docling-project/docling · error · ConversionError

No extraction pipeline could be initialized for {in_doc.file

Error message

No extraction pipeline could be initialized for {in_doc.file}.

What it means

ConversionError raised by DocumentExtractor._execute_extraction when the input document is valid but _get_pipeline(in_doc.format) returns None, i.e. no extraction pipeline is configured for that format. With raises_on_error=False it instead returns a FAILURE ExtractionResult.

Source

Thrown at docling/document_extractor.py:280

            )

    def _execute_extraction_pipeline(
        self,
        in_doc: InputDocument,
        raises_on_error: bool,
        template: ExtractionTemplateType,
    ) -> ExtractionResult:
        if not in_doc.valid:
            return ExtractionResult(
                input=in_doc,
                status=ConversionStatus.FAILURE,
                errors=build_invalid_input_errors(in_doc),
            )

        pipeline = self._get_pipeline(in_doc.format)
        if pipeline is None:
            if raises_on_error:
                raise ConversionError(
                    f"No extraction pipeline could be initialized for {in_doc.file}."
                )
            else:
                return ExtractionResult(input=in_doc, status=ConversionStatus.FAILURE)

        return pipeline.execute(
            in_doc, raises_on_error=raises_on_error, template=template
        )

    def _get_pipeline(
        self, doc_format: InputFormat
    ) -> Optional[BaseExtractionPipeline]:
        """Retrieve or initialize a pipeline, reusing instances based on class and options."""
        fopt = self.extraction_format_to_options.get(doc_format)
        if fopt is None or fopt.pipeline_options is None:
            return None

        pipeline_class = fopt.pipeline_cls

View on GitHub (pinned to 61d76f1ff3)

Solutions

1. Supply format_options for the format: DocumentExtractor(format_options={InputFormat.PDF: ExtractionFormatOption(pipeline_cls=ExtractionVlmPipeline)}).
2. Verify the key you used in format_options is the same InputFormat the file resolves to (extension-based).
3. Set raises_on_error=False to get a FAILURE result instead of an exception and inspect it.

Example fix

# before
extractor = DocumentExtractor()  # relies on defaults for a non-default format

# after
from docling.datamodel.settings import ExtractionFormatOption
extractor = DocumentExtractor(
    format_options={InputFormat.PDF: ExtractionFormatOption()}  # explicit pipeline
)

fmt = InputFormat.PDF  # resolved from extension
if fmt not in extractor.format_to_options:
    raise SystemExit(f'add format_options for {fmt} to DocumentExtractor')

from docling.datamodel.base_models import ConversionError
try:
    res = extractor.extract(path, raises_on_error=True)
except ConversionError as e:
    if 'No extraction pipeline' in str(e):
        raise SystemExit('configure ExtractionFormatOption(pipeline_cls=...) for this format')
    raise

When it happens

Trigger: Running extract() on a valid document whose format has no matching entry in the extractor's format_to_options map (no format_options supplied for that InputFormat).

Common situations: Using DocumentExtractor with default options on formats outside the defaults; constructing the extractor with format_options keyed by the wrong InputFormat; typo'd pipeline class registration.

Related errors

• No pipeline could be initialized for format {format}
• No pipeline could be initialized for {in_doc.file}.
• No default extraction backend configured for {fmt}
• Extraction failed for: {ext_res.input.file} with status: {ex
• The selected backend {type(conv_res.input._backend).__name__

AI-assisted analysis of docling-project/docling@61d76f1ff3 (2026-08-14). Data as JSON: /api/errors/8f5434d6d53dd271. Report an issue: GitHub.