BerriAI/litellm · error · ValueError

File data is required

Error message

File data is required

What it means

Multipart-building validation for Anthropic file upload. The transformation expects the file content under the 'file' key of create_file_data; a None value raises immediately. Note this check tests identity with None — an empty bytes object passes here and fails server-side instead.

Source

Thrown at litellm/llms/anthropic/files/transformation.py:141

        return optional_params

    def transform_create_file_request(
        self,
        model: str,
        create_file_data: CreateFileRequest,
        optional_params: dict,
        litellm_params: dict,
    ) -> dict:
        """
        Transform to multipart form data for Anthropic file upload.

        Anthropic expects: POST /v1/files with multipart form-data
        - file: the file content
        - purpose: "messages" (defaults to "messages" if not provided)
        """
        file_data: Final = create_file_data.get("file")
        if file_data is None:
            raise ValueError("File data is required")

        extracted: Final = extract_file_data(file_data)
        filename: Final = extracted["filename"] or f"file_{int(time.time())}"
        content: Final = extracted["content"]
        content_type: Final = extracted.get("content_type", "application/octet-stream")

        purpose: Final = create_file_data.get("purpose", "messages")

        return {
            "file": (filename, content, content_type),
            "purpose": (None, purpose),
        }

    def transform_create_file_response(
        self,
        model: str | None,
        raw_response: httpx.Response,
        logging_obj: LiteLLMLoggingObj,

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Provide the file under the 'file' key: {'file': file_obj_or_bytes, 'purpose': 'messages'}.
2. If you have raw bytes and a filename, a (filename, bytes, content_type) tuple or File-like object works — extract_file_data handles common shapes.
3. Assert the file argument is not None before calling upload.

Example fix

# before
create_file_data = {"filename": "data.jsonl", "content": file_bytes, "purpose": "messages"}

# after
create_file_data = {"file": file_bytes, "purpose": "messages"}
# or: {"file": ("data.jsonl", file_bytes, "application/json")}

def build_create_file_data(file: object) -> dict:
    if file is None:
        raise ValueError("file payload is required")
    return {"file": file, "purpose": "messages"}

def has_file_payload(create_file_data: object) -> bool:
    return isinstance(create_file_data, dict) and create_file_data.get("file") is not None

try:
    resp = litellm.create_file(file=f, purpose="messages")
except ValueError as e:
    if "File data is required" in str(e):
        return http_error(400, "multipart 'file' field is required")
    raise

When it happens

Trigger: Calling the Anthropic files transformation with create_file_data missing the 'file' key or file=None — e.g. passing {'filename': ..., 'content': ...} (OpenAI-style structured body) instead of {'file': ...}.

Common situations: Reusing OpenAI file-upload payload shapes; code that reads a path but passes the variable before assignment; optional-file flows where the file handle is None.

Related errors

• Unable to parse anthropic file message: {message}
• Either file_data or file_id must be present in the file mess
• file_id is required in file_content_request
• file content is required
• file is required

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/fdd48e3d14c14068. Report an issue: GitHub.