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
Metadata
Release files for jupyter-ai-litellm 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| jupyter_ai_litellm-0.1.0.tar.gz | 10.2 kB | Without provenance | Details for jupyter_ai_litellm-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| jupyter_ai_litellm-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for jupyter_ai_litellm-0.1.0-py3-none-any.whl |
Total release size: 17.9 kB
Release files / jupyter_ai_litellm-0.1.0.tar.gz
| Download URL | jupyter_ai_litellm-0.1.0.tar.gz |
|---|---|
| Size | 10.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
7a7ef61b439ccdfc179923dd4f8cc8437549ad6ee329214d9cb64f1a252a6226
|
|
BLAKE2b-256 checksum How to use checksums |
2ddb55daa7646cb9cc388fe8f7d9f6b1eba54158254c98502d00edbc62e09245
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.12.14
|
Release files / jupyter_ai_litellm-0.1.0-py3-none-any.whl
| Download URL | jupyter_ai_litellm-0.1.0-py3-none-any.whl |
|---|---|
| Size | 7.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
c3e6fe718f3ce60452cd6b047b86d61b904bac39c075d107d9b8dedd9618a1ad
|
|
BLAKE2b-256 checksum How to use checksums |
2867317a6b20e94008e79f2043d85e6bed01e32bad333931688c44b8c4136e53
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.12.14
|
Security for jupyter-ai-litellm 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.