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

[Feature Request]: Integrate more model calling to AutoGen through API #2841

Open
6 tasks done
yiranwu0 opened this issue May 31, 2024 · 4 comments
Open
6 tasks done
Assignees
Labels
0.2 Issues which are related to the pre 0.4 codebase models Pertains to using alternate, non-GPT, models (e.g., local models, llama, etc.) needs-triage roadmap Issues related to roadmap of AutoGen

Comments

@yiranwu0
Copy link
Collaborator

yiranwu0 commented May 31, 2024

Is your feature request related to a problem? Please describe.

Besides OpenAI and Gemini Integration, there are existing other models that are available through API calling. It would be helpful if AutoGen could provide an uniform interface for calling different models.
Specifically, the following models could be added:

Describe the solution you'd like

No response

Additional context

No response

Tasks

Preview Give feedback
  1. davorrunje
  2. bug
  3. models tool-usage
    marklysze yiranwu0
  4. models tool-usage
    Hk669
  5. models
    marklysze
@yiranwu0 yiranwu0 self-assigned this May 31, 2024
@yiranwu0 yiranwu0 added the models Pertains to using alternate, non-GPT, models (e.g., local models, llama, etc.) label Jun 11, 2024
@Hk669
Copy link
Contributor

Hk669 commented Jun 12, 2024

@marklysze as mentioned yesterday, can i know if you are working on the anthropic? ive seen the TogetherAI draft PR #2919. i can work on anthropic client if it is not implemented already. thanks

@marklysze
Copy link
Collaborator

marklysze commented Jun 12, 2024

@marklysze as mentioned yesterday, can i know if you are working on the anthropic? ive seen the TogetherAI draft PR #2919. i can work on anthropic client if it is not implemented already. thanks

Hi @Hk669, thanks for checking, sorry it is the Together AI client I was working on. I'm not working on the Anthropic client but there is a notebook with a sample Anthropic custom client class in the non-openai topic in documentation that could help with the new class. Happy to test if you can work on the class.

@Hk669
Copy link
Contributor

Hk669 commented Jun 12, 2024

@marklysze as mentioned yesterday, can i know if you are working on the anthropic? ive seen the TogetherAI draft PR #2919. i can work on anthropic client if it is not implemented already. thanks

Hi @Hk669, thanks for checking, sorry it is the Together AI client I was working on. I'm not working on the Anthropic client but there is a notebook witt a sample Anthropic custom client class in the non-openai topic in documentation that could help with the new class. Happy to test if you can work on the class.

Sure, thanks for the clarification.

@yiranwu0 yiranwu0 added the roadmap Issues related to roadmap of AutoGen label Jun 14, 2024
@Hk669
Copy link
Contributor

Hk669 commented Jul 20, 2024

@yiranwu0 , i believe we can close this issue.

@rysweet rysweet added 0.2 Issues which are related to the pre 0.4 codebase needs-triage labels Oct 2, 2024
@fniedtner fniedtner removed the feature label Oct 24, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
0.2 Issues which are related to the pre 0.4 codebase models Pertains to using alternate, non-GPT, models (e.g., local models, llama, etc.) needs-triage roadmap Issues related to roadmap of AutoGen
Projects
None yet
Development

No branches or pull requests

5 participants