BerriAI/litellm · error · HTTPException

Managed vector stores not configured. Please ensure the prox

Error message

Managed vector stores not configured. Please ensure the proxy is initialized with database support.

What it means

The request asked for managed multi-model vector stores (target_model_names present) but the 'managed_vector_stores' proxy hook is not registered, which happens when the proxy runs without database support. Managed vector stores require DB-backed initialization; either drop target_model_names or start the proxy with a database.

Source

Thrown at litellm/proxy/vector_store_endpoints/endpoints.py:226

    # Check for target_model_names parameter
    target_model_names: Final = data.pop("target_model_names", None)

    if target_model_names:
        # Use managed vector stores for multi-model support
        if isinstance(target_model_names, str):
            target_model_names_list = [m.strip() for m in target_model_names.split(",")]
        elif isinstance(target_model_names, list):
            target_model_names_list = target_model_names
        else:
            raise HTTPException(
                status_code=400,
                detail="target_model_names must be a comma-separated string or list of model names",
            )

        # Get managed vector stores hook
        managed_vector_stores: Final[Any] = proxy_logging_obj.get_proxy_hook("managed_vector_stores")
        if managed_vector_stores is None:
            raise HTTPException(
                status_code=500,
                detail="Managed vector stores not configured. Please ensure the proxy is initialized with database support.",
            )

        if llm_router is None:
            raise HTTPException(
                status_code=500,
                detail="LLM Router not initialized. Ensure models are added to proxy.",
            )

        # Create vector store across multiple models
        response: Final = await managed_vector_stores.acreate_vector_store(
            create_request=data,
            llm_router=llm_router,
            target_model_names_list=target_model_names_list,
            litellm_parent_otel_span=user_api_key_dict.parent_otel_span,
            user_api_key_dict=user_api_key_dict,
        )

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Initialize the proxy with a database (set DATABASE_URL) so managed vector stores are configured.

When it happens

Trigger: Thrown at litellm/proxy/vector_store_endpoints/endpoints.py:226 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/87e4a70d7c01ced2. Report an issue: GitHub.