BerriAI/litellm · error · HTTPException

'{field}' cannot be set in ingest_options.vector_store. Cred

Error message

'{field}' cannot be set in ingest_options.vector_store. Credentials must be configured server-side.

What it means

Security guard in RAG ingest: a credential-style field (api_key, api_base, aws_*, azure tokens, etc.) was found in ingest_options.vector_store. Client requests may not supply provider credentials; they must be configured server-side, so the request is rejected naming the offending field.

Source

Thrown at litellm/proxy/rag_endpoints/endpoints.py:393

        "vertex_ai_credentials",
        "aws_access_key_id",
        "aws_secret_access_key",
        "aws_session_token",
        "aws_web_identity_token",
        "aws_role_name",
        "aws_session_name",
        "aws_profile_name",
        "aws_sts_endpoint",
        "aws_external_id",
        "azure_ad_token",
        "api_key",
        "api_base",
    }
    vector_store_opts: Final[object] = ingest_options.get("vector_store", {})
    if isinstance(vector_store_opts, dict):
        for field in _BLOCKED_VECTOR_STORE_CREDENTIAL_PARAMS:
            if field in vector_store_opts:
                raise HTTPException(
                    status_code=400,
                    detail={
                        "error": f"'{field}' cannot be set in ingest_options.vector_store. "
                        "Credentials must be configured server-side."
                    },
                )

    return ingest_options, file_data, file_url, file_id


@router.post(
    "/v1/rag/ingest",
    dependencies=[Depends(user_api_key_auth)],
    response_class=ORJSONResponse,
    tags=["rag"],
)
@router.post(
    "/rag/ingest",

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Remove credential fields from ingest_options.vector_store; configure vector store credentials server-side in config.yaml.

When it happens

Trigger: Thrown at litellm/proxy/rag_endpoints/endpoints.py:393 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/242cd3d39eeb4334. Report an issue: GitHub.