BerriAI/litellm · error · ValueError

Failed to parse multipart form data: {e}. When using curl wi

Error message

Failed to parse multipart form data: {e}. When using curl with --form/-F, do NOT set the Content-Type header manually — curl will set it automatically with the required boundary.

What it means

Error "Failed to parse multipart form data: {e}. When using curl with --form/-F, do NOT set the Content-Type header manually — curl will set it automatically with the required boundary." thrown in BerriAI/litellm.

Source

Thrown at litellm/proxy/ocr_endpoints/endpoints.py:57

            "mime_type": mime_type or "application/octet-stream",
        }
    )


async def _parse_multipart_form(request: Request) -> dict[str, Any]:
    """
    Extract OCR data from a multipart form request.

    Uses the cached form if already parsed by auth middleware,
    otherwise parses the form from the request.

    Returns:
        A dict with 'document', 'model', and any other OCR params.
    """
    try:
        form: Final = await request.form()
    except Exception as e:
        raise ValueError(
            f"Failed to parse multipart form data: {e}. "
            "When using curl with --form/-F, do NOT set the Content-Type header "
            "manually — curl will set it automatically with the required boundary."
        )

    uploaded_file = form.get("file")
    # request.form() may return either a FastAPI or Starlette UploadFile
    # depending on middleware; check both via isinstance (FastAPI's UploadFile
    # is a subclass of Starlette's) and fall back to duck-type check.
    if uploaded_file is None or (not isinstance(uploaded_file, UploadFile) and not hasattr(uploaded_file, "read")):
        raise ValueError("Multipart OCR request must include a 'file' field with the document to process")

    uploaded_file = cast(UploadFile, uploaded_file)

    # Seek to start in case the file was already partially read by middleware
    await uploaded_file.seek(0)
    file_content: Final = await uploaded_file.read()
    if not file_content:

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. When using curl with --form/-F, do not set the Content-Type header manually; let curl set it with the boundary.

When it happens

Trigger: Thrown at litellm/proxy/ocr_endpoints/endpoints.py:57 when the library encounters an invalid state.

Common situations: See trigger scenarios.

Understand the failure class

• Parsing and encoding errors: unexpected token, malformed input — why parsers reject input and how to find the real culprit.

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/34ceb777c652fd3e. Report an issue: GitHub.