>>> from datasets import load_dataset, Pdf

>>> dataset = load_dataset("path/to/pdf/folder", split="train")
>>> dataset[0]["pdf"]
<pdfplumber.pdf.PDF at 0x1075bc320>

>>> pdf = dataset[0]["pdf"]
>>> first_page = pdf.pages[0]
>>> first_page
<Page:1>
>>> first_page.extract_text()
Docling Technical Report
Version1.0
ChristophAuer MaksymLysak AhmedNassar MicheleDolfi NikolaosLivathinos
PanosVagenas CesarBerrospiRamis MatteoOmenetti FabianLindlbauer
KasperDinkla LokeshMishra YusikKim ShubhamGupta RafaelTeixeiradeLima
ValeryWeber LucasMorin IngmarMeijer ViktorKuropiatnyk PeterW.J.Staar
AI4KGroup,IBMResearch
Ru¨schlikon,Switzerland
Abstract
This technical report introduces Docling, an easy to use, self-contained, MIT-
licensed open-source package for PDF document conversion.
...
>>> first_page.images
In [24]: first_page.images
Out[24]: 
[{'x0': 256.5,
  'y0': 621.0,
  'x1': 355.49519999999995,
  'y1': 719.9952,
  'width': 98.99519999999995,
  'height': 98.99519999999995,
  'name': 'Im1',
  'stream': <PDFStream(44): raw=88980, {'Type': /'XObject', 'Subtype': /'Image', 'BitsPerComponent': 8, 'ColorSpace': /'DeviceRGB', 'Filter': /'DCTDecode', 'Height': 1024, 'Length': 88980, 'Width': 1024}>,
  'srcsize': (1024, 1024),
  'imagemask': None,
  'bits': 8,
  'colorspace': [/'DeviceRGB'],
  'mcid': None,
  'tag': None,
  'object_type': 'image',
  'page_number': 1,
  'top': 72.00480000000005,
  'bottom': 171.0,
  'doctop': 72.00480000000005}]
>>> first_page.extract_tables()
[]

>>> import PIL.Image
>>> import io
>>> first_page.to_image()
<pdfplumber.display.PageImage at 0x107d68dd0>
>>> buffer = io.BytesIO()
>>> first_page.to_image().save(buffer)
>>> img = PIL.Image.open(buffer)
>>> img
<PIL.PngImagePlugin.PngImageFile image mode=P size=612x792>

>>> from datasets import Dataset, Pdf

>>> dataset = Dataset.from_dict({"pdf": ["path/to/pdf_1", "path/to/pdf_2", ..., "path/to/pdf_n"]}).cast_column("pdf", Pdf())
>>> dataset[0]["pdf"]
<pdfplumber.pdf.PDF at 0x1657d0280>

>>> dataset = dataset.cast_column("pdf", Pdf(decode=False))
>>> dataset[0]["pdf"]
{'bytes': None,
 'path': 'path/to/pdf/folder/pdf0.pdf'}

folder/train/resume/0001.pdf
folder/train/resume/0002.pdf
folder/train/resume/0003.pdf

folder/train/invoice/0001.pdf
folder/train/invoice/0002.pdf
folder/train/invoice/0003.pdf

>>> from datasets import load_dataset

>>> dataset = load_dataset("username/dataset_name")
>>> # OR locally:
>>> dataset = load_dataset("/path/to/folder")

>>> dataset = load_dataset("pdffolder", data_dir="/path/to/folder")

>>> dataset["train"][0]
{"pdf": <pdfplumber.pdf.PDF at 0x161715e50>, "label": 0}

>>> dataset["train"][-1]
{"pdf": <pdfplumber.pdf.PDF at 0x16170bd90>, "label": 1}

>>> from datasets import load_dataset

>>> dataset = load_dataset("username/dataset_with_metadata", drop_metadata=True)

>>> from datasets import load_dataset

>>> dataset = load_dataset("username/dataset_without_metadata", drop_labels=True)

>>> filters = [("label", "=", 0)]
>>> dataset = load_dataset("username/dataset_name", streaming=True, filters=filters)

>>> import os
>>> num_threads = num_threads = min(32, (os.cpu_count() or 1) + 4)
>>> dataset = dataset.decode(num_threads=num_threads)
>>> for example in dataset:  # up to 20 times faster !
...     ...

>>> dataset = dataset.decode(False)