[Roadmap]: Improved 'name' support for non-OpenAI clients #3333
Labels
group chat/teams
group-chat-related issues
models
Pertains to using alternate, non-GPT, models (e.g., local models, llama, etc.)
roadmap
Issues related to roadmap of AutoGen
With the increasing number of new client classes for non-OpenAI inference (Anthropic, Mistral, Cohere, Groq, Together.AI, etc.) we need to continue to cater for these throughout the framework. All these client classes remove the
name
field for inference and this can have an affect on group chats or any interaction that refers to their 'name'.Listed PRs can help rectify or overcome this issue.
I'll also add the Ollama and Amazon Bedrock client class PRs as optional, as it would be good to have them but the aren't critical to solve the issue in the roadmap. Mistral have updated their client and there's a PR to update our client class to support it.
If you have others, please feel free to add them.
Aiming for next release, 0.2.35
Better
name
support and general non-OpenAI supportThe text was updated successfully, but these errors were encountered: