BerriAI/litellm · error · Exception

API base not found for {part}

Error message

API base not found for {part}

What it means

Raised while resolving a pass-through target for a provider segment: the vector store configuration for that provider/part yielded no api_base, so the handler cannot build the upstream URL. Indicates incomplete provider or vector store configuration rather than a bad request.

Source

Thrown at litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py:1413

                vector_store_name = index_object.litellm_params.vector_store_name

                vector_store = litellm.vector_store_registry.get_litellm_managed_vector_store_from_registry_by_name(
                    vector_store_name=vector_store_name
                )
                if vector_store is None:
                    raise Exception(f"Vector store not found for {vector_store_name}")
                await assert_user_can_access_vector_store(
                    vector_store=vector_store,
                    user_api_key_dict=user_api_key_dict,
                )
                litellm_params = vector_store.get("litellm_params") or {}
                auth_credentials = provider_config.get_auth_credentials(litellm_params=litellm_params)

                extra_headers = auth_credentials.get("headers") or {}

                base_target_url = litellm_params.get("api_base")
                if base_target_url is None:
                    raise Exception(f"API base not found for {part}")
                return await BaseOpenAIPassThroughHandler._base_openai_pass_through_handler(
                    endpoint=endpoint,
                    request=request,
                    fastapi_response=fastapi_response,
                    user_api_key_dict=user_api_key_dict,
                    base_target_url=base_target_url,
                    api_key=None,
                    custom_llm_provider=litellm.LlmProviders.AZURE_AI,
                    extra_headers=cast(dict, extra_headers),
                )

    base_target_url = get_secret_str(secret_name="AZURE_API_BASE")
    if base_target_url is None:
        raise Exception("Required 'AZURE_API_BASE' in environment to make pass-through calls to Azure.")
    # Add or update query parameters
    azure_api_key: Final = passthrough_endpoint_router.get_credentials(
        custom_llm_provider=litellm.LlmProviders.AZURE.value,
        region_name=None,

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Set api_base for the referenced vector store/index in config.yaml.
2. Ensure the name in the path resolves to a configured vector store with credentials.

When it happens

Trigger: Thrown at litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py:1413 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/f9aa73d57e6eac17. Report an issue: GitHub.