantToolsFunction" + tool_resources: + type: object + description: | + A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs. + properties: + code_interpreter: + type: object + properties: + file_ids: + type: array + description: | + A list of [file](/docs/api-reference/files) IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool. + default: [] + maxItems: 20 + items: + type: string + file_search: + type: object + properties: + vector_store_ids: + type: array + description: | + The ID of the [vector store](/docs/api-reference/vector-stores/object) attached to this assistant. There can be a maximum of 1 vector store attached to the assistant. + maxItems: 1 + items: + type: string + nullable: true + metadata: + description: *metadata_description + type: object + x-oaiTypeLabel: map + nullable: true + temperature: + type: number + minimum: 0 + maximum: 2 + default: 1 + example: 1 + nullable: true + description: *run_temperature_description + top_p: + type: number + minimum: 0 + maximum: 1 + default: 1 + example: 1 + nullable: true + description: *run_top_p_description + stream: + type: boolean + nullable: true + description: | + If `true`, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a `data: [DONE]` message. + max_prompt_tokens: type: integer nullable: true - description: The Unix timestamp (in seconds) for when the fine-tuning job was finished. The value will be null if the fine-tuning job is still running. - hyperparameters: - type: object - description: The hyperparameters used for the fine-tuning job. See the [fine-tuning guide](/docs/guides/fine-tuning) for more details. - properties: - n_epochs: - oneOf: - - type: string - enum: [auto] - - type: integer - minimum: 1 - maximum: 50 - default: auto - description: - The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset. - - "auto" decides the optimal number of epochs based on the size of the dataset. If setting the number manually, we support any number between 1 and 50 epochs. - required: - - n_epochs - model: - type: string - description: The base model that is being fine-tuned. - object: - type: string - description: The object type, which is always "fine_tuning.job". - enum: [fine_tuning.job] - organization_id: - type: string - description: The organization that owns the fine-tuning job. - result_files: - type: array - description: The compiled results file ID(s) for the fine-tuning job. You can retrieve the results with the [Files API](/docs/api-reference/files/retrieve-contents). - items: - type: string - example: file-abc123 - status: - type: string - description: The current status of the fine-tuning job, which can be either `validating_files`, `queued`, `running`, `succeeded`, `failed`, or `cancelled`. - enum: - [ - "validating_files", - "queued", - "running", - "succeeded", - "failed", - "cancelled", - ] - trained_tokens: + description: | + The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status `incomplete`. See `incomplete_details` for more info. + minimum: 256 + max_completion_tokens: type: integer nullable: true - description: The total number of billable tokens processed by this fine-tuning job. The value will be null if the fine-tuning job is still running. - training_file: - type: string - description: The file ID used for training. You can retrieve the training data with the [Files API](/docs/api-reference/files/retrieve-contents). - validation_file: - type: string + description: | + The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status `incomplete`. See `incomplete_details` for more info. + minimum: 256 + truncation_strategy: + $ref: "#/components/schemas/TruncationObject" + nullable: true + tool_choice: + $ref: "#/components/schemas/AssistantsApiToolChoiceOption" + nullable: true + response_format: + $ref: "#/components/schemas/AssistantsApiResponseFormatOption" nullable: true - description: The file ID used for validation. You can retrieve the validation results with the [Files API](/docs/api-reference/files/retrieve-contents). required: - - created_at - - error - - finished_at - - fine_tuned_model - - hyperparameters - - id - - model - - object - - organization_id - - result_files - - status - - trained_tokens - - training_file - - validation_file - x-oaiMeta: - name: The fine-tuning job object - example: *fine_tuning_example + - thread_id + - assistant_id - FineTuningJobEvent: + ThreadObject: type: object - description: Fine-tuning job event object + title: Thread + description: Represents a thread that contains [messages](/docs/api-reference/messages). properties: id: - type: string - created_at: - type: integer - level: - type: string - enum: ["info", "warn", "error"] - message: + description: The identifier, which can be referenced in API endpoints. type: string object: + description: The object type, which is always `thread`. type: string - enum: [fine_tuning.job.event] + enum: ["thread"] + created_at: + description: The Unix timestamp (in seconds) for when the thread was created. + type: integer + tool_resources: + type: object + description: | + A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs. + properties: + code_interpreter: + type: object + properties: + file_ids: + type: array + description: | + A list of [file](/docs/api-reference/files) IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool. + default: [] + maxItems: 20 + items: + type: string + file_search: + type: object + properties: + vector_store_ids: + type: array + description: | + The [vector store](/docs/api-reference/vector-stores/object) attached to this thread. There can be a maximum of 1 vector store attached to the thread. + maxItems: 1 + items: + type: string + nullable: true + metadata: + description: *metadata_description + type: object + x-oaiTypeLabel: map + nullable: true required: - id - object - created_at - - level - - message + - tool_resources + - metadata x-oaiMeta: - name: The fine-tuning job event object + name: The thread object + beta: true example: | { - "object": "fine_tuning.job.event", - "id": "ftevent-abc123" - "created_at": 1677610602, - "level": "info", - "message": "Created fine-tuning job" + "id": "thread_abc123", + "object": "thread", + "created_at": 1698107661, + "metadata": {} } - CompletionUsage: + CreateThreadRequest: type: object - description: Usage statistics for the completion request. + additionalProperties: false properties: - completion_tokens: - type: integer - description: Number of tokens in the generated completion. - prompt_tokens: - type: integer - description: Number of tokens in the prompt. - total_tokens: - type: integer - description: Total number of tokens used in the request (prompt + completion). - required: - - prompt_tokens - - completion_tokens - - total_tokens + messages: + description: A list of [messages](/docs/api-reference/messages) to start the thread with. + type: array + items: + $ref: "#/components/schemas/CreateMessageRequest" + tool_resources: + type: object + description: | + A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs. + properties: + code_interpreter: + type: object + properties: + file_ids: + type: array + description: | + A list of [file](/docs/api-reference/files) IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool. + default: [] + maxItems: 20 + items: + type: string + file_search: + type: object + properties: + vector_store_ids: + type: array + description: | + The [vector store](/docs/api-reference/vector-stores/object) attached to this thread. There can be a maximum of 1 vector store attached to the thread. + maxItems: 1 + items: + type: string + vector_stores: + type: array + description: | + A helper to create a [vector store](/docs/api-reference/vector-stores/object) with file_ids and attach it to this thread. There can be a maximum of 1 vector store attached to the thread. + maxItems: 1 + items: + type: object + properties: + file_ids: + type: array + description: | + A list of [file](/docs/api-reference/files) IDs to add to the vector store. There can be a maximum of 10000 files in a vector store. + maxItems: 10000 + items: + type: string + metadata: + type: object + description: | + Set of 16 key-value pairs that can be attached to a vector store. This can be useful for storing additional information about the vector store in a structured format. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long. + x-oaiTypeLabel: map + oneOf: + - required: [vector_store_ids] + - required: [vector_stores] + nullable: true + metadata: + description: *metadata_description + type: object + x-oaiTypeLabel: map + nullable: true - RunCompletionUsage: + ModifyThreadRequest: type: object - description: Usage statistics related to the run. This value will be `null` if the run is not in a terminal state (i.e. `in_progress`, `queued`, etc.). + additionalProperties: false properties: - completion_tokens: - type: integer - description: Number of completion tokens used over the course of the run. - prompt_tokens: - type: integer - description: Number of prompt tokens used over the course of the run. - total_tokens: - type: integer - description: Total number of tokens used (prompt + completion). - required: - - prompt_tokens - - completion_tokens - - total_tokens - nullable: true + tool_resources: + type: object + description: | + A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs. + properties: + code_interpreter: + type: object + properties: + file_ids: + type: array + description: | + A list of [file](/docs/api-reference/files) IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool. + default: [] + maxItems: 20 + items: + type: string + file_search: + type: object + properties: + vector_store_ids: + type: array + description: | + The [vector store](/docs/api-reference/vector-stores/object) attached to this thread. There can be a maximum of 1 vector store attached to the thread. + maxItems: 1 + items: + type: string + nullable: true + metadata: + description: *metadata_description + type: object + x-oaiTypeLabel: map + nullable: true - RunStepCompletionUsage: + DeleteThreadResponse: type: object - description: Usage statistics related to the run step. This value will be `null` while the run step's status is `in_progress`. properties: - completion_tokens: - type: integer - description: Number of completion tokens used over the course of the run step. - prompt_tokens: - type: integer - description: Number of prompt tokens used over the course of the run step. - total_tokens: - type: integer - description: Total number of tokens used (prompt + completion). + id: + type: string + deleted: + type: boolean + object: + type: string + enum: [thread.deleted] required: - - prompt_tokens - - completion_tokens - - total_tokens - nullable: true + - id + - object + - deleted + + ListThreadsResponse: + properties: + object: + type: string + example: "list" + data: + type: array + items: + $ref: "#/components/schemas/ThreadObject" + first_id: + type: string + example: "asst_abc123" + last_id: + type: string + example: "asst_abc456" + has_more: + type: boolean + example: false + required: + - object + - data + - first_id + - last_id + - has_more - AssistantObject: + MessageObject: type: object - title: Assistant - description: Represents an `assistant` that can call the model and use tools. + title: The message object + description: Represents a message within a [thread](/docs/api-reference/threads). properties: id: description: The identifier, which can be referenced in API endpoints. type: string object: - description: The object type, which is always `assistant`. + description: The object type, which is always `thread.message`. type: string - enum: [assistant] + enum: ["thread.message"] created_at: - description: The Unix timestamp (in seconds) for when the assistant was created. + description: The Unix timestamp (in seconds) for when the message was created. type: integer - name: - description: &assistant_name_param_description | - The name of the assistant. The maximum length is 256 characters. + thread_id: + description: The [thread](/docs/api-reference/threads) ID that this message belongs to. type: string - maxLength: 256 - nullable: true - description: - description: &assistant_description_param_description | - The description of the assistant. The maximum length is 512 characters. + status: + description: The status of the message, which can be either `in_progress`, `incomplete`, or `completed`. type: string - maxLength: 512 + enum: ["in_progress", "incomplete", "completed"] + incomplete_details: + description: On an incomplete message, details about why the message is incomplete. + type: object + properties: + reason: + type: string + description: The reason the message is incomplete. + enum: + [ + "content_filter", + "max_tokens", + "run_cancelled", + "run_expired", + "run_failed", + ] nullable: true - model: - description: *model_description - type: string - instructions: - description: &assistant_instructions_param_description | - The system instructions that the assistant uses. The maximum length is 32768 characters. - type: string - maxLength: 32768 + required: + - reason + completed_at: + description: The Unix timestamp (in seconds) for when the message was completed. + type: integer nullable: true - tools: - description: &assistant_tools_param_description | - A list of tool enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types `code_interpreter`, `retrieval`, or `function`. - default: [] + incomplete_at: + description: The Unix timestamp (in seconds) for when the message was marked as incomplete. + type: integer + nullable: true + role: + description: The entity that produced the message. One of `user` or `assistant`. + type: string + enum: ["user", "assistant"] + content: + description: The content of the message in array of text and/or images. type: array - maxItems: 128 items: oneOf: - - $ref: "#/components/schemas/AssistantToolsCode" - - $ref: "#/components/schemas/AssistantToolsRetrieval" - - $ref: "#/components/schemas/AssistantToolsFunction" + - $ref: "#/components/schemas/MessageContentImageFileObject" + - $ref: "#/components/schemas/MessageContentImageUrlObject" + - $ref: "#/components/schemas/MessageContentTextObject" x-oaiExpandable: true - file_ids: - description: &assistant_file_param_description | - A list of [file](/docs/api-reference/files) IDs attached to this assistant. There can be a maximum of 20 files attached to the assistant. Files are ordered by their creation date in ascending order. - default: [] + assistant_id: + description: If applicable, the ID of the [assistant](/docs/api-reference/assistants) that authored this message. + type: string + nullable: true + run_id: + description: The ID of the [run](/docs/api-reference/runs) associated with the creation of this message. Value is `null` when messages are created manually using the create message or create thread endpoints. + type: string + nullable: true + attachments: type: array - maxItems: 20 items: - type: string + type: object + properties: + file_id: + type: string + description: The ID of the file to attach to the message. + tools: + description: The tools to add this file to. + type: array + items: + oneOf: + - $ref: "#/components/schemas/AssistantToolsCode" + - $ref: "#/components/schemas/AssistantToolsFileSearch" + x-oaiExpandable: true + description: A list of files attached to the message, and the tools they were added to. + nullable: true metadata: - description: &metadata_description | - Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long. + description: *metadata_description type: object x-oaiTypeLabel: map nullable: true @@ -7339,116 +11012,162 @@ components: - id - object - created_at - - name - - description - - model - - instructions - - tools - - file_ids + - thread_id + - status + - incomplete_details + - completed_at + - incomplete_at + - role + - content + - assistant_id + - run_id + - attachments - metadata x-oaiMeta: - name: The assistant object + name: The message object beta: true - example: *create_assistants_example + example: | + { + "id": "msg_abc123", + "object": "thread.message", + "created_at": 1698983503, + "thread_id": "thread_abc123", + "role": "assistant", + "content": [ + { + "type": "text", + "text": { + "value": "Hi! How can I help you today?", + "annotations": [] + } + } + ], + "assistant_id": "asst_abc123", + "run_id": "run_abc123", + "attachments": [], + "metadata": {} + } - CreateAssistantRequest: + MessageDeltaObject: type: object - additionalProperties: false + title: Message delta object + description: | + Represents a message delta i.e. any changed fields on a message during streaming. properties: - model: - description: *model_description - anyOf: - - type: string - name: - description: *assistant_name_param_description + id: + description: The identifier of the message, which can be referenced in API endpoints. type: string - nullable: true - maxLength: 256 - description: - description: *assistant_description_param_description + object: + description: The object type, which is always `thread.message.delta`. type: string - nullable: true - maxLength: 512 - instructions: - description: *assistant_instructions_param_description + enum: ["thread.message.delta"] + delta: + description: The delta containing the fields that have changed on the Message. + type: object + properties: + role: + description: The entity that produced the message. One of `user` or `assistant`. + type: string + enum: ["user", "assistant"] + content: + description: The content of the message in array of text and/or images. + type: array + items: + oneOf: + - $ref: "#/components/schemas/MessageDeltaContentImageFileObject" + - $ref: "#/components/schemas/MessageDeltaContentTextObject" + - $ref: "#/components/schemas/MessageDeltaContentImageUrlObject" + x-oaiExpandable: true + required: + - id + - object + - delta + x-oaiMeta: + name: The message delta object + beta: true + example: | + { + "id": "msg_123", + "object": "thread.message.delta", + "delta": { + "content": [ + { + "index": 0, + "type": "text", + "text": { "value": "Hello", "annotations": [] } + } + ] + } + } + + CreateMessageRequest: + type: object + additionalProperties: false + required: + - role + - content + properties: + role: type: string - nullable: true - maxLength: 32768 - tools: - description: *assistant_tools_param_description - default: [] - type: array - maxItems: 128 - items: - oneOf: - - $ref: "#/components/schemas/AssistantToolsCode" - - $ref: "#/components/schemas/AssistantToolsRetrieval" - - $ref: "#/components/schemas/AssistantToolsFunction" - x-oaiExpandable: true - file_ids: - description: *assistant_file_param_description - default: [] - maxItems: 20 + enum: ["user", "assistant"] + description: | + The role of the entity that is creating the message. Allowed values include: + - `user`: Indicates the message is sent by an actual user and should be used in most cases to represent user-generated messages. + - `assistant`: Indicates the message is generated by the assistant. Use this value to insert messages from the assistant into the conversation. + content: + oneOf: + - type: string + description: The text contents of the message. + title: Text content + - type: array + description: An array of content parts with a defined type, each can be of type `text` or images can be passed with `image_url` or `image_file`. Image types are only supported on [Vision-compatible models](/docs/models/overview). + title: Array of content parts + items: + oneOf: + - $ref: "#/components/schemas/MessageContentImageFileObject" + - $ref: "#/components/schemas/MessageContentImageUrlObject" + - $ref: "#/components/schemas/MessageRequestContentTextObject" + x-oaiExpandable: true + minItems: 1 + x-oaiExpandable: true + attachments: type: array items: - type: string + type: object + properties: + file_id: + type: string + description: The ID of the file to attach to the message. + tools: + description: The tools to add this file to. + type: array + items: + oneOf: + - $ref: "#/components/schemas/AssistantToolsCode" + - $ref: "#/components/schemas/AssistantToolsFileSearch" + x-oaiExpandable: true + description: A list of files attached to the message, and the tools they should be added to. + required: + - file_id + - tools + nullable: true metadata: description: *metadata_description type: object x-oaiTypeLabel: map nullable: true - required: - - model - ModifyAssistantRequest: + ModifyMessageRequest: type: object additionalProperties: false properties: - model: - description: *model_description - anyOf: - - type: string - name: - description: *assistant_name_param_description - type: string - nullable: true - maxLength: 256 - description: - description: *assistant_description_param_description - type: string - nullable: true - maxLength: 512 - instructions: - description: *assistant_instructions_param_description - type: string - nullable: true - maxLength: 32768 - tools: - description: *assistant_tools_param_description - default: [] - type: array - maxItems: 128 - items: - oneOf: - - $ref: "#/components/schemas/AssistantToolsCode" - - $ref: "#/components/schemas/AssistantToolsRetrieval" - - $ref: "#/components/schemas/AssistantToolsFunction" - x-oaiExpandable: true - file_ids: - description: | - A list of [File](/docs/api-reference/files) IDs attached to this assistant. There can be a maximum of 20 files attached to the assistant. Files are ordered by their creation date in ascending order. If a file was previously attached to the list but does not show up in the list, it will be deleted from the assistant. - default: [] - type: array - maxItems: 20 - items: - type: string metadata: description: *metadata_description type: object x-oaiTypeLabel: map nullable: true - DeleteAssistantResponse: + DeleteMessageResponse: type: object properties: id: @@ -7457,14 +11176,13 @@ components: type: boolean object: type: string - enum: [assistant.deleted] + enum: [thread.message.deleted] required: - id - object - deleted - ListAssistantsResponse: - type: object + ListMessagesResponse: properties: object: type: string @@ -7472,13 +11190,13 @@ components: data: type: array items: - $ref: "#/components/schemas/AssistantObject" + $ref: "#/components/schemas/MessageObject" first_id: type: string - example: "asst_abc123" + example: "msg_abc123" last_id: type: string - example: "asst_abc456" + example: "msg_abc123" has_more: type: boolean example: false @@ -7488,451 +11206,474 @@ components: - first_id - last_id - has_more - x-oaiMeta: - name: List assistants response object - group: chat - example: *list_assistants_example - AssistantToolsCode: + MessageContentImageFileObject: + title: Image file type: object - title: Code interpreter tool + description: References an image [File](/docs/api-reference/files) in the content of a message. properties: type: + description: Always `image_file`. type: string - description: "The type of tool being defined: `code_interpreter`" - enum: ["code_interpreter"] + enum: ["image_file"] + image_file: + type: object + properties: + file_id: + description: The [File](/docs/api-reference/files) ID of the image in the message content. Set `purpose="vision"` when uploading the File if you need to later display the file content. + type: string + detail: + type: string + description: Specifies the detail level of the image if specified by the user. `low` uses fewer tokens, you can opt in to high resolution using `high`. + enum: ["auto", "low", "high"] + default: "auto" + required: + - file_id required: - type + - image_file - AssistantToolsRetrieval: + MessageDeltaContentImageFileObject: + title: Image file type: object - title: Retrieval tool + description: References an image [File](/docs/api-reference/files) in the content of a message. properties: + index: + type: integer + description: The index of the content part in the message. type: + description: Always `image_file`. type: string - description: "The type of tool being defined: `retrieval`" - enum: ["retrieval"] + enum: ["image_file"] + image_file: + type: object + properties: + file_id: + description: The [File](/docs/api-reference/files) ID of the image in the message content. Set `purpose="vision"` when uploading the File if you need to later display the file content. + type: string + detail: + type: string + description: Specifies the detail level of the image if specified by the user. `low` uses fewer tokens, you can opt in to high resolution using `high`. + enum: ["auto", "low", "high"] + default: "auto" required: + - index - type - AssistantToolsFunction: + MessageContentImageUrlObject: + title: Image URL type: object - title: Function tool + description: References an image URL in the content of a message. properties: type: type: string - description: "The type of tool being defined: `function`" - enum: ["function"] - function: - $ref: "#/components/schemas/FunctionObject" + enum: ["image_url"] + description: The type of the content part. + image_url: + type: object + properties: + url: + type: string + description: "The external URL of the image, must be a supported image types: jpeg, jpg, png, gif, webp." + format: uri + detail: + type: string + description: Specifies the detail level of the image. `low` uses fewer tokens, you can opt in to high resolution using `high`. Default value is `auto` + enum: ["auto", "low", "high"] + default: "auto" + required: + - url required: - type - - function + - image_url - RunObject: + MessageDeltaContentImageUrlObject: + title: Image URL type: object - title: A run on a thread - description: Represents an execution run on a [thread](/docs/api-reference/threads). + description: References an image URL in the content of a message. properties: - id: - description: The identifier, which can be referenced in API endpoints. - type: string - object: - description: The object type, which is always `thread.run`. - type: string - enum: ["thread.run"] - created_at: - description: The Unix timestamp (in seconds) for when the run was created. + index: type: integer - thread_id: - description: The ID of the [thread](/docs/api-reference/threads) that was executed on as a part of this run. - type: string - assistant_id: - description: The ID of the [assistant](/docs/api-reference/assistants) used for execution of this run. - type: string - status: - description: The status of the run, which can be either `queued`, `in_progress`, `requires_action`, `cancelling`, `cancelled`, `failed`, `completed`, or `expired`. + description: The index of the content part in the message. + type: + description: Always `image_url`. type: string - enum: - [ - "queued", - "in_progress", - "requires_action", - "cancelling", - "cancelled", - "failed", - "completed", - "expired", - ] - required_action: + enum: ["image_url"] + image_url: type: object - description: Details on the action required to continue the run. Will be `null` if no action is required. - nullable: true properties: - type: - description: For now, this is always `submit_tool_outputs`. + url: + description: "The URL of the image, must be a supported image types: jpeg, jpg, png, gif, webp." type: string - enum: ["submit_tool_outputs"] - submit_tool_outputs: - type: object - description: Details on the tool outputs needed for this run to continue. - properties: - tool_calls: - type: array - description: A list of the relevant tool calls. - items: - $ref: "#/components/schemas/RunToolCallObject" - required: - - tool_calls - required: - - type - - submit_tool_outputs - last_error: + detail: + type: string + description: Specifies the detail level of the image. `low` uses fewer tokens, you can opt in to high resolution using `high`. + enum: ["auto", "low", "high"] + default: "auto" + required: + - index + - type + + MessageContentTextObject: + title: Text + type: object + description: The text content that is part of a message. + properties: + type: + description: Always `text`. + type: string + enum: ["text"] + text: type: object - description: The last error associated with this run. Will be `null` if there are no errors. - nullable: true properties: - code: - type: string - description: One of `server_error` or `rate_limit_exceeded`. - enum: ["server_error", "rate_limit_exceeded"] - message: + value: + description: The data that makes up the text. type: string - description: A human-readable description of the error. + annotations: + type: array + items: + oneOf: + - $ref: "#/components/schemas/MessageContentTextAnnotationsFileCitationObject" + - $ref: "#/components/schemas/MessageContentTextAnnotationsFilePathObject" + x-oaiExpandable: true required: - - code - - message - expires_at: - description: The Unix timestamp (in seconds) for when the run will expire. - type: integer - started_at: - description: The Unix timestamp (in seconds) for when the run was started. - type: integer - nullable: true - cancelled_at: - description: The Unix timestamp (in seconds) for when the run was cancelled. - type: integer - nullable: true - failed_at: - description: The Unix timestamp (in seconds) for when the run failed. - type: integer - nullable: true - completed_at: - description: The Unix timestamp (in seconds) for when the run was completed. - type: integer - nullable: true - model: - description: The model that the [assistant](/docs/api-reference/assistants) used for this run. + - value + - annotations + required: + - type + - text + + MessageRequestContentTextObject: + title: Text + type: object + description: The text content that is part of a message. + properties: + type: + description: Always `text`. type: string - instructions: - description: The instructions that the [assistant](/docs/api-reference/assistants) used for this run. + enum: ["text"] + text: type: string - tools: - description: The list of tools that the [assistant](/docs/api-reference/assistants) used for this run. - default: [] - type: array - maxItems: 20 - items: - oneOf: - - $ref: "#/components/schemas/AssistantToolsCode" - - $ref: "#/components/schemas/AssistantToolsRetrieval" - - $ref: "#/components/schemas/AssistantToolsFunction" - x-oaiExpandable: true - file_ids: - description: The list of [File](/docs/api-reference/files) IDs the [assistant](/docs/api-reference/assistants) used for this run. - default: [] - type: array - items: - type: string - metadata: - description: *metadata_description - type: object - x-oaiTypeLabel: map - nullable: true - usage: - $ref: "#/components/schemas/RunCompletionUsage" + description: Text content to be sent to the model required: - - id - - object - - created_at - - thread_id - - assistant_id - - status - - required_action - - last_error - - expires_at - - started_at - - cancelled_at - - failed_at - - completed_at - - model - - instructions - - tools - - file_ids - - metadata - - usage - x-oaiMeta: - name: The run object - beta: true - example: | - { - "id": "run_abc123", - "object": "thread.run", - "created_at": 1698107661, - "assistant_id": "asst_abc123", - "thread_id": "thread_abc123", - "status": "completed", - "started_at": 1699073476, - "expires_at": null, - "cancelled_at": null, - "failed_at": null, - "completed_at": 1699073498, - "last_error": null, - "model": "gpt-4", - "instructions": null, - "tools": [{"type": "retrieval"}, {"type": "code_interpreter"}], - "file_ids": [], - "metadata": {}, - "usage": { - "prompt_tokens": 123, - "completion_tokens": 456, - "total_tokens": 579 - } - } - CreateRunRequest: + - type + - text + + MessageContentTextAnnotationsFileCitationObject: + title: File citation type: object - additionalProperties: false + description: A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the "file_search" tool to search files. properties: - assistant_id: - description: The ID of the [assistant](/docs/api-reference/assistants) to use to execute this run. - type: string - model: - description: The ID of the [Model](/docs/api-reference/models) to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used. - type: string - nullable: true - instructions: - description: Overrides the [instructions](/docs/api-reference/assistants/createAssistant) of the assistant. This is useful for modifying the behavior on a per-run basis. + type: + description: Always `file_citation`. type: string - nullable: true - additional_instructions: - description: Appends additional instructions at the end of the instructions for the run. This is useful for modifying the behavior on a per-run basis without overriding other instructions. + enum: ["file_citation"] + text: + description: The text in the message content that needs to be replaced. type: string - nullable: true - tools: - description: Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis. - nullable: true - type: array - maxItems: 20 - items: - oneOf: - - $ref: "#/components/schemas/AssistantToolsCode" - - $ref: "#/components/schemas/AssistantToolsRetrieval" - - $ref: "#/components/schemas/AssistantToolsFunction" - x-oaiExpandable: true - metadata: - description: *metadata_description + file_citation: type: object - x-oaiTypeLabel: map - nullable: true + properties: + file_id: + description: The ID of the specific File the citation is from. + type: string + quote: + description: The specific quote in the file. + type: string + required: + - file_id + - quote + start_index: + type: integer + minimum: 0 + end_index: + type: integer + minimum: 0 required: - - thread_id - - assistant_id - ListRunsResponse: + - type + - text + - file_citation + - start_index + - end_index + + MessageContentTextAnnotationsFilePathObject: + title: File path type: object + description: A URL for the file that's generated when the assistant used the `code_interpreter` tool to generate a file. properties: - object: - type: string - example: "list" - data: - type: array - items: - $ref: "#/components/schemas/RunObject" - first_id: + type: + description: Always `file_path`. type: string - example: "run_abc123" - last_id: + enum: ["file_path"] + text: + description: The text in the message content that needs to be replaced. type: string - example: "run_abc456" - has_more: - type: boolean - example: false + file_path: + type: object + properties: + file_id: + description: The ID of the file that was generated. + type: string + required: + - file_id + start_index: + type: integer + minimum: 0 + end_index: + type: integer + minimum: 0 required: - - object - - data - - first_id - - last_id - - has_more - ModifyRunRequest: + - type + - text + - file_path + - start_index + - end_index + + MessageDeltaContentTextObject: + title: Text type: object - additionalProperties: false + description: The text content that is part of a message. properties: - metadata: - description: *metadata_description + index: + type: integer + description: The index of the content part in the message. + type: + description: Always `text`. + type: string + enum: ["text"] + text: type: object - x-oaiTypeLabel: map - nullable: true - SubmitToolOutputsRunRequest: + properties: + value: + description: The data that makes up the text. + type: string + annotations: + type: array + items: + oneOf: + - $ref: "#/components/schemas/MessageDeltaContentTextAnnotationsFileCitationObject" + - $ref: "#/components/schemas/MessageDeltaContentTextAnnotationsFilePathObject" + x-oaiExpandable: true + required: + - index + - type + + MessageDeltaContentTextAnnotationsFileCitationObject: + title: File citation type: object - additionalProperties: false + description: A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the "file_search" tool to search files. properties: - tool_outputs: - description: A list of tools for which the outputs are being submitted. - type: array - items: - type: object - properties: - tool_call_id: - type: string - description: The ID of the tool call in the `required_action` object within the run object the output is being submitted for. - output: - type: string - description: The output of the tool call to be submitted to continue the run. + index: + type: integer + description: The index of the annotation in the text content part. + type: + description: Always `file_citation`. + type: string + enum: ["file_citation"] + text: + description: The text in the message content that needs to be replaced. + type: string + file_citation: + type: object + properties: + file_id: + description: The ID of the specific File the citation is from. + type: string + quote: + description: The specific quote in the file. + type: string + start_index: + type: integer + minimum: 0 + end_index: + type: integer + minimum: 0 required: - - tool_outputs + - index + - type - RunToolCallObject: + MessageDeltaContentTextAnnotationsFilePathObject: + title: File path type: object - description: Tool call objects + description: A URL for the file that's generated when the assistant used the `code_interpreter` tool to generate a file. properties: - id: - type: string - description: The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the [Submit tool outputs to run](/docs/api-reference/runs/submitToolOutputs) endpoint. + index: + type: integer + description: The index of the annotation in the text content part. type: + description: Always `file_path`. type: string - description: The type of tool call the output is required for. For now, this is always `function`. - enum: ["function"] - function: + enum: ["file_path"] + text: + description: The text in the message content that needs to be replaced. + type: string + file_path: type: object - description: The function definition. properties: - name: - type: string - description: The name of the function. - arguments: + file_id: + description: The ID of the file that was generated. type: string - description: The arguments that the model expects you to pass to the function. - required: - - name - - arguments + start_index: + type: integer + minimum: 0 + end_index: + type: integer + minimum: 0 required: - - id + - index - type - - function - CreateThreadAndRunRequest: + RunStepObject: type: object - additionalProperties: false + title: Run steps + description: | + Represents a step in execution of a run. properties: + id: + description: The identifier of the run step, which can be referenced in API endpoints. + type: string + object: + description: The object type, which is always `thread.run.step`. + type: string + enum: ["thread.run.step"] + created_at: + description: The Unix timestamp (in seconds) for when the run step was created. + type: integer assistant_id: - description: The ID of the [assistant](/docs/api-reference/assistants) to use to execute this run. + description: The ID of the [assistant](/docs/api-reference/assistants) associated with the run step. type: string - thread: - $ref: "#/components/schemas/CreateThreadRequest" - description: If no thread is provided, an empty thread will be created. - model: - description: The ID of the [Model](/docs/api-reference/models) to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used. + thread_id: + description: The ID of the [thread](/docs/api-reference/threads) that was run. + type: string + run_id: + description: The ID of the [run](/docs/api-reference/runs) that this run step is a part of. + type: string + type: + description: The type of run step, which can be either `message_creation` or `tool_calls`. + type: string + enum: ["message_creation", "tool_calls"] + status: + description: The status of the run step, which can be either `in_progress`, `cancelled`, `failed`, `completed`, or `expired`. type: string + enum: ["in_progress", "cancelled", "failed", "completed", "expired"] + step_details: + type: object + description: The details of the run step. + oneOf: + - $ref: "#/components/schemas/RunStepDetailsMessageCreationObject" + - $ref: "#/components/schemas/RunStepDetailsToolCallsObject" + x-oaiExpandable: true + last_error: + type: object + description: The last error associated with this run step. Will be `null` if there are no errors. nullable: true - instructions: - description: Override the default system message of the assistant. This is useful for modifying the behavior on a per-run basis. - type: string + properties: + code: + type: string + description: One of `server_error` or `rate_limit_exceeded`. + enum: ["server_error", "rate_limit_exceeded"] + message: + type: string + description: A human-readable description of the error. + required: + - code + - message + expired_at: + description: The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired. + type: integer nullable: true - tools: - description: Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis. + cancelled_at: + description: The Unix timestamp (in seconds) for when the run step was cancelled. + type: integer nullable: true - type: array - maxItems: 20 - items: - oneOf: - - $ref: "#/components/schemas/AssistantToolsCode" - - $ref: "#/components/schemas/AssistantToolsRetrieval" - - $ref: "#/components/schemas/AssistantToolsFunction" - metadata: - description: *metadata_description - type: object - x-oaiTypeLabel: map + failed_at: + description: The Unix timestamp (in seconds) for when the run step failed. + type: integer nullable: true - required: - - thread_id - - assistant_id - - ThreadObject: - type: object - title: Thread - description: Represents a thread that contains [messages](/docs/api-reference/messages). - properties: - id: - description: The identifier, which can be referenced in API endpoints. - type: string - object: - description: The object type, which is always `thread`. - type: string - enum: ["thread"] - created_at: - description: The Unix timestamp (in seconds) for when the thread was created. + completed_at: + description: The Unix timestamp (in seconds) for when the run step completed. type: integer + nullable: true metadata: description: *metadata_description type: object x-oaiTypeLabel: map nullable: true + usage: + $ref: "#/components/schemas/RunStepCompletionUsage" required: - id - object - created_at + - assistant_id + - thread_id + - run_id + - type + - status + - step_details + - last_error + - expired_at + - cancelled_at + - failed_at + - completed_at - metadata + - usage x-oaiMeta: - name: The thread object + name: The run step object beta: true - example: | - { - "id": "thread_abc123", - "object": "thread", - "created_at": 1698107661, - "metadata": {} - } - - CreateThreadRequest: - type: object - additionalProperties: false - properties: - messages: - description: A list of [messages](/docs/api-reference/messages) to start the thread with. - type: array - items: - $ref: "#/components/schemas/CreateMessageRequest" - metadata: - description: *metadata_description - type: object - x-oaiTypeLabel: map - nullable: true - - ModifyThreadRequest: - type: object - additionalProperties: false - properties: - metadata: - description: *metadata_description - type: object - x-oaiTypeLabel: map - nullable: true + example: *run_step_object_example - DeleteThreadResponse: + RunStepDeltaObject: type: object + title: Run step delta object + description: | + Represents a run step delta i.e. any changed fields on a run step during streaming. properties: id: + description: The identifier of the run step, which can be referenced in API endpoints. type: string - deleted: - type: boolean object: + description: The object type, which is always `thread.run.step.delta`. type: string - enum: [thread.deleted] + enum: ["thread.run.step.delta"] + delta: + description: The delta containing the fields that have changed on the run step. + type: object + properties: + step_details: + type: object + description: The details of the run step. + oneOf: + - $ref: "#/components/schemas/RunStepDeltaStepDetailsMessageCreationObject" + - $ref: "#/components/schemas/RunStepDeltaStepDetailsToolCallsObject" + x-oaiExpandable: true required: - id - object - - deleted + - delta + x-oaiMeta: + name: The run step delta object + beta: true + example: | + { + "id": "step_123", + "object": "thread.run.step.delta", + "delta": { + "step_details": { + "type": "tool_calls", + "tool_calls": [ + { + "index": 0, + "id": "call_123", + "type": "code_interpreter", + "code_interpreter": { "input": "", "outputs": [] } + } + ] + } + } + } - ListThreadsResponse: + ListRunStepsResponse: properties: object: type: string @@ -7940,13 +11681,13 @@ components: data: type: array items: - $ref: "#/components/schemas/ThreadObject" + $ref: "#/components/schemas/RunStepObject" first_id: type: string - example: "asst_abc123" + example: "step_abc123" last_id: type: string - example: "asst_abc456" + example: "step_abc456" has_more: type: boolean example: false @@ -7957,361 +11698,421 @@ components: - last_id - has_more - MessageObject: + RunStepDetailsMessageCreationObject: + title: Message creation type: object - title: The message object - description: Represents a message within a [thread](/docs/api-reference/threads). + description: Details of the message creation by the run step. properties: - id: - description: The identifier, which can be referenced in API endpoints. - type: string - object: - description: The object type, which is always `thread.message`. + type: + description: Always `message_creation`. type: string - enum: ["thread.message"] - created_at: - description: The Unix timestamp (in seconds) for when the message was created. - type: integer - thread_id: - description: The [thread](/docs/api-reference/threads) ID that this message belongs to. + enum: ["message_creation"] + message_creation: + type: object + properties: + message_id: + type: string + description: The ID of the message that was created by this run step. + required: + - message_id + required: + - type + - message_creation + + RunStepDeltaStepDetailsMessageCreationObject: + title: Message creation + type: object + description: Details of the message creation by the run step. + properties: + type: + description: Always `message_creation`. type: string - role: - description: The entity that produced the message. One of `user` or `assistant`. + enum: ["message_creation"] + message_creation: + type: object + properties: + message_id: + type: string + description: The ID of the message that was created by this run step. + required: + - type + + RunStepDetailsToolCallsObject: + title: Tool calls + type: object + description: Details of the tool call. + properties: + type: + description: Always `tool_calls`. type: string - enum: ["user", "assistant"] - content: - description: The content of the message in array of text and/or images. + enum: ["tool_calls"] + tool_calls: type: array + description: | + An array of tool calls the run step was involved in. These can be associated with one of three types of tools: `code_interpreter`, `file_search`, or `function`. items: oneOf: - - $ref: "#/components/schemas/MessageContentImageFileObject" - - $ref: "#/components/schemas/MessageContentTextObject" - x-oaiExpandable: true - assistant_id: - description: If applicable, the ID of the [assistant](/docs/api-reference/assistants) that authored this message. - type: string - nullable: true - run_id: - description: If applicable, the ID of the [run](/docs/api-reference/runs) associated with the authoring of this message. - type: string - nullable: true - file_ids: - description: A list of [file](/docs/api-reference/files) IDs that the assistant should use. Useful for tools like retrieval and code_interpreter that can access files. A maximum of 10 files can be attached to a message. - default: [] - maxItems: 10 - type: array - items: - type: string - metadata: - description: *metadata_description - type: object - x-oaiTypeLabel: map - nullable: true - required: - - id - - object - - created_at - - thread_id - - role - - content - - assistant_id - - run_id - - file_ids - - metadata - x-oaiMeta: - name: The message object - beta: true - example: | - { - "id": "msg_abc123", - "object": "thread.message", - "created_at": 1698983503, - "thread_id": "thread_abc123", - "role": "assistant", - "content": [ - { - "type": "text", - "text": { - "value": "Hi! How can I help you today?", - "annotations": [] - } - } - ], - "file_ids": [], - "assistant_id": "asst_abc123", - "run_id": "run_abc123", - "metadata": {} - } + - $ref: "#/components/schemas/RunStepDetailsToolCallsCodeObject" + - $ref: "#/components/schemas/RunStepDetailsToolCallsFileSearchObject" + - $ref: "#/components/schemas/RunStepDetailsToolCallsFunctionObject" + x-oaiExpandable: true + required: + - type + - tool_calls - CreateMessageRequest: + RunStepDeltaStepDetailsToolCallsObject: + title: Tool calls type: object - additionalProperties: false - required: - - role - - content + description: Details of the tool call. properties: - role: - type: string - enum: ["user"] - description: The role of the entity that is creating the message. Currently only `user` is supported. - content: + type: + description: Always `tool_calls`. type: string - minLength: 1 - maxLength: 32768 - description: The content of the message. - file_ids: - description: A list of [File](/docs/api-reference/files) IDs that the message should use. There can be a maximum of 10 files attached to a message. Useful for tools like `retrieval` and `code_interpreter` that can access and use files. - default: [] + enum: ["tool_calls"] + tool_calls: type: array - minItems: 1 - maxItems: 10 + description: | + An array of tool calls the run step was involved in. These can be associated with one of three types of tools: `code_interpreter`, `file_search`, or `function`. items: - type: string - metadata: - description: *metadata_description - type: object - x-oaiTypeLabel: map - nullable: true + oneOf: + - $ref: "#/components/schemas/RunStepDeltaStepDetailsToolCallsCodeObject" + - $ref: "#/components/schemas/RunStepDeltaStepDetailsToolCallsFileSearchObject" + - $ref: "#/components/schemas/RunStepDeltaStepDetailsToolCallsFunctionObject" + x-oaiExpandable: true + required: + - type - ModifyMessageRequest: + RunStepDetailsToolCallsCodeObject: + title: Code Interpreter tool call type: object - additionalProperties: false + description: Details of the Code Interpreter tool call the run step was involved in. properties: - metadata: - description: *metadata_description + id: + type: string + description: The ID of the tool call. + type: + type: string + description: The type of tool call. This is always going to be `code_interpreter` for this type of tool call. + enum: ["code_interpreter"] + code_interpreter: type: object - x-oaiTypeLabel: map - nullable: true + description: The Code Interpreter tool call definition. + required: + - input + - outputs + properties: + input: + type: string + description: The input to the Code Interpreter tool call. + outputs: + type: array + description: The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (`logs`) or images (`image`). Each of these are represented by a different object type. + items: + type: object + oneOf: + - $ref: "#/components/schemas/RunStepDetailsToolCallsCodeOutputLogsObject" + - $ref: "#/components/schemas/RunStepDetailsToolCallsCodeOutputImageObject" + x-oaiExpandable: true + required: + - id + - type + - code_interpreter - DeleteMessageResponse: + RunStepDeltaStepDetailsToolCallsCodeObject: + title: Code interpreter tool call type: object + description: Details of the Code Interpreter tool call the run step was involved in. properties: + index: + type: integer + description: The index of the tool call in the tool calls array. id: type: string - deleted: - type: boolean - object: + description: The ID of the tool call. + type: type: string - enum: [thread.message.deleted] + description: The type of tool call. This is always going to be `code_interpreter` for this type of tool call. + enum: ["code_interpreter"] + code_interpreter: + type: object + description: The Code Interpreter tool call definition. + properties: + input: + type: string + description: The input to the Code Interpreter tool call. + outputs: + type: array + description: The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (`logs`) or images (`image`). Each of these are represented by a different object type. + items: + type: object + oneOf: + - $ref: "#/components/schemas/RunStepDeltaStepDetailsToolCallsCodeOutputLogsObject" + - $ref: "#/components/schemas/RunStepDeltaStepDetailsToolCallsCodeOutputImageObject" + x-oaiExpandable: true required: - - id - - object - - deleted + - index + - type - ListMessagesResponse: + RunStepDetailsToolCallsCodeOutputLogsObject: + title: Code Interpreter log output + type: object + description: Text output from the Code Interpreter tool call as part of a run step. properties: - object: + type: + description: Always `logs`. type: string - example: "list" - data: - type: array - items: - $ref: "#/components/schemas/MessageObject" - first_id: + enum: ["logs"] + logs: type: string - example: "msg_abc123" - last_id: + description: The text output from the Code Interpreter tool call. + required: + - type + - logs + + RunStepDeltaStepDetailsToolCallsCodeOutputLogsObject: + title: Code interpreter log output + type: object + description: Text output from the Code Interpreter tool call as part of a run step. + properties: + index: + type: integer + description: The index of the output in the outputs array. + type: + description: Always `logs`. type: string - example: "msg_abc123" - has_more: - type: boolean - example: false + enum: ["logs"] + logs: + type: string + description: The text output from the Code Interpreter tool call. required: - - object - - data - - first_id - - last_id - - has_more + - index + - type - MessageContentImageFileObject: - title: Image file + RunStepDetailsToolCallsCodeOutputImageObject: + title: Code Interpreter image output type: object - description: References an image [File](/docs/api-reference/files) in the content of a message. properties: type: - description: Always `image_file`. + description: Always `image`. type: string - enum: ["image_file"] - image_file: + enum: ["image"] + image: type: object properties: file_id: - description: The [File](/docs/api-reference/files) ID of the image in the message content. + description: The [file](/docs/api-reference/files) ID of the image. type: string required: - file_id required: - type - - image_file + - image - MessageContentTextObject: - title: Text + RunStepDeltaStepDetailsToolCallsCodeOutputImageObject: + title: Code interpreter image output type: object - description: The text content that is part of a message. properties: + index: + type: integer + description: The index of the output in the outputs array. type: - description: Always `text`. + description: Always `image`. type: string - enum: ["text"] - text: + enum: ["image"] + image: type: object properties: - value: - description: The data that makes up the text. + file_id: + description: The [file](/docs/api-reference/files) ID of the image. type: string - annotations: - type: array - items: - oneOf: - - $ref: "#/components/schemas/MessageContentTextAnnotationsFileCitationObject" - - $ref: "#/components/schemas/MessageContentTextAnnotationsFilePathObject" - x-oaiExpandable: true - required: - - value - - annotations required: + - index - type - - text - MessageContentTextAnnotationsFileCitationObject: - title: File citation + RunStepDetailsToolCallsFileSearchObject: + title: File search tool call + type: object + properties: + id: + type: string + description: The ID of the tool call object. + type: + type: string + description: The type of tool call. This is always going to be `file_search` for this type of tool call. + enum: ["file_search"] + file_search: + type: object + description: For now, this is always going to be an empty object. + x-oaiTypeLabel: map + required: + - id + - type + - file_search + + RunStepDeltaStepDetailsToolCallsFileSearchObject: + title: File search tool call + type: object + properties: + index: + type: integer + description: The index of the tool call in the tool calls array. + id: + type: string + description: The ID of the tool call object. + type: + type: string + description: The type of tool call. This is always going to be `file_search` for this type of tool call. + enum: ["file_search"] + file_search: + type: object + description: For now, this is always going to be an empty object. + x-oaiTypeLabel: map + required: + - index + - type + - file_search + + RunStepDetailsToolCallsFunctionObject: + type: object + title: Function tool call + properties: + id: + type: string + description: The ID of the tool call object. + type: + type: string + description: The type of tool call. This is always going to be `function` for this type of tool call. + enum: ["function"] + function: + type: object + description: The definition of the function that was called. + properties: + name: + type: string + description: The name of the function. + arguments: + type: string + description: The arguments passed to the function. + output: + type: string + description: The output of the function. This will be `null` if the outputs have not been [submitted](/docs/api-reference/runs/submitToolOutputs) yet. + nullable: true + required: + - name + - arguments + - output + required: + - id + - type + - function + + RunStepDeltaStepDetailsToolCallsFunctionObject: type: object - description: A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the "retrieval" tool to search files. + title: Function tool call properties: - type: - description: Always `file_citation`. + index: + type: integer + description: The index of the tool call in the tool calls array. + id: type: string - enum: ["file_citation"] - text: - description: The text in the message content that needs to be replaced. + description: The ID of the tool call object. + type: type: string - file_citation: + description: The type of tool call. This is always going to be `function` for this type of tool call. + enum: ["function"] + function: type: object + description: The definition of the function that was called. properties: - file_id: - description: The ID of the specific File the citation is from. + name: type: string - quote: - description: The specific quote in the file. + description: The name of the function. + arguments: type: string - required: - - file_id - - quote - start_index: - type: integer - minimum: 0 - end_index: - type: integer - minimum: 0 + description: The arguments passed to the function. + output: + type: string + description: The output of the function. This will be `null` if the outputs have not been [submitted](/docs/api-reference/runs/submitToolOutputs) yet. + nullable: true required: + - index - type - - text - - file_citation - - start_index - - end_index - MessageContentTextAnnotationsFilePathObject: - title: File path + VectorStoreExpirationAfter: type: object - description: A URL for the file that's generated when the assistant used the `code_interpreter` tool to generate a file. + title: Vector store expiration policy + description: The expiration policy for a vector store. properties: - type: - description: Always `file_path`. + anchor: + description: "Anchor timestamp after which the expiration policy applies. Supported anchors: `last_active_at`." type: string - enum: ["file_path"] - text: - description: The text in the message content that needs to be replaced. - type: string - file_path: - type: object - properties: - file_id: - description: The ID of the file that was generated. - type: string - required: - - file_id - start_index: - type: integer - minimum: 0 - end_index: + enum: ["last_active_at"] + days: + description: The number of days after the anchor time that the vector store will expire. type: integer - minimum: 0 + minimum: 1 + maximum: 365 required: - - type - - text - - file_path - - start_index - - end_index + - anchor + - days - RunStepObject: + VectorStoreObject: type: object - title: Run steps - description: | - Represents a step in execution of a run. + title: Vector store + description: A vector store is a collection of processed files can be used by the `file_search` tool. properties: id: - description: The identifier of the run step, which can be referenced in API endpoints. + description: The identifier, which can be referenced in API endpoints. type: string object: - description: The object type, which is always `thread.run.step`. + description: The object type, which is always `vector_store`. type: string - enum: ["thread.run.step"] + enum: ["vector_store"] created_at: - description: The Unix timestamp (in seconds) for when the run step was created. + description: The Unix timestamp (in seconds) for when the vector store was created. type: integer - assistant_id: - description: The ID of the [assistant](/docs/api-reference/assistants) associated with the run step. - type: string - thread_id: - description: The ID of the [thread](/docs/api-reference/threads) that was run. - type: string - run_id: - description: The ID of the [run](/docs/api-reference/runs) that this run step is a part of. - type: string - type: - description: The type of run step, which can be either `message_creation` or `tool_calls`. - type: string - enum: ["message_creation", "tool_calls"] - status: - description: The status of the run step, which can be either `in_progress`, `cancelled`, `failed`, `completed`, or `expired`. + name: + description: The name of the vector store. type: string - enum: ["in_progress", "cancelled", "failed", "completed", "expired"] - step_details: - type: object - description: The details of the run step. - oneOf: - - $ref: "#/components/schemas/RunStepDetailsMessageCreationObject" - - $ref: "#/components/schemas/RunStepDetailsToolCallsObject" - x-oaiExpandable: true - last_error: + usage_bytes: + description: The total number of bytes used by the files in the vector store. + type: integer + file_counts: type: object - description: The last error associated with this run step. Will be `null` if there are no errors. - nullable: true properties: - code: - type: string - description: One of `server_error` or `rate_limit_exceeded`. - enum: ["server_error", "rate_limit_exceeded"] - message: - type: string - description: A human-readable description of the error. + in_progress: + description: The number of files that are currently being processed. + type: integer + completed: + description: The number of files that have been successfully processed. + type: integer + failed: + description: The number of files that have failed to process. + type: integer + cancelled: + description: The number of files that were cancelled. + type: integer + total: + description: The total number of files. + type: integer required: - - code - - message - expired_at: - description: The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired. - type: integer - nullable: true - cancelled_at: - description: The Unix timestamp (in seconds) for when the run step was cancelled. - type: integer - nullable: true - failed_at: - description: The Unix timestamp (in seconds) for when the run step failed. + - in_progress + - completed + - failed + - cancelled + - total + status: + description: The status of the vector store, which can be either `expired`, `in_progress`, or `completed`. A status of `completed` indicates that the vector store is ready for use. + type: string + enum: ["expired", "in_progress", "completed"] + expires_after: + $ref: "#/components/schemas/VectorStoreExpirationAfter" + expires_at: + description: The Unix timestamp (in seconds) for when the vector store will expire. type: integer nullable: true - completed_at: - description: The Unix timestamp (in seconds) for when the run step completed. + last_active_at: + description: The Unix timestamp (in seconds) for when the vector store was last active. type: integer nullable: true metadata: @@ -8319,31 +12120,78 @@ components: type: object x-oaiTypeLabel: map nullable: true - usage: - $ref: "#/components/schemas/RunStepCompletionUsage" required: - id - object + - usage_bytes - created_at - - assistant_id - - thread_id - - run_id - - type - status - - step_details - - last_error - - expired_at - - cancelled_at - - failed_at - - completed_at + - last_active_at + - name + - file_counts - metadata - - usage x-oaiMeta: - name: The run step object + name: The vector store object beta: true - example: *run_step_object_example + example: | + { + "id": "vs_123", + "object": "vector_store", + "created_at": 1698107661, + "usage_bytes": 123456, + "last_active_at": 1698107661, + "name": "my_vector_store", + "status": "completed", + "file_counts": { + "in_progress": 0, + "completed": 100, + "cancelled": 0, + "failed": 0, + "total": 100 + }, + "metadata": {}, + "last_used_at": 1698107661 + } - ListRunStepsResponse: + CreateVectorStoreRequest: + type: object + additionalProperties: false + properties: + file_ids: + description: A list of [File](/docs/api-reference/files) IDs that the vector store should use. Useful for tools like `file_search` that can access files. + type: array + maxItems: 500 + items: + type: string + name: + description: The name of the vector store. + type: string + expires_after: + $ref: "#/components/schemas/VectorStoreExpirationAfter" + metadata: + description: *metadata_description + type: object + x-oaiTypeLabel: map + nullable: true + + UpdateVectorStoreRequest: + type: object + additionalProperties: false + properties: + name: + description: The name of the vector store. + type: string + nullable: true + expires_after: + $ref: "#/components/schemas/VectorStoreExpirationAfter" + nullable: true + metadata: + description: *metadata_description + type: object + x-oaiTypeLabel: map + nullable: true + + ListVectorStoresResponse: properties: object: type: string @@ -8351,13 +12199,13 @@ components: data: type: array items: - $ref: "#/components/schemas/RunStepObject" + $ref: "#/components/schemas/VectorStoreObject" first_id: type: string - example: "step_abc123" + example: "vs_abc123" last_id: type: string - example: "step_abc456" + example: "vs_abc456" has_more: type: boolean example: false @@ -8368,325 +12216,801 @@ components: - last_id - has_more - RunStepDetailsMessageCreationObject: - title: Message creation + DeleteVectorStoreResponse: type: object - description: Details of the message creation by the run step. properties: - type: - description: Always `message_creation`. + id: type: string - enum: ["message_creation"] - message_creation: - type: object - properties: - message_id: - type: string - description: The ID of the message that was created by this run step. - required: - - message_id - required: - - type - - message_creation - - RunStepDetailsToolCallsObject: - title: Tool calls - type: object - description: Details of the tool call. - properties: - type: - description: Always `tool_calls`. + deleted: + type: boolean + object: type: string - enum: ["tool_calls"] - tool_calls: - type: array - description: | - An array of tool calls the run step was involved in. These can be associated with one of three types of tools: `code_interpreter`, `retrieval`, or `function`. - items: - oneOf: - - $ref: "#/components/schemas/RunStepDetailsToolCallsCodeObject" - - $ref: "#/components/schemas/RunStepDetailsToolCallsRetrievalObject" - - $ref: "#/components/schemas/RunStepDetailsToolCallsFunctionObject" - x-oaiExpandable: true + enum: [vector_store.deleted] required: - - type - - tool_calls + - id + - object + - deleted - RunStepDetailsToolCallsCodeObject: - title: Code interpreter tool call + VectorStoreFileObject: type: object - description: Details of the Code Interpreter tool call the run step was involved in. + title: Vector store files + description: A list of files attached to a vector store. properties: id: + description: The identifier, which can be referenced in API endpoints. type: string - description: The ID of the tool call. - type: + object: + description: The object type, which is always `vector_store.file`. type: string - description: The type of tool call. This is always going to be `code_interpreter` for this type of tool call. - enum: ["code_interpreter"] - code_interpreter: - type: object - description: The Code Interpreter tool call definition. - required: - - input - - outputs + enum: ["vector_store.file"] + usage_bytes: + description: The total vector store usage in bytes. Note that this may be different from the original file size. + type: integer + created_at: + description: The Unix timestamp (in seconds) for when the vector store file was created. + type: integer + vector_store_id: + description: The ID of the [vector store](/docs/api-reference/vector-stores/object) that the [File](/docs/api-reference/files) is attached to. + type: string + status: + description: The status of the vector store file, which can be either `in_progress`, `completed`, `cancelled`, or `failed`. The status `completed` indicates that the vector store file is ready for use. + type: string + enum: ["in_progress", "completed", "cancelled", "failed"] + last_error: + type: object + description: The last error associated with this vector store file. Will be `null` if there are no errors. + nullable: true properties: - input: + code: type: string - description: The input to the Code Interpreter tool call. - outputs: - type: array - description: The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (`logs`) or images (`image`). Each of these are represented by a different object type. - items: - type: object - oneOf: - - $ref: "#/components/schemas/RunStepDetailsToolCallsCodeOutputLogsObject" - - $ref: "#/components/schemas/RunStepDetailsToolCallsCodeOutputImageObject" - x-oaiExpandable: true + description: One of `server_error` or `rate_limit_exceeded`. + enum: + [ + "internal_error", + "file_not_found", + "parsing_error", + "unhandled_mime_type", + ] + message: + type: string + description: A human-readable description of the error. + required: + - code + - message required: - id - - type - - code_interpreter + - object + - usage_bytes + - created_at + - vector_store_id + - status + - last_error + x-oaiMeta: + name: The vector store file object + beta: true + example: | + { + "id": "file-abc123", + "object": "vector_store.file", + "usage_bytes": 1234, + "created_at": 1698107661, + "vector_store_id": "vs_abc123", + "status": "completed", + "last_error": null + } - RunStepDetailsToolCallsCodeOutputLogsObject: - title: Code interpreter log output + CreateVectorStoreFileRequest: type: object - description: Text output from the Code Interpreter tool call as part of a run step. + additionalProperties: false properties: - type: - description: Always `logs`. - type: string - enum: ["logs"] - logs: + file_id: + description: A [File](/docs/api-reference/files) ID that the vector store should use. Useful for tools like `file_search` that can access files. type: string - description: The text output from the Code Interpreter tool call. required: - - type - - logs + - file_id - RunStepDetailsToolCallsCodeOutputImageObject: - title: Code interpreter image output - type: object + ListVectorStoreFilesResponse: properties: - type: - description: Always `image`. + object: type: string - enum: ["image"] - image: - type: object - properties: - file_id: - description: The [file](/docs/api-reference/files) ID of the image. - type: string - required: - - file_id + example: "list" + data: + type: array + items: + $ref: "#/components/schemas/VectorStoreFileObject" + first_id: + type: string + example: "file-abc123" + last_id: + type: string + example: "file-abc456" + has_more: + type: boolean + example: false required: - - type - - image + - object + - data + - first_id + - last_id + - has_more - RunStepDetailsToolCallsRetrievalObject: - title: Retrieval tool call + DeleteVectorStoreFileResponse: type: object properties: id: type: string - description: The ID of the tool call object. - type: + deleted: + type: boolean + object: type: string - description: The type of tool call. This is always going to be `retrieval` for this type of tool call. - enum: ["retrieval"] - retrieval: - type: object - description: For now, this is always going to be an empty object. - x-oaiTypeLabel: map + enum: [vector_store.file.deleted] required: - id - - type - - retrieval + - object + - deleted - RunStepDetailsToolCallsFunctionObject: + VectorStoreFileBatchObject: type: object - title: Function tool call + title: Vector store file batch + description: A batch of files attached to a vector store. properties: id: + description: The identifier, which can be referenced in API endpoints. type: string - description: The ID of the tool call object. - type: + object: + description: The object type, which is always `vector_store.file_batch`. type: string - description: The type of tool call. This is always going to be `function` for this type of tool call. - enum: ["function"] - function: + enum: ["vector_store.files_batch"] + created_at: + description: The Unix timestamp (in seconds) for when the vector store files batch was created. + type: integer + vector_store_id: + description: The ID of the [vector store](/docs/api-reference/vector-stores/object) that the [File](/docs/api-reference/files) is attached to. + type: string + status: + description: The status of the vector store files batch, which can be either `in_progress`, `completed`, `cancelled` or `failed`. + type: string + enum: ["in_progress", "completed", "cancelled", "failed"] + file_counts: type: object - description: The definition of the function that was called. properties: - name: + in_progress: + description: The number of files that are currently being processed. + type: integer + completed: + description: The number of files that have been processed. + type: integer + failed: + description: The number of files that have failed to process. + type: integer + cancelled: + description: The number of files that where cancelled. + type: integer + total: + description: The total number of files. + type: integer + required: + - in_progress + - completed + - cancelled + - failed + - total + required: + - id + - object + - created_at + - vector_store_id + - status + - file_counts + x-oaiMeta: + name: The vector store files batch object + beta: true + example: | + { + "id": "vsfb_123", + "object": "vector_store.files_batch", + "created_at": 1698107661, + "vector_store_id": "vs_abc123", + "status": "completed", + "file_counts": { + "in_progress": 0, + "completed": 100, + "failed": 0, + "cancelled": 0, + "total": 100 + } + } + + CreateVectorStoreFileBatchRequest: + type: object + additionalProperties: false + properties: + file_ids: + description: A list of [File](/docs/api-reference/files) IDs that the vector store should use. Useful for tools like `file_search` that can access files. + type: array + minItems: 1 + maxItems: 500 + items: + type: string + required: + - file_ids + + AssistantStreamEvent: + description: | + Represents an event emitted when streaming a Run. + + Each event in a server-sent events stream has an `event` and `data` property: + + ``` + event: thread.created + data: {"id": "thread_123", "object": "thread", ...} + ``` + + We emit events whenever a new object is created, transitions to a new state, or is being + streamed in parts (deltas). For example, we emit `thread.run.created` when a new run + is created, `thread.run.completed` when a run completes, and so on. When an Assistant chooses + to create a message during a run, we emit a `thread.message.created event`, a + `thread.message.in_progress` event, many `thread.message.delta` events, and finally a + `thread.message.completed` event. + + We may add additional events over time, so we recommend handling unknown events gracefully + in your code. See the [Assistants API quickstart](/docs/assistants/overview) to learn how to + integrate the Assistants API with streaming. + oneOf: + - $ref: "#/components/schemas/ThreadStreamEvent" + - $ref: "#/components/schemas/RunStreamEvent" + - $ref: "#/components/schemas/RunStepStreamEvent" + - $ref: "#/components/schemas/MessageStreamEvent" + - $ref: "#/components/schemas/ErrorEvent" + - $ref: "#/components/schemas/DoneEvent" + x-oaiMeta: + name: Assistant stream events + beta: true + + ThreadStreamEvent: + oneOf: + - type: object + properties: + event: + type: string + enum: ["thread.created"] + data: + $ref: "#/components/schemas/ThreadObject" + required: + - event + - data + description: Occurs when a new [thread](/docs/api-reference/threads/object) is created. + x-oaiMeta: + dataDescription: "`data` is a [thread](/docs/api-reference/threads/object)" + + RunStreamEvent: + oneOf: + - type: object + properties: + event: + type: string + enum: ["thread.run.created"] + data: + $ref: "#/components/schemas/RunObject" + required: + - event + - data + description: Occurs when a new [run](/docs/api-reference/runs/object) is created. + x-oaiMeta: + dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" + - type: object + properties: + event: + type: string + enum: ["thread.run.queued"] + data: + $ref: "#/components/schemas/RunObject" + required: + - event + - data + description: Occurs when a [run](/docs/api-reference/runs/object) moves to a `queued` status. + x-oaiMeta: + dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" + - type: object + properties: + event: + type: string + enum: ["thread.run.in_progress"] + data: + $ref: "#/components/schemas/RunObject" + required: + - event + - data + description: Occurs when a [run](/docs/api-reference/runs/object) moves to an `in_progress` status. + x-oaiMeta: + dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" + - type: object + properties: + event: + type: string + enum: ["thread.run.requires_action"] + data: + $ref: "#/components/schemas/RunObject" + required: + - event + - data + description: Occurs when a [run](/docs/api-reference/runs/object) moves to a `requires_action` status. + x-oaiMeta: + dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" + - type: object + properties: + event: + type: string + enum: ["thread.run.completed"] + data: + $ref: "#/components/schemas/RunObject" + required: + - event + - data + description: Occurs when a [run](/docs/api-reference/runs/object) is completed. + x-oaiMeta: + dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" + - type: object + properties: + event: + type: string + enum: ["thread.run.failed"] + data: + $ref: "#/components/schemas/RunObject" + required: + - event + - data + description: Occurs when a [run](/docs/api-reference/runs/object) fails. + x-oaiMeta: + dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" + - type: object + properties: + event: + type: string + enum: ["thread.run.cancelling"] + data: + $ref: "#/components/schemas/RunObject" + required: + - event + - data + description: Occurs when a [run](/docs/api-reference/runs/object) moves to a `cancelling` status. + x-oaiMeta: + dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" + - type: object + properties: + event: + type: string + enum: ["thread.run.cancelled"] + data: + $ref: "#/components/schemas/RunObject" + required: + - event + - data + description: Occurs when a [run](/docs/api-reference/runs/object) is cancelled. + x-oaiMeta: + dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" + - type: object + properties: + event: + type: string + enum: ["thread.run.expired"] + data: + $ref: "#/components/schemas/RunObject" + required: + - event + - data + description: Occurs when a [run](/docs/api-reference/runs/object) expires. + x-oaiMeta: + dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" + + RunStepStreamEvent: + oneOf: + - type: object + properties: + event: + type: string + enum: ["thread.run.step.created"] + data: + $ref: "#/components/schemas/RunStepObject" + required: + - event + - data + description: Occurs when a [run step](/docs/api-reference/runs/step-object) is created. + x-oaiMeta: + dataDescription: "`data` is a [run step](/docs/api-reference/runs/step-object)" + - type: object + properties: + event: + type: string + enum: ["thread.run.step.in_progress"] + data: + $ref: "#/components/schemas/RunStepObject" + required: + - event + - data + description: Occurs when a [run step](/docs/api-reference/runs/step-object) moves to an `in_progress` state. + x-oaiMeta: + dataDescription: "`data` is a [run step](/docs/api-reference/runs/step-object)" + - type: object + properties: + event: + type: string + enum: ["thread.run.step.delta"] + data: + $ref: "#/components/schemas/RunStepDeltaObject" + required: + - event + - data + description: Occurs when parts of a [run step](/docs/api-reference/runs/step-object) are being streamed. + x-oaiMeta: + dataDescription: "`data` is a [run step delta](/docs/api-reference/assistants-streaming/run-step-delta-object)" + - type: object + properties: + event: + type: string + enum: ["thread.run.step.completed"] + data: + $ref: "#/components/schemas/RunStepObject" + required: + - event + - data + description: Occurs when a [run step](/docs/api-reference/runs/step-object) is completed. + x-oaiMeta: + dataDescription: "`data` is a [run step](/docs/api-reference/runs/step-object)" + - type: object + properties: + event: + type: string + enum: ["thread.run.step.failed"] + data: + $ref: "#/components/schemas/RunStepObject" + required: + - event + - data + description: Occurs when a [run step](/docs/api-reference/runs/step-object) fails. + x-oaiMeta: + dataDescription: "`data` is a [run step](/docs/api-reference/runs/step-object)" + - type: object + properties: + event: + type: string + enum: ["thread.run.step.cancelled"] + data: + $ref: "#/components/schemas/RunStepObject" + required: + - event + - data + description: Occurs when a [run step](/docs/api-reference/runs/step-object) is cancelled. + x-oaiMeta: + dataDescription: "`data` is a [run step](/docs/api-reference/runs/step-object)" + - type: object + properties: + event: + type: string + enum: ["thread.run.step.expired"] + data: + $ref: "#/components/schemas/RunStepObject" + required: + - event + - data + description: Occurs when a [run step](/docs/api-reference/runs/step-object) expires. + x-oaiMeta: + dataDescription: "`data` is a [run step](/docs/api-reference/runs/step-object)" + + MessageStreamEvent: + oneOf: + - type: object + properties: + event: + type: string + enum: ["thread.message.created"] + data: + $ref: "#/components/schemas/MessageObject" + required: + - event + - data + description: Occurs when a [message](/docs/api-reference/messages/object) is created. + x-oaiMeta: + dataDescription: "`data` is a [message](/docs/api-reference/messages/object)" + - type: object + properties: + event: + type: string + enum: ["thread.message.in_progress"] + data: + $ref: "#/components/schemas/MessageObject" + required: + - event + - data + description: Occurs when a [message](/docs/api-reference/messages/object) moves to an `in_progress` state. + x-oaiMeta: + dataDescription: "`data` is a [message](/docs/api-reference/messages/object)" + - type: object + properties: + event: type: string - description: The name of the function. - arguments: + enum: ["thread.message.delta"] + data: + $ref: "#/components/schemas/MessageDeltaObject" + required: + - event + - data + description: Occurs when parts of a [Message](/docs/api-reference/messages/object) are being streamed. + x-oaiMeta: + dataDescription: "`data` is a [message delta](/docs/api-reference/assistants-streaming/message-delta-object)" + - type: object + properties: + event: type: string - description: The arguments passed to the function. - output: + enum: ["thread.message.completed"] + data: + $ref: "#/components/schemas/MessageObject" + required: + - event + - data + description: Occurs when a [message](/docs/api-reference/messages/object) is completed. + x-oaiMeta: + dataDescription: "`data` is a [message](/docs/api-reference/messages/object)" + - type: object + properties: + event: type: string - description: The output of the function. This will be `null` if the outputs have not been [submitted](/docs/api-reference/runs/submitToolOutputs) yet. - nullable: true + enum: ["thread.message.incomplete"] + data: + $ref: "#/components/schemas/MessageObject" required: - - name - - arguments - - output - required: - - id - - type - - function + - event + - data + description: Occurs when a [message](/docs/api-reference/messages/object) ends before it is completed. + x-oaiMeta: + dataDescription: "`data` is a [message](/docs/api-reference/messages/object)" - AssistantFileObject: + ErrorEvent: type: object - title: Assistant files - description: A list of [Files](/docs/api-reference/files) attached to an `assistant`. properties: - id: - description: The identifier, which can be referenced in API endpoints. - type: string - object: - description: The object type, which is always `assistant.file`. - type: string - enum: [assistant.file] - created_at: - description: The Unix timestamp (in seconds) for when the assistant file was created. - type: integer - assistant_id: - description: The assistant ID that the file is attached to. + event: type: string + enum: ["error"] + data: + $ref: "#/components/schemas/Error" required: - - id - - object - - created_at - - assistant_id + - event + - data + description: Occurs when an [error](/docs/guides/error-codes/api-errors) occurs. This can happen due to an internal server error or a timeout. x-oaiMeta: - name: The assistant file object - beta: true - example: | - { - "id": "file-abc123", - "object": "assistant.file", - "created_at": 1699055364, - "assistant_id": "asst_abc123" - } + dataDescription: "`data` is an [error](/docs/guides/error-codes/api-errors)" - CreateAssistantFileRequest: + DoneEvent: type: object - additionalProperties: false properties: - file_id: - description: A [File](/docs/api-reference/files) ID (with `purpose="assistants"`) that the assistant should use. Useful for tools like `retrieval` and `code_interpreter` that can access files. + event: + type: string + enum: ["done"] + data: type: string + enum: ["[DONE]"] required: - - file_id + - event + - data + description: Occurs when a stream ends. + x-oaiMeta: + dataDescription: "`data` is `[DONE]`" - DeleteAssistantFileResponse: + Batch: type: object - description: Deletes the association between the assistant and the file, but does not delete the [File](/docs/api-reference/files) object itself. properties: id: type: string - deleted: - type: boolean object: type: string - enum: [assistant.file.deleted] + enum: [batch] + description: The object type, which is always `batch`. + endpoint: + type: string + description: The OpenAI API endpoint used by the batch. + + errors: + type: object + properties: + object: + type: string + description: The object type, which is always `list`. + data: + type: array + items: + type: object + properties: + code: + type: string + description: An error code identifying the error type. + message: + type: string + description: A human-readable message providing more details about the error. + param: + type: string + description: The name of the parameter that caused the error, if applicable. + nullable: true + line: + type: integer + description: The line number of the input file where the error occurred, if applicable. + nullable: true + input_file_id: + type: string + description: The ID of the input file for the batch. + completion_window: + type: string + description: The time frame within which the batch should be processed. + status: + type: string + description: The current status of the batch. + enum: + - validating + - failed + - in_progress + - finalizing + - completed + - expired + - cancelling + - cancelled + output_file_id: + type: string + description: The ID of the file containing the outputs of successfully executed requests. + error_file_id: + type: string + description: The ID of the file containing the outputs of requests with errors. + created_at: + type: integer + description: The Unix timestamp (in seconds) for when the batch was created. + in_progress_at: + type: integer + description: The Unix timestamp (in seconds) for when the batch started processing. + expires_at: + type: integer + description: The Unix timestamp (in seconds) for when the batch will expire. + finalizing_at: + type: integer + description: The Unix timestamp (in seconds) for when the batch started finalizing. + completed_at: + type: integer + description: The Unix timestamp (in seconds) for when the batch was completed. + failed_at: + type: integer + description: The Unix timestamp (in seconds) for when the batch failed. + expired_at: + type: integer + description: The Unix timestamp (in seconds) for when the batch expired. + cancelling_at: + type: integer + description: The Unix timestamp (in seconds) for when the batch started cancelling. + cancelled_at: + type: integer + description: The Unix timestamp (in seconds) for when the batch was cancelled. + request_counts: + type: object + properties: + total: + type: integer + description: Total number of requests in the batch. + completed: + type: integer + description: Number of requests that have been completed successfully. + failed: + type: integer + description: Number of requests that have failed. + required: + - total + - completed + - failed + description: The request counts for different statuses within the batch. + metadata: + description: *metadata_description + type: object + x-oaiTypeLabel: map + nullable: true required: - id - object - - deleted - ListAssistantFilesResponse: + - endpoint + - input_file_id + - completion_window + - status + - created_at + x-oaiMeta: + name: The batch object + example: *batch_object + + BatchRequestInput: + type: object + description: The per-line object of the batch input file properties: - object: + custom_id: type: string - example: "list" - data: - type: array - items: - $ref: "#/components/schemas/AssistantFileObject" - first_id: + description: A developer-provided per-request id that will be used to match outputs to inputs. Must be unique for each request in a batch. + method: type: string - example: "file-abc123" - last_id: + enum: ["POST"] + description: The HTTP method to be used for the request. Currently only `POST` is supported. + url: type: string - example: "file-abc456" - has_more: - type: boolean - example: false - required: - - object - - data - - items - - first_id - - last_id - - has_more + description: The OpenAI API relative URL to be used for the request. Currently `/v1/chat/completions`, `/v1/embeddings`, and `/v1/completions` are supported. + x-oaiMeta: + name: The request input object + example: | + {"custom_id": "request-1", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "What is 2+2?"}]}} - MessageFileObject: + BatchRequestOutput: type: object - title: Message files - description: A list of files attached to a `message`. + description: The per-line object of the batch output and error files properties: id: - description: The identifier, which can be referenced in API endpoints. - type: string - object: - description: The object type, which is always `thread.message.file`. type: string - enum: ["thread.message.file"] - created_at: - description: The Unix timestamp (in seconds) for when the message file was created. - type: integer - message_id: - description: The ID of the [message](/docs/api-reference/messages) that the [File](/docs/api-reference/files) is attached to. + custom_id: type: string - required: - - id - - object - - created_at - - message_id + description: A developer-provided per-request id that will be used to match outputs to inputs. + response: + type: object + nullable: true + properties: + status_code: + type: integer + description: The HTTP status code of the response + request_id: + type: string + description: An unique identifier for the OpenAI API request. Please include this request ID when contacting support. + body: + type: object + x-oaiTypeLabel: map + description: The JSON body of the response + error: + type: object + nullable: true + description: For requests that failed with a non-HTTP error, this will contain more information on the cause of the failure. + properties: + code: + type: string + description: A machine-readable error code. + message: + type: string + description: A human-readable error message. x-oaiMeta: - name: The message file object - beta: true + name: The request output object example: | - { - "id": "file-abc123", - "object": "thread.message.file", - "created_at": 1698107661, - "message_id": "message_QLoItBbqwyAJEzlTy4y9kOMM", - "file_id": "file-abc123" - } + {"id": "batch_req_wnaDys", "custom_id": "request-2", "response": {"status_code": 200, "request_id": "req_c187b3", "body": {"id": "chatcmpl-9758Iw", "object": "chat.completion", "created": 1711475054, "model": "gpt-3.5-turbo", "choices": [{"index": 0, "message": {"role": "assistant", "content": "2 + 2 equals 4."}, "finish_reason": "stop"}], "usage": {"prompt_tokens": 24, "completion_tokens": 15, "total_tokens": 39}, "system_fingerprint": null}}, "error": null} - ListMessageFilesResponse: + ListBatchesResponse: + type: object properties: - object: - type: string - example: "list" data: type: array items: - $ref: "#/components/schemas/MessageFileObject" + $ref: "#/components/schemas/Batch" first_id: type: string - example: "file-abc123" + example: "batch_abc123" last_id: type: string - example: "file-abc456" + example: "batch_abc456" has_more: type: boolean - example: false + object: + type: string + enum: [list] required: - object - data - - items - - first_id - - last_id - has_more security: - ApiKeyAuth: [] + x-oaiMeta: + navigationGroups: + - id: endpoints + title: Endpoints + - id: assistants + title: Assistants + - id: legacy + title: Legacy groups: # > General Notes # The `groups` section is used to generate the API reference pages and navigation, in the same @@ -8715,6 +13039,7 @@ x-oaiMeta: Learn how to turn audio into text or text into audio. Related guide: [Speech to text](/docs/guides/speech-to-text) + navigationGroup: endpoints sections: - type: endpoint key: createSpeech @@ -8725,12 +13050,19 @@ x-oaiMeta: - type: endpoint key: createTranslation path: createTranslation + - type: object + key: CreateTranscriptionResponseJson + path: json-object + - type: object + key: CreateTranscriptionResponseVerboseJson + path: verbose-json-object - id: chat title: Chat description: | Given a list of messages comprising a conversation, the model will return a response. Related guide: [Chat Completions](/docs/guides/text-generation) + navigationGroup: endpoints sections: - type: endpoint key: createChatCompletion @@ -8747,6 +13079,7 @@ x-oaiMeta: Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms. Related guide: [Embeddings](/docs/guides/embeddings) + navigationGroup: endpoints sections: - type: endpoint key: createEmbedding @@ -8760,6 +13093,7 @@ x-oaiMeta: Manage fine-tuning jobs to tailor a model to your specific training data. Related guide: [Fine-tune models](/docs/guides/fine-tuning) + navigationGroup: endpoints sections: - type: endpoint key: createFineTuningJob @@ -8770,6 +13104,9 @@ x-oaiMeta: - type: endpoint key: listFineTuningEvents path: list-events + - type: endpoint + key: listFineTuningJobCheckpoints + path: list-checkpoints - type: endpoint key: retrieveFineTuningJob path: retrieve @@ -8782,10 +13119,43 @@ x-oaiMeta: - type: object key: FineTuningJobEvent path: event-object + - type: object + key: FineTuningJobCheckpoint + path: checkpoint-object + - id: batch + title: Batch + description: | + Create large batches of API requests for asynchronous processing. The Batch API returns completions within 24 hours for a 50% discount. + + Related guide: [Batch](/docs/guides/batch) + navigationGroup: endpoints + sections: + - type: endpoint + key: createBatch + path: create + - type: endpoint + key: retrieveBatch + path: retrieve + - type: endpoint + key: cancelBatch + path: cancel + - type: endpoint + key: listBatches + path: list + - type: object + key: Batch + path: object + - type: object + key: BatchRequestInput + path: requestInput + - type: object + key: BatchRequestOutput + path: requestOutput - id: files title: Files description: | - Files are used to upload documents that can be used with features like [Assistants](/docs/api-reference/assistants) and [Fine-tuning](/docs/api-reference/fine-tuning). + Files are used to upload documents that can be used with features like [Assistants](/docs/api-reference/assistants), [Fine-tuning](/docs/api-reference/fine-tuning), and [Batch API](/docs/guides/batch). + navigationGroup: endpoints sections: - type: endpoint key: createFile @@ -8811,6 +13181,7 @@ x-oaiMeta: Given a prompt and/or an input image, the model will generate a new image. Related guide: [Image generation](/docs/guides/images) + navigationGroup: endpoints sections: - type: endpoint key: createImage @@ -8828,6 +13199,7 @@ x-oaiMeta: title: Models description: | List and describe the various models available in the API. You can refer to the [Models](/docs/models) documentation to understand what models are available and the differences between them. + navigationGroup: endpoints sections: - type: endpoint key: listModels @@ -8844,9 +13216,10 @@ x-oaiMeta: - id: moderations title: Moderations description: | - Given a input text, outputs if the model classifies it as violating OpenAI's content policy. + Given some input text, outputs if the model classifies it as potentially harmful across several categories. Related guide: [Moderations](/docs/guides/moderation) + navigationGroup: endpoints sections: - type: endpoint key: createModeration @@ -8861,40 +13234,26 @@ x-oaiMeta: Build assistants that can call models and use tools to perform tasks. [Get started with the Assistants API](/docs/assistants) + navigationGroup: assistants sections: - type: endpoint key: createAssistant path: createAssistant - - type: endpoint - key: createAssistantFile - path: createAssistantFile - type: endpoint key: listAssistants path: listAssistants - - type: endpoint - key: listAssistantFiles - path: listAssistantFiles - type: endpoint key: getAssistant path: getAssistant - - type: endpoint - key: getAssistantFile - path: getAssistantFile - type: endpoint key: modifyAssistant path: modifyAssistant - type: endpoint key: deleteAssistant path: deleteAssistant - - type: endpoint - key: deleteAssistantFile - path: deleteAssistantFile - type: object key: AssistantObject path: object - - type: object - key: AssistantFileObject - path: file-object - id: threads title: Threads beta: true @@ -8902,6 +13261,7 @@ x-oaiMeta: Create threads that assistants can interact with. Related guide: [Assistants](/docs/assistants/overview) + navigationGroup: assistants sections: - type: endpoint key: createThread @@ -8925,6 +13285,7 @@ x-oaiMeta: Create messages within threads Related guide: [Assistants](/docs/assistants/overview) + navigationGroup: assistants sections: - type: endpoint key: createMessage @@ -8932,24 +13293,18 @@ x-oaiMeta: - type: endpoint key: listMessages path: listMessages - - type: endpoint - key: listMessageFiles - path: listMessageFiles - type: endpoint key: getMessage path: getMessage - - type: endpoint - key: getMessageFile - path: getMessageFile - type: endpoint key: modifyMessage path: modifyMessage + - type: endpoint + key: deleteMessage + path: deleteMessage - type: object key: MessageObject path: object - - type: object - key: MessageFileObject - path: file-object - id: runs title: Runs beta: true @@ -8957,6 +13312,7 @@ x-oaiMeta: Represents an execution run on a thread. Related guide: [Assistants](/docs/assistants/overview) + navigationGroup: assistants sections: - type: endpoint key: createRun @@ -8967,15 +13323,9 @@ x-oaiMeta: - type: endpoint key: listRuns path: listRuns - - type: endpoint - key: listRunSteps - path: listRunSteps - type: endpoint key: getRun path: getRun - - type: endpoint - key: getRunStep - path: getRunStep - type: endpoint key: modifyRun path: modifyRun @@ -8988,14 +13338,128 @@ x-oaiMeta: - type: object key: RunObject path: object + - id: run-steps + title: Run Steps + beta: true + description: | + Represents the steps (model and tool calls) taken during the run. + + Related guide: [Assistants](/docs/assistants/overview) + navigationGroup: assistants + sections: + - type: endpoint + key: listRunSteps + path: listRunSteps + - type: endpoint + key: getRunStep + path: getRunStep - type: object key: RunStepObject path: step-object + - id: vector-stores + title: Vector Stores + beta: true + description: | + Vector stores are used to store files for use by the `file_search` tool. + + Related guide: [File Search](/docs/assistants/tools/file-search) + navigationGroup: assistants + sections: + - type: endpoint + key: createVectorStore + path: create + - type: endpoint + key: listVectorStores + path: list + - type: endpoint + key: getVectorStore + path: retrieve + - type: endpoint + key: modifyVectorStore + path: modify + - type: endpoint + key: deleteVectorStore + path: delete + - type: object + key: VectorStoreObject + path: object + - id: vector-stores-files + title: Vector Store Files + beta: true + description: | + Vector store files represent files inside a vector store. + + Related guide: [File Search](/docs/assistants/tools/file-search) + navigationGroup: assistants + sections: + - type: endpoint + key: createVectorStoreFile + path: createFile + - type: endpoint + key: listVectorStoreFiles + path: listFiles + - type: endpoint + key: getVectorStoreFile + path: getFile + - type: endpoint + key: deleteVectorStoreFile + path: deleteFile + - type: object + key: VectorStoreFileObject + path: file-object + - id: vector-stores-file-batches + title: Vector Store File Batches + beta: true + description: | + Vector store file batches represent operations to add multiple files to a vector store. + + Related guide: [File Search](/docs/assistants/tools/file-search) + navigationGroup: assistants + sections: + - type: endpoint + key: createVectorStoreFileBatch + path: createBatch + - type: endpoint + key: getVectorStoreFileBatch + path: getBatch + - type: endpoint + key: cancelVectorStoreFileBatch + path: cancelBatch + - type: endpoint + key: listFilesInVectorStoreBatch + path: listBatchFiles + - type: object + key: VectorStoreFileBatchObject + path: batch-object + - id: assistants-streaming + title: Streaming + beta: true + description: | + Stream the result of executing a Run or resuming a Run after submitting tool outputs. + + You can stream events from the [Create Thread and Run](/docs/api-reference/runs/createThreadAndRun), + [Create Run](/docs/api-reference/runs/createRun), and [Submit Tool Outputs](/docs/api-reference/runs/submitToolOutputs) + endpoints by passing `"stream": true`. The response will be a [Server-Sent events](https://html.spec.whatwg.org/multipage/server-sent-events.html#server-sent-events) stream. + + Our Node and Python SDKs provide helpful utilities to make streaming easy. Reference the + [Assistants API quickstart](/docs/assistants/overview) to learn more. + navigationGroup: assistants + sections: + - type: object + key: MessageDeltaObject + path: message-delta-object + - type: object + key: RunStepDeltaObject + path: run-step-delta-object + - type: object + key: AssistantStreamEvent + path: events - id: completions title: Completions legacy: true + navigationGroup: legacy description: | - Given a prompt, the model will return one or more predicted completions along with the probabilities of alternative tokens at each position. Most developer should use our [Chat Completions API](/docs/guides/text-generation/text-generation-models) to leverage our best and newest models. Most models that support the legacy Completions endpoint [will be shut off on January 4th, 2024](/docs/deprecations/2023-07-06-gpt-and-embeddings). + Given a prompt, the model will return one or more predicted completions along with the probabilities of alternative tokens at each position. Most developer should use our [Chat Completions API](/docs/guides/text-generation/text-generation-models) to leverage our best and newest models. sections: - type: endpoint key: createCompletion