BerriAI/litellm · error · HTTPException

Unable to find Milvus vector store index registry or vector

Error message

Unable to find Milvus vector store index registry or vector store registry.

What it means

Server-side guard in the Milvus /vectors pass-through: litellm.vector_store_index_registry or litellm.vector_store_registry is None on the proxy server, meaning managed vector store support was never initialized (registries not loaded at startup). This is an internal configuration error, not caused by the request payload.

Source

Thrown at litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py:464

            status_code=500,
            detail="Unable to find Milvus vector store config.",
        )

    # check if managed vector store index is used
    request_body: Final = await get_request_body(request)

    # check collectionName
    collection_name: Final = cast(str | None, request_body.get("collectionName"))
    extra_headers = {}
    base_target_url: str | None = None
    if not collection_name:
        raise HTTPException(
            status_code=400,
            detail=f"Collection name is required. Got {request_body}",
        )

    if not litellm.vector_store_index_registry or not litellm.vector_store_registry:
        raise HTTPException(
            status_code=500,
            detail="Unable to find Milvus vector store index registry or vector store registry.",
        )

    # check if vector store index
    is_vector_store_index: Final = litellm.vector_store_index_registry.is_vector_store_index(
        vector_store_index_name=collection_name
    )

    if not is_vector_store_index:
        raise HTTPException(
            status_code=400,
            detail=f"Collection {collection_name} is not a litellm managed vector store index. Only litellm managed vector store indexes are supported.",
        )

    is_allowed_to_call_vector_store_endpoint(
        index_name=collection_name,
        provider=LlmProviders.MILVUS,

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Ensure the proxy was started with a vector store registry and vector store index registry configured (litellm.vector_store_registry / vector_store_index_registry).
2. Register the Milvus vector store and its index in config.yaml before issuing managed vector store requests.

When it happens

Trigger: Thrown at litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py:464 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/207c6ce6e5aabb2b. Report an issue: GitHub.