BerriAI/litellm · error · HTTPException

ingest_options must contain 'vector_store' configuration

Error message

ingest_options must contain 'vector_store' configuration

What it means

RAG ingest validation: ingest_options has no usable 'vector_store' configuration (missing or not a dict), so the handler cannot create or target a vector store for ingestion; rejected with 400.

Source

Thrown at litellm/proxy/rag_endpoints/endpoints.py:361

            if filename and content_b64:
                try:
                    file_content = base64.b64decode(content_b64)
                    file_data = (filename, file_content, content_type)
                except Exception as e:
                    raise HTTPException(
                        status_code=400,
                        detail={"error": f"Invalid base64 content: {e}"},
                    )

    # Validate
    if file_data is None and file_url is None and file_id is None:
        raise HTTPException(
            status_code=400,
            detail={"error": "Must provide file, file_url, or file_id"},
        )

    if "vector_store" not in ingest_options:
        raise HTTPException(
            status_code=400,
            detail={"error": "ingest_options must contain 'vector_store' configuration"},
        )

    # Credential fields must come from server configuration, not user requests.
    # Accepting user-supplied credentials (e.g. vertex_credentials with
    # type=external_account + credential_source.file=/proc/1/environ) allows
    # any authenticated user to exfiltrate host secrets via SSRF through
    # google-auth's identity_pool credential refresh.
    # api_base is also blocked: a user-controlled base URL causes the server
    # to send its configured provider credentials to an attacker endpoint.
    _BLOCKED_VECTOR_STORE_CREDENTIAL_PARAMS: Final = {
        "vertex_credentials",
        "vertex_ai_credentials",
        "aws_access_key_id",
        "aws_secret_access_key",
        "aws_session_token",
        "aws_web_identity_token",

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Include a vector_store object inside ingest_options with the target vector store configuration or ID.

When it happens

Trigger: Thrown at litellm/proxy/rag_endpoints/endpoints.py:361 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/a2dddbbb0631b550. Report an issue: GitHub.