docling-project/docling · error · RuntimeError

Invalid binary_data_size value: {parsed_size}

Error message

Invalid binary_data_size value: {parsed_size}

What it means

_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.

Source

Thrown at docling/models/inference_engines/common/kserve_v2_http.py:136

    shape = tuple(int(dim) for dim in raw_output.shape)
    if raw_output.datatype == "BYTES":
        return decode_bytes_tensor(raw_payload, shape)

    return np.frombuffer(raw_payload, dtype=np_dtype).reshape(shape)


def _parse_binary_data_size(parameters: Mapping[str, Any] | None) -> int | None:
    if not parameters or "binary_data_size" not in parameters:
        return None

    size = parameters["binary_data_size"]
    try:
        parsed_size = int(size)
    except (TypeError, ValueError) as exc:
        raise RuntimeError(f"Invalid binary_data_size value: {size!r}") from exc
    if parsed_size < 0:
        raise RuntimeError(f"Invalid binary_data_size value: {parsed_size}")
    return parsed_size


def _build_binary_request(
    *,
    inputs: Mapping[str, np.ndarray],
    output_names: list[str],
    request_parameters: Optional[Mapping[str, Any]],
) -> tuple[Dict[str, str], bytes]:
    raw_inputs: list[bytes] = []
    payload: Dict[str, Any] = {"inputs": []}
    for input_name, tensor in inputs.items():
        encoded_tensor, raw_payload = _encode_binary_input_tensor(
            name=input_name, tensor=np.asarray(tensor)
        )
        payload["inputs"].append(encoded_tensor)
        raw_inputs.append(raw_payload)

View on GitHub (pinned to 61d76f1ff3)

Solutions

1. Inspect the raw response JSON to confirm the negative value and report/fix the server-side computation
2. Disable binary transport (use_binary_data=False) until the server is fixed
3. If the parameter should be absent, ensure the predictor omits it rather than sending -1

try:
    outputs = client.infer(inputs=inputs, output_names=[...])
except RuntimeError as e:
    if "Invalid binary_data_size value" in str(e):
        raise  # server bug: negative byte count; report upstream
    raise

When it happens

Trigger: 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.

Common situations: Custom predictors using -1 as 'no data' marker instead of omitting the parameter; upstream size calculation bugs after model changes.

Related errors

• Invalid binary_data_size value: {size!r}
• Invalid binary inference response header from {response.url}
• KServe v2 HTTP response did not include enough binary output
• KServe v2 HTTP response included trailing binary output data
• Unsupported numpy dtype for KServe v2 input: {tensor.dtype!s

AI-assisted analysis of docling-project/docling@61d76f1ff3 (2026-08-14). Data as JSON: /api/errors/b292c4d41a36c599. Report an issue: GitHub.