{"record":{"id":"b292c4d41a36c599","repo":"docling-project/docling","slug":"invalid-binary-data-size-value-parsed-size","errorCode":null,"errorMessage":"Invalid binary_data_size value: {parsed_size}","messagePattern":"Invalid binary_data_size value: (.+?)","errorType":"exception","errorClass":"RuntimeError","httpStatus":null,"severity":"error","filePath":"docling/models/inference_engines/common/kserve_v2_http.py","lineNumber":136,"sourceCode":"\n    shape = tuple(int(dim) for dim in raw_output.shape)\n    if raw_output.datatype == \"BYTES\":\n        return decode_bytes_tensor(raw_payload, shape)\n\n    return np.frombuffer(raw_payload, dtype=np_dtype).reshape(shape)\n\n\ndef _parse_binary_data_size(parameters: Mapping[str, Any] | None) -> int | None:\n    if not parameters or \"binary_data_size\" not in parameters:\n        return None\n\n    size = parameters[\"binary_data_size\"]\n    try:\n        parsed_size = int(size)\n    except (TypeError, ValueError) as exc:\n        raise RuntimeError(f\"Invalid binary_data_size value: {size!r}\") from exc\n    if parsed_size < 0:\n        raise RuntimeError(f\"Invalid binary_data_size value: {parsed_size}\")\n    return parsed_size\n\n\ndef _build_binary_request(\n    *,\n    inputs: Mapping[str, np.ndarray],\n    output_names: list[str],\n    request_parameters: Optional[Mapping[str, Any]],\n) -> tuple[Dict[str, str], bytes]:\n    raw_inputs: list[bytes] = []\n    payload: Dict[str, Any] = {\"inputs\": []}\n    for input_name, tensor in inputs.items():\n        encoded_tensor, raw_payload = _encode_binary_input_tensor(\n            name=input_name, tensor=np.asarray(tensor)\n        )\n        payload[\"inputs\"].append(encoded_tensor)\n        raw_inputs.append(raw_payload)\n","sourceCodeStart":118,"sourceCodeEnd":154,"githubUrl":"https://github.com/docling-project/docling/blob/61d76f1ff3f8428065465889f7b4577da7df704c/docling/models/inference_engines/common/kserve_v2_http.py#L118-L154","documentation":"_parse_binary_data_size successfully parsed binary_data_size as an int but the value was negative. A negative byte count is nonsensical and would corrupt the offset arithmetic that slices the binary body, so it is rejected.","triggerScenarios":"A server bug or corrupted response sets binary_data_size to a negative integer (e.g. -1 as a sentinel); integer underflow in a predictor computing payload sizes; tampered/truncated body.","commonSituations":"Custom predictors using -1 as 'no data' marker instead of omitting the parameter; upstream size calculation bugs after model changes.","solutions":["Inspect the raw response JSON to confirm the negative value and report/fix the server-side computation","Disable binary transport (use_binary_data=False) until the server is fixed","If the parameter should be absent, ensure the predictor omits it rather than sending -1"],"exampleFix":null,"handlingStrategy":"try-catch","validationCode":null,"typeGuard":null,"tryCatchPattern":"try:\n    outputs = client.infer(inputs=inputs, output_names=[...])\nexcept RuntimeError as e:\n    if \"Invalid binary_data_size value\" in str(e):\n        raise  # server bug: negative byte count; report upstream\n    raise","preventionTips":["Ensure predictors omit binary_data_size rather than sending sentinels like -1","Unit-test server-side size computation with empty and multi-tensor outputs"],"tags":["http","kserve","binary-data","server-bug","validation"],"backgroundTag":null,"analyzedSha":"61d76f1ff3f8428065465889f7b4577da7df704c","analyzedAt":"2026-08-14T23:53:18.727Z","schemaVersion":2},"datasetVersion":"2026-08-15T22:17:37.221Z"}