Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add LiteLLM Connector #4748

Open
flefevre opened this issue Nov 21, 2024 · 2 comments
Open

Add LiteLLM Connector #4748

flefevre opened this issue Nov 21, 2024 · 2 comments
Labels
enhancement New feature or request

Comments

@flefevre
Copy link

Feature Request

I would like to suggest adding a connector for LiteLLM to LangFlow.
LiteLLM is a lightweight and fast open-source library for integrating various LLM providers with a simplified interface. Including this connector in LangFlow would offer several benefits:

Broader compatibility: Support for multiple LLM providers through LiteLLM's unified interface.

Improved usability: Simplifies the process of integrating and switching between LLMs.

Community adoption: LiteLLM has an active and growing user base, making it a valuable addition to LangFlow.

Proposed Solution

  1. Create a new connector module in LangFlow that interfaces with LiteLLM.
  2. Ensure compatibility with key LiteLLM features, such as provider switching and request optimization.
  3. Provide documentation and examples for users to set up and use the LiteLLM connector.

This feature would make LangFlow more versatile and appealing to users seeking streamlined LLM integration

Motivation

This enhancement aligns with LangFlow's goal of being a versatile platform for LLM integration. The inclusion of LiteLLM would:

Solve the challenge of managing multiple LLM providers with a unified interface.

Reduce friction for users who often switch between providers or experiment with different LLMs.

Leverage LiteLLM’s active community for broader adoption and support.

Thank you for considering this proposal!

Your Contribution

I could test asap this component and share a basic flow.

@flefevre
Copy link
Author

By adding Litellm, you will also unleash the power of Vllm which is as famous as Ollama
https://github.com/vllm-project/vllm

LiteLLM is fully openai ai compatible and so the work to be done sould be really easy by duplicating a component such as Ollama?

@flefevre
Copy link
Author

Going deeper I have found this : #3401
So the code is here...
Could you reactivate such LiteLLM feature?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

1 participant