A JupyterLab extension that provides LiteLLM model abstraction
Project description
jupyter_ai_litellm
A JupyterLab extension that provides LiteLLM model abstraction for Jupyter AI
This extension is composed of a Python package named jupyter_ai_litellm that exposes LiteLLM's extensive catalog of language models through a standardized API.
Features
- Comprehensive Model Support: Access to hundreds of chat and embedding models from various providers (OpenAI, Anthropic, Google, Cohere, Azure, AWS, and more) through LiteLLM's unified interface
- Standardized API: Consistent REST API endpoints for model discovery and interaction
- Easy Integration: Seamlessly integrates with Jupyter AI to expand available model options
API Endpoints
Chat Models
GET /api/ai/models/chat- Returns a list of all available chat models
The response includes model IDs in LiteLLM format (e.g., openai/gpt-4, anthropic/claude-3-sonnet, etc.)
Model Lists
The extension automatically discovers and categorizes models from LiteLLM's supported providers:
- Chat models for conversational AI
- Embedding models for vector representations
Requirements
- JupyterLab >= 4.0.0
Install
To install the extension, execute:
pip install jupyter_ai_litellm
Uninstall
To remove the extension, execute:
pip uninstall jupyter_ai_litellm
Troubleshoot
If you are seeing the frontend extension, but it is not working, check that the server extension is enabled:
jupyter server extension list
Contributing
Development install
# Clone the repo to your local environment
# Change directory to the jupyter_ai_litellm directory
# Install package in development mode
pip install -e ".[test]"
# Server extension must be manually installed in develop mode
jupyter server extension enable jupyter_ai_litellm
Development uninstall
# Server extension must be manually disabled in develop mode
jupyter server extension disable jupyter_ai_litellm
pip uninstall jupyter_ai_litellm
Testing the extension
Server tests
This extension is using Pytest for Python code testing.
Install test dependencies (needed only once):
pip install -e ".[test]"
To execute them, run:
pytest -vv -r ap --cov jupyter_ai_litellm
Packaging the extension
See RELEASE
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file jupyter_ai_litellm-0.0.1.tar.gz.
File metadata
- Download URL: jupyter_ai_litellm-0.0.1.tar.gz
- Upload date:
- Size: 9.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.2.0 CPython/3.12.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
38d103552f3bb637e18509b2f6608b545bb3b4d45064a8558e4efedfcef5b104
|
|
| MD5 |
e8c2dc91f24e25ae66edb623fadb4786
|
|
| BLAKE2b-256 |
b39e5da78f1f72056d9bb14e97938382025657b83523f432fab396b844e6f073
|
File details
Details for the file jupyter_ai_litellm-0.0.1-py3-none-any.whl.
File metadata
- Download URL: jupyter_ai_litellm-0.0.1-py3-none-any.whl
- Upload date:
- Size: 7.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.2.0 CPython/3.12.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
17008f0351211bf07f4aa41ad2d47e34d63d02e300ec71fdc14b2615dd311fb4
|
|
| MD5 |
24305eb0b45cd360224401a1c33db37c
|
|
| BLAKE2b-256 |
d7088e50be1b37a38e0147670630f78095e69a1d0bdaceb22b23cdeb41445756
|