docling-parse 7.0.0

Simple package to extract text with coordinates from programmatic PDFs

Docling Parse

Simple package to extract text, paths and bitmap images with coordinates from programmatic PDFs. This package is used in the Docling PDF conversion. Below, we show a few output of the latest parser with char, word and line level output for text, in addition to the extracted paths and bitmap resources.

To do the visualizations yourself, simply run (change word into char or line),

uv run python ./docling_parse/visualize.py -i <path-to-pdf-file> -c word --interactive

original	char	word	line

Quick start

Install the package from Pypi

pip install docling-parse

Convert a PDF (look in the visualize.py for a more detailed information)

from docling_core.types.doc.page import TextCellUnit
from docling_parse.pdf_parser import DoclingPdfParser, PdfDocument

parser = DoclingPdfParser()

pdf_doc: PdfDocument = parser.load(
    path_or_stream="<path-to-pdf>"
)

# PdfDocument.iterate_pages() will automatically populate pages as they are yielded.
for page_no, pred_page in pdf_doc.iterate_pages():

    # iterate over the word-cells
    for word in pred_page.iterate_cells(unit_type=TextCellUnit.WORD):
        print(word.rect, ": ", word.text)

        # create a PIL image with the char cells
    img = pred_page.render_as_image(cell_unit=TextCellUnit.CHAR)
    img.show()

Parallel parsing (multi-threaded)

Parse pages from one or more PDFs in parallel using a thread pool with backpressure:

from docling_parse.pdf_parser import (
    DecodeConfig,
    DoclingThreadedPdfParser,
    ThreadedPdfParserConfig,
)

parser_config = ThreadedPdfParserConfig(
    loglevel="fatal",
    threads=4,                # worker threads
    max_concurrent_results=32 # cap buffered results to limit memory
)
decode_config = DecodeConfig()

parser = DoclingThreadedPdfParser(
    parser_config=parser_config,
    decode_config=decode_config,
)

# load one or more documents
for source in ["doc_a.pdf", "doc_b.pdf"]:
    doc_key = parser.load(source)
    print(doc_key, parser.page_count(doc_key))

# consume decoded pages as they become available
for result in parser.iterate_results():
    if result.success:
        seg_page = result.get_page()
        timings = result.get_timings()
        print(f"{result.doc_key} p{result.page_number}: "
              f"{len(seg_page.word_cells)} words in {timings.total():.3f}s")
    else:
        print(f"error on {result.doc_key} p{result.page_number}: {result.error_message}")

Use the CLI

$ docling-parse -h
usage: docling-parse [-h] -p PDF

Process a PDF file.

options:
  -h, --help         show this help message and exit
  -p PDF, --pdf PDF  Path to the PDF file

Performance Benchmarks

Coming soon - benchmarks will be updated for the current parser version.

For historical V1 vs V2 benchmarks, see legacy_performance_benchmarks.md.

Development

CXX

To build the parser, simply run the following command in the root folder,

rm -rf build; cmake -B ./build; cd build; make

You can run the parser from your build folder:

% ./parse.exe -h
program to process PDF files or configuration files
Usage:
  PDFProcessor [OPTION...]

  -i, --input arg          Input PDF file
  -c, --config arg         Config file
      --create-config arg  Create config file
  -p, --page arg           Pages to process (default: -1 for all) (default:
                           -1)
      --password arg       Password for accessing encrypted, password-protected files
  -o, --output arg         Output file
  -l, --loglevel arg       loglevel [error;warning;success;info]
  -h, --help               Print usage

If you don't have an input file, a template input file will be printed on the terminal.

Python

To build the package, simply run (make sure uv is installed),

uv sync

The latter will only work after a clean git clone. If you are developing and updating C++ code, please use,

# uv pip install --force-reinstall --no-deps -e .
rm -rf .venv; uv venv; uv pip install --force-reinstall --no-deps -e ".[perf-tools]"

or

BUILD_THREADS=12 uv pip install --force-reinstall --no-deps -e ".[perf]"

To test the package, run:

uv run pytest ./tests -v -s

Contributing

Please read Contributing to Docling Parse for details.

References

If you use Docling in your projects, please consider citing the following:

@techreport{Docling,
  author = {Docling Team},
  month = {8},
  title = {Docling Technical Report},
  url = {https://arxiv.org/abs/2408.09869},
  eprint = {2408.09869},
  doi = {10.48550/arXiv.2408.09869},
  version = {1.0.0},
  year = {2024}
}

License

The Docling Parse codebase is under MIT license. For individual model usage, please refer to the model licenses found in the original packages.

LF AI & Data

Docling (and also docling-parse) is hosted as a project in the LF AI & Data Foundation.

IBM ❤️ Open Source AI

The project was started by the AI for knowledge team at IBM Research Zurich.