BerriAI/litellm · error · HTTPException

Invalid base64 content: {e}

Error message

Invalid base64 content: {e}

What it means

JSON-body ingestion guard: the request supplied a file object with filename and content, but the 'content' field failed base64 decoding (malformed base64 string), so the file bytes cannot be reconstructed; rejected with 400 including the decoder's error text.

Source

Thrown at litellm/proxy/rag_endpoints/endpoints.py:348

        # JSON body
        data: Final = await _read_request_body(request)
        ingest_options = data.get("ingest_options", {})
        file_url = data.get("file_url")
        file_id = data.get("file_id")

        # Handle base64-encoded file in JSON body
        file_obj = data.get("file")
        if file_obj and isinstance(file_obj, dict):
            filename: Final = file_obj.get("filename")
            content_b64: Final = file_obj.get("content")
            content_type = file_obj.get("content_type", "application/octet-stream")

            if filename and content_b64:
                try:
                    file_content = base64.b64decode(content_b64)
                    file_data = (filename, file_content, content_type)
                except Exception as e:
                    raise HTTPException(
                        status_code=400,
                        detail={"error": f"Invalid base64 content: {e}"},
                    )

    # Validate
    if file_data is None and file_url is None and file_id is None:
        raise HTTPException(
            status_code=400,
            detail={"error": "Must provide file, file_url, or file_id"},
        )

    if "vector_store" not in ingest_options:
        raise HTTPException(
            status_code=400,
            detail={"error": "ingest_options must contain 'vector_store' configuration"},
        )

    # Credential fields must come from server configuration, not user requests.

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Send valid base64-encoded file content; re-encode the file with standard base64 and retry.

When it happens

Trigger: Thrown at litellm/proxy/rag_endpoints/endpoints.py:348 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/b70c035ef25126a4. Report an issue: GitHub.