Claude support about autogen HOT 7 OPEN

This is great actually, I'd say this is a clean way to offer support for multiple models via litellm in autogen.
We can guide users to do this by updating the documentation to show how to:

• Install and run an OAI compliant endpoint (with support for 100s of models) via litellm
• Show how AutoGen can consume these endpoints seamlessly via the oai_config_list

from autogen import AssistantAgent, UserProxyAgent, oai
config_list=[
    {
        "model": "palm/text-bison",
        "api_base": "http://localhost:8000/v1",  #litellm compatible endpoint
        "api_type": "open_ai",
        "api_key": "NULL", # just a placeholder
    }
]

response = oai.Completion.create(config_list=config_list, prompt="Hi")
print(response) # works fine

assistant = AssistantAgent("assistant")
user_proxy = UserProxyAgent("user_proxy")
user_proxy.initiate_chat(assistant, message="Plot a chart of META and TESLA stock price change YTD.", config_list=config_list)
# fails with the error: openai.error.AuthenticationError: No API key provided.

There is a chance I may have missed something here, happy to get your thoughts

from autogen.

Hey @victordibia thank you for this incredible tutorial. I added it to our docs and gave you credit for it:
https://docs.litellm.ai/docs/proxy_server#tutorial-use-with-aiderautogencontinue-dev

from autogen.

@victordibia thanks for taking a look at litelm

Yes the endpoint is OpenAI compatible

What do you want to use it for ? (I want to make sure we can support it well)

from autogen.

related to #46

from autogen.

@LeoLjl

from autogen.

made a PR for this: #95

from autogen.

Quick question @ishaan-jaff.
I have taken a look at litelllm and the list of models supported in the python api is very impressive!

I also see that you can serve any model over a web endpoint.

litellm --model <model_name>

Can you confirm if this end point is OpenAI api compatible, similar to something like what fastchat //vllm provides?

This could be a clean way broaden the list of supported models.

from autogen.