New SDK structure

.github/workflows/publish.yaml

@@ -2,6 +2,7 @@ name: Publish to PyPI.org
 on:
   push:
     tags: ["v*"]
+
 jobs:
   pypi:
     runs-on: ubuntu-latest
@@ -12,8 +13,13 @@ jobs:
         uses: actions/checkout@v3
         with:
           fetch-depth: 0
-      - run: python3 -m pip install --upgrade build && python3 -m build
-      - name: Publish package
-        uses: pypa/gh-action-pypi-publish@release/v1
-        with:
-          password: ${{ secrets.PYPI_TOKEN }}
+
+      - name: Set up Python
+        run: |
+          python3 -m pip install --upgrade build
+          python3 -m build
+
+     - name: Publish package
+       uses: pypa/gh-action-pypi-publish@release/v1
+       with:
+         password: ${{ secrets.PYPI_TOKEN }}

.gitignore

@@ -1,11 +1,23 @@
-*.py[cod]
 __pycache__/
+build/
+dist/
+*.egg-info/
+.pytest_cache/
 
-# build
-/*.egg*/
-/prem/_dist_ver.py
-/build/
-/dist/
+# pyenv
+.python-version
 
-venv/
-docs/build
+# Environments
+.env
+.venv
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# JetBrains
+.idea/
+
+/coverage.xml
+/.coverage

README.md

@@ -1,117 +1,97 @@
-<div align="center">
-  <h1 align="center">🚀 Prem Python SDK</h1>
-  <p align="center">The Prem Python SDK is a Python library for interacting with the <a href="https://github.com/premAI-io/prem-saas">Prem  API</a></p>
-
-[![PyPI version](https://img.shields.io/pypi/v/premai.svg)](https://pypi.org/project/premai/)
-[![GitHub contributors](https://img.shields.io/github/contributors/premAI-io/prem-python-sdk.svg)](https://github.com/premAI-io/prem-python-sdk/graphs/contributors)
-[![GitHub last commit](https://img.shields.io/github/last-commit/premAI-io/prem-python-sdk.svg)](https://github.com/premAI-io/prem-python-sdk/commits/master)
-[![GitHub top language](https://img.shields.io/github/languages/top/premAI-io/prem-python-sdk.svg)](https://github.com/premAI-io/prem-python-sdk)
-[![GitHub issues](https://img.shields.io/github/issues/premAI-io/prem-python-sdk.svg)](https://github.com/premAI-io/prem-python-sdk/issues)
-</div>
-
-
-<details>
-    <summary>Table of Contents</summary>
-    <ol>
-        <li><a href="#installation">Installation</a></li>
-        <li><a href="#usage">Usage</a></li>
-        <ol>
-            <li><a href="#getting-started">Getting Started</a></li>
-            <li><a href="#completions">Completions</a></li>
-            <li><a href="#embeddings">Embeddings</a></li>
-            <li><a href="#data-points">DataPoints</a></li>
-        </ol>
-    </ol>
-</details>
-
-## Installation
-
-### From Source
-
-1. Clone the Prem Python SDK repository:
-
-   ```bash
-   git clone https://github.com/premAI-io/prem-python-sdk.git
-   ``````
-
-2. Install the SDK
-    ```bash
-    cd prem-python-sdk
-    python -m venv venv
-    source venv/bin/activate
-    pip install .
-    ```
-### From PyPI
-You can also install the Prem Python SDK directly from PyPI.
+# Installation
+
+## From Source
+
+1\. Clone the Prem Python SDK repository:
+```bash
+git clone https://github.com/premAI-io/prem-python-sdk.git
+```
 
+2\. Install the SDK
 ```bash
+cd prem-python-sdk
 python -m venv venv
 source venv/bin/activate
+pip install .
+```
+
+## From PyPI
+You can also install the Prem Python SDK directly from PyPI.
+
+```bash
 pip install premai
 ```
-## Usage
-### Getting Started
+
+# Usage
+## Getting Started
 To use the Prem Python SDK, you need to obtain an API key from the Prem platform. You can then create a `Prem` instance to make requests to the API.
 
 ```python
-from prem import Prem
+from premai import Prem
 
 api_key = "YOUR_API_KEY"
-base_url = "https://api.prem.com"  # Update with the base URL of the Prem API
-
-client = Prem(api_key=api_key, base_url=base_url)
+client = Prem(api_key=api_key)
 ```
 
-### Completions
-The `completions` module allows you to generate completions based on user input. Here's an example:
+## Chat completion
+The `chat.completions` module allows you to generate completions based on user input. Here's an example:
 
 ```python
 messages = [
     {"role": "system", "content": "You are a helpful assistant."},
     {"role": "user", "content": "Who won the world series in 2020?"},
 ]
 model = "gpt-3.5-turbo"
+project_id = YOUR_PROJECT_ID
 
 # Create completion
-response = client.completions.create(project_id=1, messages=messages, model=model, stream=False)
-print(response)
+response = client.chat.completions.create(
+  project_id=project_id,
+  messages=messages, 
+  model=model
+)
+
+print(response.choices)
 ```
 
-### Embeddings
+## Embeddings
 The `embeddings` module enables you to create embeddings for given input. Example:
 
 ```python
 input_text = "What is a transformer?"
 model = "text-embedding-ada-002"
+project_id = YOUR_PROJECT_ID
 
 # Create embeddings
-response = client.embeddings.create(project_id=1, input=input_text, model=model)
-print(response)
+response = client.embeddings.create(project_id=project_id, input=input_text, model=model)
+
+print(response.data)
 ```
 
-### Data Points
+## Data Points
 The `datapoints` module allows you to manage data points, including creating, updating, retrieving, and deleting. Example:
 ```python
 input_text = "What is a transformer?"
 output_text = "A transformer is a deep learning model that uses self-attention."
+project_id = YOUR_PROJECT_ID
 
 # Create 10 data points
 for _ in range(10):
-    data_point = client.datapoints.create(project_id=1, input=input_text, output=output_text, positive=True)
+    data_point = client.datapoints.create(project=project_id, input=input_text, output=output_text, positive=True)
 
 # Update the last data point
-patched_data_point = client.datapoints.update(datapoint_id=data_point.id, data={"positive": False})
+patched_data_point = client.datapoints.patch(id=data_point.id, positive=False)
 
 # Retrieve the updated data point
-print(client.datapoints.retrieve(datapoint_id=data_point.id))
+print(client.datapoints.retrieve(id=data_point.id))
 
 # Delete the updated data point
-client.datapoints.delete(datapoint_id=data_point.id)
+client.datapoints.delete(id=data_point.id)
 
 # List all data points
-datapoints = client.datapoints.list(project_id=1)
+datapoints = client.datapoints.list(project=project_id)
 print("Total number of datapoints:", len(datapoints))
 for datapoint in datapoints:
     print("Deleted data point with ID:", datapoint.id)
-    client.datapoints.delete(datapoint_id=datapoint.id)
-```
+    client.datapoints.delete(id=datapoint.id)
+```