BerriAI/litellm · error · Exception

Vector store not found for {vector_store_name}

Error message

Vector store not found for {vector_store_name}

What it means

The vector store referenced by the resolved index object (index_object.litellm_params.vector_store_name) is absent from litellm.vector_store_registry, indicating an index definition pointing at a vector store that was never registered or has been removed. Thrown as a bare Exception from the Milvus pass-through handler.

Source

Thrown at litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py:508

        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 {collection_name}")

    vector_store_name: Final = index_object.litellm_params.vector_store_name
    vector_store_index: Final = index_object.litellm_params.vector_store_index

    request_body["collectionName"] = vector_store_index

    # Update the request object with the modified collection name
    _safe_set_request_parsed_body(request, request_body)

    vector_store: Final = 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: Final = provider_config.get_auth_credentials(litellm_params=litellm_params)

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

    litellm_params = vector_store.get("litellm_params") or {}

    base_target_url = provider_config.get_complete_url(
        api_base=litellm_params.get("api_base"), litellm_params=litellm_params
    )

    if base_target_url is None:
        raise Exception(f"api_base not found in vector store configuration for {vector_store_name}")

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Register the vector store (with vector_store_name) in config.yaml or via the management API.
2. Verify the vector_store_name in the request matches a configured entry exactly.

When it happens

Trigger: Thrown at litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py:508 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/94aa2b06f1df4a9d. Report an issue: GitHub.