PaddlePaddle/PaddleOCR · error · InvalidRequestError

Unsupported document parsing model: {model}

Error message

Unsupported document parsing model: {model}

What it means

Raised as InvalidRequestError by resolve_document_model() when the resolved model is not a document-parsing model. It mirrors resolve_ocr_model: the value may be a valid Model, but it does not belong to the document-parsing set, so the document-parsing API refuses it client-side.

Source

Thrown at paddleocr/_api_client/_core.py:61

def default_payload(model: Model) -> dict:
    if is_ocr_model(model):
        return OCROptions().to_payload()
    return resolve_document_options(model, None).to_payload()


def resolve_ocr_model(model: Union[Model, str]) -> Model:
    resolved = resolve_model(model)
    if not is_ocr_model(resolved):
        raise InvalidRequestError(f"Unsupported OCR model: {model}")
    return resolved


def resolve_document_model(model: Union[Model, str]) -> Model:
    resolved = resolve_model(model)
    if not is_document_parsing_model(resolved):
        raise InvalidRequestError(f"Unsupported document parsing model: {model}")
    return resolved


def resolve_model(model: Union[Model, str]) -> Model:
    if isinstance(model, Model):
        return model
    try:
        return Model(model)
    except ValueError as e:
        raise InvalidRequestError(f"Unsupported model: {model}") from e


def resolve_document_options(
    model: Model, options: Optional[DocParsingOptions]
) -> DocParsingOptions:
    if options is not None:
        if model == Model.PP_STRUCTURE_V3 and not isinstance(
            options, PPStructureV3Options

View on GitHub (pinned to 2661c7c0ef)

Solutions

1. Use a document-parsing model such as PP-StructureV3 or a PaddleOCR-VL model for document-parsing calls.
2. Verify the model against the document-parsing set in the Model enum.
3. Keep separate config keys for OCR vs document-parsing model names.

Example fix

# before
job = client.parse_document(file_path="a.pdf", model="PP-OCRv5")

# after
job = client.parse_document(file_path="a.pdf", model="PP-StructureV3")

from paddleocr._api_client.models import is_document_parsing_model, resolve_model

def usable_for_doc_parsing(model) -> bool:
    try:
        return is_document_parsing_model(resolve_model(model))
    except Exception:
        return False

When it happens

Trigger: Calling a document-parsing method with an OCR-only model (or any non document-parsing Model), e.g. model='PP-OCRv5'.

Common situations: Switching an existing OCR pipeline to document parsing without changing the configured model, or assuming all Model values work with every endpoint.

Related errors

• Unsupported OCR model: {model}
• Unsupported model: {model}
• PP-StructureV3 requires PPStructureV3Options.
• PaddleOCR-VL models require PaddleOCRVLOptions.
• Job model is not an OCR model: {job.model}.

AI-assisted analysis of PaddlePaddle/PaddleOCR@2661c7c0ef (2026-08-14). Data as JSON: /api/errors/b95ffee773fa25ed. Report an issue: GitHub.