PaddlePaddle/PaddleOCR · error · InvalidRequestError

Job model is not an OCR model: {job.model}.

Error message

Job model is not an OCR model: {job.model}.

What it means

Raised as InvalidRequestError by job_id_for_task() when task == 'ocr' but the Job's model fails is_ocr_model(). It catches Jobs that claim the OCR task while carrying a non-OCR model, before an OCR endpoint is called with an incompatible job id.

Source

Thrown at paddleocr/_api_client/_core.py:98

        ):
            raise InvalidRequestError("PP-StructureV3 requires PPStructureV3Options.")
        if is_vl_model(model) and not isinstance(options, PaddleOCRVLOptions):
            raise InvalidRequestError("PaddleOCR-VL models require PaddleOCRVLOptions.")
        return options
    if model == Model.PP_STRUCTURE_V3:
        return PPStructureV3Options()
    return PaddleOCRVLOptions()


def job_id_for_task(job: Union[Job, str], task: str) -> str:
    if isinstance(job, str):
        return job
    if job.task != task:
        raise InvalidRequestError(
            f"Job task mismatch: expected {task}, got {job.task}."
        )
    if task == "ocr" and not is_ocr_model(job.model):
        raise InvalidRequestError(f"Job model is not an OCR model: {job.model}.")
    if task == "document_parsing" and not is_document_parsing_model(job.model):
        raise InvalidRequestError(
            f"Job model is not a document parsing model: {job.model}."
        )
    return job.job_id


def extract_api_message_from_payload(payload: dict) -> Optional[str]:
    for key in ("msg", "errorMsg", "message"):
        value = payload.get(key)
        if value:
            return str(value)
    data = payload.get("data")
    if isinstance(data, dict):
        value = data.get("errorMsg")
        if value:
            return str(value)
    return None

View on GitHub (pinned to 2661c7c0ef)

Solutions

1. Use the Job returned by the matching create call; do not synthesize Job objects manually.
2. Verify job.model is an OCR model before calling OCR follow-up methods.
3. If the job is genuinely document parsing, use the document-parsing endpoint.

Example fix

# before
ocr_result = client.get_ocr_result(job)  # job.model is PP-StructureV3

# after
assert is_ocr_model(job.model), "use document-parsing result API for this job"
ocr_result = client.get_ocr_result(job)

from paddleocr._api_client.models import is_ocr_model

def job_is_ocr(job) -> bool:
    return job.task == "ocr" and is_ocr_model(job.model)

When it happens

Trigger: Passing a Job whose model is a document-parsing or VL model to an OCR-scoped method (task='ocr').

Common situations: Hand-constructed or deserialized Job objects with inconsistent task/model fields, or jobs from an older version where task semantics differed.

Related errors

• Job model is not a document parsing model: {job.model}.
• Unsupported OCR model: {model}
• Unsupported document parsing model: {model}
• Unsupported model: {model}
• PP-StructureV3 requires PPStructureV3Options.

AI-assisted analysis of PaddlePaddle/PaddleOCR@2661c7c0ef (2026-08-14). Data as JSON: /api/errors/e5577505d9b9ae53. Report an issue: GitHub.