BerriAI/litellm · error · ValueError

Provider '{provider}' is not supported for RAG ingestion. Su

Error message

Provider '{provider}' is not supported for RAG ingestion. Supported providers: {supported}

What it means

Registry lookup miss in get_ingestion_class: the requested vector store provider name has no registered RAG ingestion class, so ingestion cannot proceed. Fired by a misspelled or genuinely unsupported 'provider' value.

Source

Thrown at litellm/rag/main.py:69

def get_ingestion_class(provider: str) -> type[BaseRAGIngestion]:
    """
    Get the ingestion class for a given provider.

    Args:
        provider: The vector store provider name (e.g., 'openai')

    Returns:
        The ingestion class for the provider

    Raises:
        ValueError: If provider is not supported
    """
    ingestion_class: Final = INGESTION_REGISTRY.get(provider)
    if ingestion_class is None:
        supported: Final = ", ".join(INGESTION_REGISTRY.keys())
        raise ValueError(f"Provider '{provider}' is not supported for RAG ingestion. Supported providers: {supported}")
    return ingestion_class


async def _execute_ingest_pipeline(
    ingest_options: RAGIngestOptions,
    file_data: tuple[str, bytes, str] | None = None,
    file_url: str | None = None,
    file_id: str | None = None,
    router: Router | None = None,
) -> RAGIngestResponse:
    """
    Execute the RAG ingest pipeline using provider-specific implementation.

    Args:
        ingest_options: Configuration for the ingest pipeline
        file_data: Tuple of (filename, content_bytes, content_type)
        file_url: URL to fetch file from
        file_id: Existing file ID to use

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Use one of the listed supported providers for RAG ingestion.

When it happens

Trigger: Thrown at litellm/rag/main.py:69 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/e7842c9e10671230. Report an issue: GitHub.