docling-project/docling · error · RuntimeError

Invalid {_INFERENCE_HEADER_CONTENT_LENGTH} value: {header_le

Error message

Invalid {_INFERENCE_HEADER_CONTENT_LENGTH} value: {header_len_text!r}

What it means

_decode_binary_response: the Inference-Header-Content-Length response header exists but its value cannot be parsed as an integer (int() raised ValueError). The header must be the decimal byte length of the JSON header; garbage like '12; charset=utf-8' or an empty value fails here.

Source

Thrown at docling/models/inference_engines/common/kserve_v2_http.py:187

    }
    return request_headers, request_body


def _decode_binary_response(response: requests.Response) -> KserveV2InferResponse:
    header_len_text = response.headers.get(_INFERENCE_HEADER_CONTENT_LENGTH)
    if header_len_text is None:
        try:
            return KserveV2InferResponse.model_validate(response.json())
        except Exception as exc:
            raise RuntimeError(
                f"Binary KServe response from {response.url} did not include "
                f"{_INFERENCE_HEADER_CONTENT_LENGTH} and was not valid JSON: {exc}"
            ) from exc

    try:
        header_len = int(header_len_text)
    except ValueError as exc:
        raise RuntimeError(
            f"Invalid {_INFERENCE_HEADER_CONTENT_LENGTH} value: {header_len_text!r}"
        ) from exc

    if header_len < 0 or header_len > len(response.content):
        raise RuntimeError(
            f"Invalid {_INFERENCE_HEADER_CONTENT_LENGTH} value: {header_len}"
        )

    try:
        header_json = json.loads(response.content[:header_len].decode("utf-8"))
        return KserveV2InferResponse.model_validate(header_json)
    except Exception as exc:
        raise RuntimeError(
            f"Invalid binary inference response header from {response.url}: {exc}"
        ) from exc


@dataclass(frozen=True)

View on GitHub (pinned to 61d76f1ff3)

Solutions

1. Check the actual header value with curl -i / a network trace
2. Fix or reconfigure the intermediary that mutates the header, or route the infer traffic around it
3. Disable use_binary_data to avoid binary parsing entirely while the header path is broken

try:
    outputs = client.infer(inputs=inputs, output_names=[...])
except RuntimeError as e:
    if "Invalid Inference-Header-Content-Length value" in str(e):
        raise  # header mangled by intermediary; fix proxy config
    raise

When it happens

Trigger: A proxy rewrites the header value (appends parameters, quotes it); a custom server sends a float or empty string; header name-collision with another middleware writing the same header.

Common situations: API gateways that normalize/annotate hop-by-hop headers; hand-rolled test servers; WAFs mangling numeric headers.

Related errors

• Binary KServe response from {response.url} did not include {
• Invalid {_INFERENCE_HEADER_CONTENT_LENGTH} value: {header_le
• KServe v2 output tensor {raw_output.name} did not include in
• Invalid binary_data_size value: {size!r}
• Invalid binary_data_size value: {parsed_size}

AI-assisted analysis of docling-project/docling@61d76f1ff3 (2026-08-14). Data as JSON: /api/errors/50d60905d7fb8ae6. Report an issue: GitHub.