BerriAI/litellm · error · Exception

Provider config not found for Azure AI

Error message

Provider config not found for Azure AI

What it means

Raised in the Azure AI vector-store branch when ProviderConfigManager returns no vector-store config for the provider — meaning the deployment lacked the provider-specific settings (api key/base) needed to call the vector store index endpoint.

Source

Thrown at litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py:1375

                # Non-streaming response
                result = cast(httpx.Response, result)
                content = await result.aread()
                return Response(
                    content=content,
                    status_code=result.status_code,
                    headers=HttpPassThroughEndpointHelpers.get_response_headers(
                        headers=result.headers,
                        custom_headers=None,
                    ),
                )
            elif is_vector_store_index:
                # get the api key from the provider config
                provider_config = ProviderConfigManager.get_provider_vector_stores_config(
                    provider=litellm.LlmProviders.AZURE_AI
                )
                if provider_config is None:
                    raise Exception("Provider config not found for Azure AI")
                # get the index from registry
                if litellm.vector_store_registry is None:
                    raise Exception("Vector store registry not found")

                is_allowed_to_call_vector_store_endpoint(
                    index_name=part,
                    provider=litellm.LlmProviders.AZURE_AI,
                    request=request,
                    user_api_key_dict=user_api_key_dict,
                )
                # get the vector store name from index registry
                index_object = (
                    (litellm.vector_store_index_registry.get_vector_store_index_by_name(vector_store_index_name=part))
                    if litellm.vector_store_index_registry is not None
                    else None
                )
                if index_object is None:
                    raise Exception(f"Vector store index not found for {part}")

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Register an Azure AI provider configuration in the proxy config (azure_ai provider section or via the UI).
2. Verify the provider name in the request matches a configured Azure AI provider.

When it happens

Trigger: Thrown at litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py:1375 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/848971f682908dba. Report an issue: GitHub.