Function convert

docling/cli/main.py:155–450

(
    input_sources: Annotated[
        List[str],
        typer.Argument(
            ...,
            metavar="source",
            help="PDF files to convert. Can be local file / directory paths or URL.",
        ),
    ],
    from_formats: List[InputFormat] = typer.Option(
        None,
        "--from",
        help="Specify input formats to convert from. Defaults to all formats.",
    ),
    to_formats: List[OutputFormat] = typer.Option(
        None, "--to", help="Specify output formats. Defaults to Markdown."
    ),
    headers: str = typer.Option(
        None,
        "--headers",
        help="Specify http request headers used when fetching url input sources in the form of a JSON string",
    ),
    image_export_mode: Annotated[
        ImageRefMode,
        typer.Option(
            ...,
            help="Image export mode for the document (only in case of JSON, Markdown or HTML). With `placeholder`, only the position of the image is marked in the output. In `embedded` mode, the image is embedded as base64 encoded string. In `referenced` mode, the image is exported in PNG format and referenced from the main exported document.",
        ),
    ] = ImageRefMode.EMBEDDED,
    ocr: Annotated[
        bool,
        typer.Option(
            ..., help="If enabled, the bitmap content will be processed using OCR."
        ),
    ] = True,
    force_ocr: Annotated[
        bool,
        typer.Option(
            ...,
            help="Replace any existing text with OCR generated text over the full content.",
        ),
    ] = False,
    ocr_engine: Annotated[
        OcrEngine, typer.Option(..., help="The OCR engine to use.")
    ] = OcrEngine.EASYOCR,
    ocr_lang: Annotated[
        Optional[str],
        typer.Option(
            ...,
            help="Provide a comma-separated list of languages used by the OCR engine. Note that each OCR engine has different values for the language names.",
        ),
    ] = None,
    pdf_backend: Annotated[
        PdfBackend, typer.Option(..., help="The PDF backend to use.")
    ] = PdfBackend.DLPARSE_V2,
    table_mode: Annotated[
        TableFormerMode,
        typer.Option(..., help="The mode to use in the table structure model."),
    ] = TableFormerMode.FAST,
    enrich_code: Annotated[
        bool,
        typer.Option(..., help="Enable the code enrichment model in the pipeline."),
    ] = False,
    enrich_formula: Annotated[
        bool,
        typer.Option(..., help="Enable the formula enrichment model in the pipeline."),
    ] = False,
    enrich_picture_classes: Annotated[
        bool,
        typer.Option(
            ...,
            help="Enable the picture classification enrichment model in the pipeline.",
        ),
    ] = False,
    enrich_picture_description: Annotated[
        bool,
        typer.Option(..., help="Enable the picture description model in the pipeline."),
    ] = False,
    artifacts_path: Annotated[
        Optional[Path],
        typer.Option(..., help="If provided, the location of the model artifacts."),
    ] = None,
    abort_on_error: Annotated[
        bool,
        typer.Option(
            ...,
            "--abort-on-error/--no-abort-on-error",
            help="If enabled, the bitmap content will be processed using OCR.",
        ),
    ] = False,
    output: Annotated[
        Path, typer.Option(..., help="Output directory where results are saved.")
    ] = Path("."),
    verbose: Annotated[
        int,
        typer.Option(
            "--verbose",
            "-v",
            count=True,
            help="Set the verbosity level. -v for info logging, -vv for debug logging.",
        ),
    ] = 0,
    debug_visualize_cells: Annotated[
        bool,
        typer.Option(..., help="Enable debug output which visualizes the PDF cells"),
    ] = False,
    debug_visualize_ocr: Annotated[
        bool,
        typer.Option(..., help="Enable debug output which visualizes the OCR cells"),
    ] = False,
    debug_visualize_layout: Annotated[
        bool,
        typer.Option(
            ..., help="Enable debug output which visualizes the layour clusters"
        ),
    ] = False,
    debug_visualize_tables: Annotated[
        bool,
        typer.Option(..., help="Enable debug output which visualizes the table cells"),
    ] = False,
    version: Annotated[
        Optional[bool],
        typer.Option(
            "--version",
            callback=version_callback,
            is_eager=True,
            help="Show version information.",
        ),
    ] = None,
    document_timeout: Annotated[
        Optional[float],
        typer.Option(
            ...,
            help="The timeout for processing each document, in seconds.",
        ),
    ] = None,
    num_threads: Annotated[int, typer.Option(..., help="Number of threads")] = 4,
    device: Annotated[
        AcceleratorDevice, typer.Option(..., help="Accelerator device")
    ] = AcceleratorDevice.AUTO,
)

@app.command(no_args_is_help=True)
def convert(
    input_sources: Annotated[
        List[str],
        typer.Argument(
            ...,
            metavar="source",
            help="PDF files to convert. Can be local file / directory paths or URL.",
        ),
    ],
    from_formats: List[InputFormat] = typer.Option(
        None,
        "--from",
        help="Specify input formats to convert from. Defaults to all formats.",
    ),
    to_formats: List[OutputFormat] = typer.Option(
        None, "--to", help="Specify output formats. Defaults to Markdown."
    ),
    headers: str = typer.Option(
        None,
        "--headers",
        help="Specify http request headers used when fetching url input sources in the form of a JSON string",
    ),
    image_export_mode: Annotated[
        ImageRefMode,
        typer.Option(
            ...,
            help="Image export mode for the document (only in case of JSON, Markdown or HTML). With `placeholder`, only the position of the image is marked in the output. In `embedded` mode, the image is embedded as base64 encoded string. In `referenced` mode, the image is exported in PNG format and referenced from the main exported document.",
        ),
    ] = ImageRefMode.EMBEDDED,
    ocr: Annotated[
        bool,
        typer.Option(
            ..., help="If enabled, the bitmap content will be processed using OCR."
        ),
    ] = True,
    force_ocr: Annotated[
        bool,
        typer.Option(
            ...,
            help="Replace any existing text with OCR generated text over the full content.",
        ),
    ] = False,
    ocr_engine: Annotated[
        OcrEngine, typer.Option(..., help="The OCR engine to use.")
    ] = OcrEngine.EASYOCR,
    ocr_lang: Annotated[
        Optional[str],
        typer.Option(
            ...,
            help="Provide a comma-separated list of languages used by the OCR engine. Note that each OCR engine has different values for the language names.",
        ),
    ] = None,
    pdf_backend: Annotated[
        PdfBackend, typer.Option(..., help="The PDF backend to use.")
    ] = PdfBackend.DLPARSE_V2,
    table_mode: Annotated[
        TableFormerMode,
        typer.Option(..., help="The mode to use in the table structure model."),