fix: /api/id/<id>/namespace/<namespace>/<token>

CHANGELOG.md

@@ -5,8 +5,10 @@
     *Andrea Sponziello* 
 ### **Copyrigth**: *Tiledesk SRL*
 
-## [2024-09-21]
-### 0.3.1
+
+## [2024-10-10]
+### 0.3.2-rc2
+- fix: /api/id/{id}/namespace/{namespace}/{token}
 - add sentence embedding with bge-m3
 - add: hybrid search with bg3-m3
 - modify: deleted env variable for vector store 

README.md

@@ -12,12 +12,8 @@ pip install -e .
 
 
 ```commandline
-export REDIS_URL="redis://localhost:6379/0"
-export PINECONE_TYPE="serverless|pod"
-export PINECONE_API_KEY="pinecone api key"
-export PINECONE_TEXT_KEY="pinecone field for text - default text in pod content"
-export PINECONE_INDEX="pinecone index name"
-export TILELLM_ROLE="role in pod. Train enable all the APIs, qa do not consume redis queue only Q&A"
+export JWT_SECRET_KEY="yourkey-256-bit"
+export TOKENIZERS_PARALLELISM=false
 export WORKERS=INT number of workers 2*CPU+1
 export TIMEOUT=INT seconds of timeout default=180
 export MAXREQUESTS=INT The maximum number of requests a worker will process before restarting. deafult=1200
@@ -34,11 +30,9 @@ sudo docker build -t tilellm .
 
 
 ```
-sudo docker run -d -p 8000:8000 --env environment="dev|prod" \
---env PINECONE_API_KEY="yourapikey" \
---env PINECONE_TEXT_KEY="text|content" \
---env PINECONE_INDEX="index_name" \
---env TILELLM_ROLE="train|qa" \
+sudo docker run -d -p 8000:8000 \
+--env JWT_SECRET_KEY = "yourkey-256-bit"
+--env TOKENIZERS_PARALLELISM=false
 --env WORKERS=3 \
 --env TIMEOUT=180 \
 --env MAXREQUESTS=1200 \
@@ -145,19 +139,52 @@ In this method, the gradient of distance is used to split chunks along with the
 
 ```json
 {
- ...
- "embedding":"huggingface",
-  "hybrid":true,
-  "sparse_encoder":"splade|bge-m3",
-  ... 
-  "engine":
-   {
-    "name": "",
-    "type": "",
-    "apikey" : "",
-    "vector_size": 1024,
-    "index_name": "" 
-   }  
+  "id": "content id",
+  "source": "name or url of document",
+  "type": "text|txt|url|pdf|docx",
+  "content": "content of document",
+  "hybrid": true,
+  "sparse_encoder": "splade|bge-m3",
+  "gptkey": "llm key; openai|anthropic|groq|cohere|gemini|ollama, ",
+  "scrape_type": 0,
+  "embedding": "name of embedding; huggingface|ollama|openai...|bge-m3",
+  "model": {
+    "name": "optional, used only with ollama",
+    "url": "ollama base url",
+    "dimension": 3072
+  },
+  "namespace": "vector store namespace",
+  "webhook": "string",
+  "semantic_chunk": false,
+  "breakpoint_threshold_type": "percentile",
+  "chunk_size": 1000,
+  "chunk_overlap": 100,
+  "parameters_scrape_type_4": {
+    "unwanted_tags": [
+      "string"
+    ],
+    "tags_to_extract": [
+      "string"
+    ],
+    "unwanted_classnames": [
+      "string"
+    ],
+    "desired_classnames": [
+      "string"
+    ],
+    "remove_lines": true,
+    "remove_comments": true,
+    "time_sleep": 2
+  },
+  "engine": {
+    "name": "pinecone",
+    "type": "serverless",
+    "apikey": "string",
+    "vector_size": 1536,
+    "index_name": "index name",
+    "text_key": "text for serverless; content for pod",
+    "metric": "cosine|dotproduct for hybrid"
+  }
 }
 ```
 
@@ -174,7 +201,7 @@ In this method, the gradient of distance is used to split chunks along with the
   "model": "es. claude-3-5-sonnet-20240620 | llama-3.1-70b-versatile",
   "temperature": 0.9,
   "max_tokens":2048,
-  "embedding":"huggingfacce",
+  "embedding":"huggingface",
   "sparse_encoder":"splade|bge-m3",
   "search_type":"hybrid",
   "alpha": 0.2,

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "tilellm"
-version = "0.3.0"
+version = "0.3.2-rc2"
 description = "tiledesk for RAG"
 authors = ["Gianluca Lorenzo <gianluca.lorenzo@gmail.com>"]
 repository = "https://github.com/Tiledesk/tiledesk-llm"
@@ -34,6 +34,7 @@ langchain-community = "0.3.1" #"0.2.10"
 langchain-experimental = "0.3.1" #no previous
 langchain-pinecone = "0.2.0"
 langchain-huggingface="0.1.0"
+langchain-ollama="0.2.0"
 peft = "0.13.0"
 
 tiktoken = "0.7.0"

tilellm/__main__.py

@@ -496,9 +496,13 @@ async def scrape_status_main(scrape_status_req: ScrapeStatusReq,
             return JSONResponse(content=scrape_status_response.model_dump())
         else:
             try:
-                retrieved_pinecone_data = await get_ids_namespace(metadata_id=scrape_status_req.id,
+                repository_engine = RepositoryEngine(engine=scrape_status_req.engine)
+                print(repository_engine.engine)
+                retrieved_pinecone_data = await get_ids_namespace(repository_engine,
+                                                                  metadata_id=scrape_status_req.id,
                                                                   namespace=scrape_status_req.namespace)
 
+
                 if retrieved_pinecone_data.matches:
                     logger.debug(retrieved_pinecone_data.matches[0].date)
                     date_from_metadata = retrieved_pinecone_data.matches[0].date

tilellm/controller/controller_utils.py

@@ -155,9 +155,12 @@ async def generate_answer_with_history(llm, question_answer, rag_chain, retrieve
                 | qa_prompt
                 | llm.with_structured_output(QuotedAnswer)
         )
-        chain_w_citations = RunnablePassthrough.assign(context=retrieve_docs).assign(
-            answer=rag_chain_from_docs
-        ).assign(only_answer=lambda text: text["answer"].answer)
+
+        chain_w_citations = (RunnablePassthrough.assign(context=retrieve_docs)
+                             .assign(answer=rag_chain_from_docs)
+                             .assign(only_answer=lambda text: text["answer"].answer)
+                             )
+
         conversational_rag_chain = RunnableWithMessageHistory(
             chain_w_citations,
             get_session_history,

tilellm/models/item_model.py

@@ -3,6 +3,11 @@
 from typing import Dict, Optional, List, Union, Any
 import datetime
 
+class OllamaModel(BaseModel):
+    name: str
+    url: str
+    dimension: Optional[int] = 1024
+
 
 class Engine(BaseModel):
     name: str = Field(default="pinecone")
@@ -50,6 +55,7 @@ class ItemSingle(BaseModel):
     gptkey: str | None = None
     scrape_type: int = Field(default_factory=lambda: 0)
     embedding: str = Field(default_factory=lambda: "text-embedding-ada-002")
+    model: Optional[OllamaModel] | None = None
     namespace: str | None = None
     webhook: str = Field(default_factory=lambda: "")
     semantic_chunk: Optional[bool] = Field(default=False)
@@ -108,15 +114,15 @@ class QuestionAnswer(BaseModel):
     namespace: str
     llm: Optional[str] = Field(default="openai")
     gptkey: str
-    model: str = Field(default="gpt-3.5-turbo")
+    model: Union[str, OllamaModel] = Field(default="gpt-3.5-turbo")
     sparse_encoder: Optional[str] = Field(default="splade") #bge-m3
     temperature: float = Field(default=0.0)
     top_k: int = Field(default=5)
-    max_tokens: int = Field(default=128)
+    max_tokens: int = Field(default=1024)
     embedding: str = Field(default_factory=lambda: "text-embedding-ada-002")
     similarity_threshold: float = Field(default_factory=lambda: 1.0)
     debug: bool = Field(default_factory=lambda: False)
-    citations: bool = Field(default_factory=lambda: True)
+    citations: bool = Field(default_factory=lambda: False)
     alpha: Optional[float] = Field(default=0.5)
     system_context: Optional[str] = None
     search_type: str = Field(default_factory=lambda: "similarity")
@@ -155,7 +161,7 @@ class QuestionToLLM(BaseModel):
     question: str
     llm_key: Union[str, AWSAuthentication]
     llm: str
-    model: str = Field(default="gpt-3.5-turbo")
+    model: Union[str, OllamaModel] = Field(default="gpt-3.5-turbo")
     temperature: float = Field(default=0.0)
     max_tokens: int = Field(default=128)
     debug: bool = Field(default_factory=lambda: False)
@@ -285,6 +291,7 @@ class ScrapeStatusReq(BaseModel):
     id: str
     namespace: str
     namespace_list: Optional[List[str]] | None = None
+    engine: Engine
 
 
 class ScrapeStatusResponse(BaseModel):

tilellm/shared/utility.py

@@ -1,4 +1,3 @@
-import os
 from functools import wraps
 
 import logging
@@ -7,10 +6,12 @@
 import langchain_aws
 from langchain_community.callbacks.openai_info import OpenAICallbackHandler
 from langchain_community.embeddings import CohereEmbeddings #, GooglePalmEmbeddings
+from langchain_experimental.llms.ollama_functions import OllamaFunctions
 from langchain_huggingface import HuggingFaceEmbeddings
+from langchain_ollama import ChatOllama
 from langchain_voyageai import VoyageAIEmbeddings
 from langchain_openai import OpenAIEmbeddings
-
+from openai import base_url
 
 from tilellm.shared import const
 
@@ -92,6 +93,14 @@ async def wrapper(self, item, *args, **kwargs):
 
                                                       )
                 dimension = 1024
+            elif item.embedding == "ollama":
+                from langchain_ollama.embeddings import OllamaEmbeddings
+                embedding_obj = OllamaEmbeddings(model=item.model.name,
+                                                 base_url=item.model.url
+                                                )
+                dimension = item.model.dimension
+                # dimension for llama3.2 3072
+
             else:
                 embedding_obj = OpenAIEmbeddings(api_key=item.gptkey, model=item.embedding)
                 dimension = 1536
@@ -138,6 +147,11 @@ async def wrapper(question, *args, **kwargs):
                                                 max_tokens=question.max_tokens,
                                                 convert_system_message_to_human=True)
 
+        elif question.llm == "ollama":
+            chat_model = ChatOllama(model = question.model.name,
+                                    temperature=question.temperature,
+                                    um_predict = question.max_tokens,
+                                    base_url=question.model.url)
         elif question.llm == "groq":
             chat_model = ChatGroq(api_key=question.llm_key,
                                   model=question.model,
@@ -263,8 +277,29 @@ async def wrapper(question, *args, **kwargs):
                                   model=question.model,
                                   temperature=question.temperature,
                                   max_tokens=question.max_tokens
+
+
                                   )
 
+        elif question.llm == "ollama":
+            callback_handler = TiledeskAICallbackHandler()
+
+            from langchain_ollama.embeddings import OllamaEmbeddings
+            llm_embeddings = OllamaEmbeddings(model=question.model.name,
+                                             base_url=question.model.url
+                                             )
+            dimension = question.model.dimension
+
+            llm = ChatOllama(model=question.model.name,
+                             temperature=question.temperature,
+                             num_predict=question.max_tokens,
+                             base_url=question.model.url,
+                             format="json",
+                             callback_handler=[callback_handler]
+                             )
+
+
+
         elif question.llm == "aws":
             import os
 

tilellm/store/pinecone/pinecone_repository_base.py

@@ -138,7 +138,7 @@ async def get_pc_ids_namespace(engine: Engine, metadata_id: str, namespace: str)
                                                     metadata_source=obj.get('metadata').get('source'),
                                                     metadata_type=obj.get('metadata').get('type'),
                                                     date=obj.get('metadata').get('date', 'Date not defined'),
-                                                    text=obj.get('metadata').get(const.PINECONE_TEXT_KEY)
+                                                    text=obj.get('metadata').get(engine.text_key)
                                                     # su pod content, su Serverless text
                                                     )
                               )
@@ -373,7 +373,7 @@ async def get_pc_sources_namespace(engine: Engine, source: str, namespace: str)
                                                     metadata_source=obj.get('metadata').get('source'),
                                                     metadata_type=obj.get('metadata').get('type'),
                                                     date=obj.get('metadata').get('date', 'Date not defined'),
-                                                    text=obj.get('metadata').get(const.PINECONE_TEXT_KEY)
+                                                    text=obj.get('metadata').get(engine.text_key)
                                                     # su pod content, su Serverless text
                                                     )
                               )