You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Is your feature request related to a problem? Please describe.
Currently, there's no easy way to use GitHub's inference endpoint with automatic fallback to Azure in the autogen library. This makes it difficult for users who want to leverage GitHub's LLM capabilities while ensuring high availability through Azure fallback.
We need a seamless way to integrate GitHub's LLM API with autogen, including rate limiting handling and automatic fallback to Azure when needed.
Describe the solution you'd like
Implement a new GithubLLM class in autogen that supports:
Using GitHub's inference endpoint as the primary LLM provider
Automatic fallback to Azure when rate limits are reached
Configurable system prompts and model selection
Compatibility with autogen's existing API structure
The solution should include:
A GithubClient class that handles API calls to GitHub and Azure
A GithubWrapper class that integrates with autogen's existing structure
Support for both single-turn and multi-turn conversations
Proper error handling and logging
Easy configuration through environment variables
Additional context
This feature would be particularly useful for developers who have access to GitHub's LLM API and want to integrate it into their autogen workflows while maintaining the option to fall back to Azure for reliability.
Why are these changes needed?
This PR introduces a new GithubLLM class to autogen, allowing users to leverage GitHub's inference endpoint with automatic fallback to Azure. It provides a seamless way to use GitHub's LLM capabilities within the autogen ecosystem, handling rate limits and ensuring high availability through Azure fallback.
Is your feature request related to a problem? Please describe.
Currently, there's no easy way to use GitHub's inference endpoint with automatic fallback to Azure in the autogen library. This makes it difficult for users who want to leverage GitHub's LLM capabilities while ensuring high availability through Azure fallback.
We need a seamless way to integrate GitHub's LLM API with autogen, including rate limiting handling and automatic fallback to Azure when needed.
Describe the solution you'd like
Implement a new GithubLLM class in autogen that supports:
Using GitHub's inference endpoint as the primary LLM provider
Automatic fallback to Azure when rate limits are reached
Configurable system prompts and model selection
Compatibility with autogen's existing API structure
The solution should include:
A GithubClient class that handles API calls to GitHub and Azure
A GithubWrapper class that integrates with autogen's existing structure
Support for both single-turn and multi-turn conversations
Proper error handling and logging
Easy configuration through environment variables
Additional context
This feature would be particularly useful for developers who have access to GitHub's LLM API and want to integrate it into their autogen workflows while maintaining the option to fall back to Azure for reliability.
Why are these changes needed?
This PR introduces a new GithubLLM class to autogen, allowing users to leverage GitHub's inference endpoint with automatic fallback to Azure. It provides a seamless way to use GitHub's LLM capabilities within the autogen ecosystem, handling rate limits and ensuring high availability through Azure fallback.
Tasks
Tests
Refs
The text was updated successfully, but these errors were encountered: