BerriAI/litellm · error · ValueError

file content is required

Error message

file content is required

What it means

BedrockJsonlFilesTransformation.get_object_name() needs the uploaded file's bytes (via extracted_file_data['content']) both to name the object and, for batch purpose, to parse each JSONL line and derive the model-specific object name. Missing content means the extraction step failed or the caller bypassed it.

Source

Thrown at litellm/llms/bedrock/files/transformation.py:300

        named as: litellm-bedrock-files/{model}/{uuid}
        """
        _model = openai_jsonl_content[0].get("body", {}).get("model", "")
        # Remove bedrock/ prefix if present
        _model = _model.removeprefix("bedrock/")

        safe_model: Final = sanitize_cloud_object_component(_model.replace(":", "-"), fallback="model")

        object_name: Final = f"{BEDROCK_MANAGED_S3_BATCH_PREFIX}{safe_model}-{uuid.uuid4()}.jsonl"
        return object_name

    def get_object_name(self, extracted_file_data: ExtractedFileData, purpose: str) -> str:
        """
        Get the object name for the request
        """
        extracted_file_data_content: Final = extracted_file_data.get("content")

        if extracted_file_data_content is None:
            raise ValueError("file content is required")

        if purpose == "batch":
            ## 1. If jsonl, check if there's a model name
            file_content: Final = self._get_content_from_openai_file(extracted_file_data_content)

            # Split into lines and parse each line as JSON
            openai_jsonl_content: Final = [json.loads(line) for line in file_content.splitlines() if line.strip()]
            if len(openai_jsonl_content) > 0:
                return self._get_s3_object_name_from_batch_jsonl(openai_jsonl_content)

        ## 2. If not jsonl, store under a server-generated managed object name
        filename: Final = extracted_file_data.get("filename")
        return build_managed_cloud_object_name(
            prefix=BEDROCK_MANAGED_S3_UPLOAD_PREFIX,
            filename=filename,
            fallback_filename="file",
        )

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Ensure the actual file bytes are attached as extracted_file_data['content'] (bytes) before upload.
2. Use litellm's standard file upload flow rather than constructing ExtractedFileData by hand.
3. If a framework consumed the stream, reset via await file.seek(0) before passing it on.

def has_content(extracted_file_data: dict) -> bool:
    return extracted_file_data.get("content") is not None

When it happens

Trigger: Calling create-file (upload) where extracted_file_data carries metadata only — content is None because the multipart file body was not read, or a custom File storage integration passed an already-consumed file object.

Common situations: Custom integrations constructing ExtractedFileData manually and omitting 'content'; a FastAPI/Starlette upload handler reading the stream before litellm does; tests with stub file objects lacking bytes.

Related errors

• file is required
• purpose is required
• File data is required
• file_id is required in file_content_request
• file_id must be a managed LiteLLM S3 file id

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/42d11425a2583ad2. Report an issue: GitHub.