Enrich simple pipeline

In [ ]:

import logging
from pathlib import Path

import logging from pathlib import Path

In [ ]:

from docling.datamodel.base_models import InputFormat
from docling.datamodel.pipeline_options import ConvertPipelineOptions
from docling.document_converter import (
    DocumentConverter,
    HTMLFormatOption,
    WordFormatOption,
)

from docling.datamodel.base_models import InputFormat from docling.datamodel.pipeline_options import ConvertPipelineOptions from docling.document_converter import ( DocumentConverter, HTMLFormatOption, WordFormatOption, )

In [ ]:

_log = logging.getLogger(__name__)

_log = logging.getLogger(__name__)

In [ ]:

def main():
    input_path = Path("tests/data/docx/word_sample.docx")

    pipeline_options = ConvertPipelineOptions()
    pipeline_options.do_picture_classification = True
    pipeline_options.do_picture_description = True

    doc_converter = DocumentConverter(
        format_options={
            InputFormat.DOCX: WordFormatOption(pipeline_options=pipeline_options),
            InputFormat.HTML: HTMLFormatOption(pipeline_options=pipeline_options),
        },
    )

    res = doc_converter.convert(input_path)

    print(res.document.export_to_markdown())

def main(): input_path = Path("tests/data/docx/word_sample.docx") pipeline_options = ConvertPipelineOptions() pipeline_options.do_picture_classification = True pipeline_options.do_picture_description = True doc_converter = DocumentConverter( format_options={ InputFormat.DOCX: WordFormatOption(pipeline_options=pipeline_options), InputFormat.HTML: HTMLFormatOption(pipeline_options=pipeline_options), }, ) res = doc_converter.convert(input_path) print(res.document.export_to_markdown())

In [ ]:

if __name__ == "__main__":
    main()

if __name__ == "__main__": main()