[fix] use openai model provider as default #644

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.

Sign up for GitHub

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

Jump to bottom

Open

jneeee wants to merge 1 commit into openai:main from jneeee:fix_provider

jneeee commented May 3, 2025

This commit fix the error:

When set default openai client but not use litellm provider, would got unknown prefix error.

Another reason is many of the endpoints are already compatible with the OpenAI SDK/Openai api, I want use them without install litellm.

client = AsyncOpenAI(
    base_url="https://integrate.api.nvidia.com/v1",
    api_key=os.getenv("NV_API_KEY"),
)
set_default_openai_client(client=client, use_for_tracing=False)
...
  agent = Agent(
      name="Assistant",
      instructions="You only respond in haikus.",
      model="meta/llama-4-scout-17b-16e-instruct",
      tools=[get_weather],
  )

Got Error:

openai-agents-python/src/agents/models/multi_provider.py", line 117, in _create_fallback_provider
    raise UserError(f"Unknown prefix: {prefix}")
agents.exceptions.UserError: Unknown prefix: meta


          [fix] use openai model provider as default

ac98fc1

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet