from docling.document_converter import DocumentConverter

source = "https://arxiv.org/pdf/2408.09869"  # URL, Path, or BytesIO
converter = DocumentConverter()
result = converter.convert(source)
print(result.document.export_to_markdown())

from docling.document_converter import DocumentConverter
from docling.datamodel.base_models import InputFormat
from docling.document_converter import PdfFormatOption
from docling.datamodel.pipeline_options import PdfPipelineOptions

# Basic converter (all formats enabled)
converter = DocumentConverter()

# Restricted formats
converter = DocumentConverter(
    allowed_formats=[InputFormat.PDF, InputFormat.DOCX]
)

# Custom pipeline options
pipeline_options = PdfPipelineOptions()
pipeline_options.do_ocr = True
pipeline_options.do_table_structure = True

converter = DocumentConverter(
    format_options={
        InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)
    }
)

from docling.datamodel.base_models import ConversionStatus

result = converter.convert("document.pdf")

if result.status == ConversionStatus.SUCCESS:
    markdown = result.document.export_to_markdown()
    html = result.document.export_to_html()
    data = result.document.export_to_dict()

from docling.document_converter import DocumentConverter

converter = DocumentConverter()
result = converter.convert("document.pdf")

# Export to different formats
markdown = result.document.export_to_markdown()
html = result.document.export_to_html()
json_data = result.document.export_to_dict()

# Or save directly to file
result.document.save_as_markdown("output.md")
result.document.save_as_html("output.html")
result.document.save_as_json("output.json")

converter = DocumentConverter()
result = converter.convert("https://example.com/document.pdf")

from io import BytesIO
from docling.datamodel.base_models import DocumentStream

with open("document.pdf", "rb") as f:
    buf = BytesIO(f.read())

source = DocumentStream(name="document.pdf", stream=buf)
result = converter.convert(source)

from docling.datamodel.base_models import InputFormat
from docling.datamodel.pipeline_options import PdfPipelineOptions
from docling.document_converter import DocumentConverter, PdfFormatOption

# Configure PDF-specific options
pipeline_options = PdfPipelineOptions()
pipeline_options.do_ocr = True
pipeline_options.ocr_options.lang = ["en", "es"]
pipeline_options.do_table_structure = True
pipeline_options.generate_page_images = True

converter = DocumentConverter(
    format_options={
        InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)
    }
)

converter = DocumentConverter()

# Limit file size (bytes) and page count
result = converter.convert(
    "large_document.pdf",
    max_file_size=20_971_520,  # 20 MB
    max_num_pages=100
)

# Access document structure
doc = result.document

# Content items (lists)
doc.texts         # TextItem instances (paragraphs, headings, etc.)
doc.tables        # TableItem instances
doc.pictures      # PictureItem instances
doc.key_value_items  # Key-value pairs

# Structure (tree nodes)
doc.body          # Main content hierarchy
doc.furniture     # Headers, footers, page numbers
doc.groups        # Lists, chapters, sections

# Iterate all elements in reading order
for item, level in doc.iterate_items():
    print(f"{'  ' * level}{item.label}: {item.text[:50]}")

from docling.datamodel.pipeline_options import (
    PdfPipelineOptions,
    EasyOcrOptions,
    TesseractOcrOptions,
    TesseractCliOcrOptions,
    OcrMacOptions,
    RapidOcrOptions
)

# EasyOCR (default)
pipeline_options = PdfPipelineOptions()
pipeline_options.do_ocr = True
pipeline_options.ocr_options = EasyOcrOptions(lang=["en", "de"])

# Tesseract
pipeline_options = PdfPipelineOptions()
pipeline_options.do_ocr = True
pipeline_options.ocr_options = TesseractOcrOptions(lang=["eng", "deu"])

# RapidOCR
pipeline_options = PdfPipelineOptions()
pipeline_options.do_ocr = True
pipeline_options.ocr_options = RapidOcrOptions()

from docling.datamodel.pipeline_options import (
    PdfPipelineOptions,
    TableFormerMode
)

pipeline_options = PdfPipelineOptions()
pipeline_options.do_table_structure = True

# Use cell matching (map to PDF cells)
pipeline_options.table_structure_options.do_cell_matching = True

# Or use predicted cells
pipeline_options.table_structure_options.do_cell_matching = False

# Choose accuracy mode
pipeline_options.table_structure_options.mode = TableFormerMode.ACCURATE

pipeline_options = PdfPipelineOptions()
pipeline_options.generate_page_images = True  # Needed for HTML export with images

# Export with embedded images
result.document.save_as_html(
    "output.html",
    image_mode=ImageRefMode.EMBEDDED
)

from docling.datamodel.base_models import ConversionStatus

result = converter.convert("document.pdf")

if result.status == ConversionStatus.SUCCESS:
    print("Conversion successful")
elif result.status == ConversionStatus.PARTIAL_SUCCESS:
    print("Partial conversion:")
    for error in result.errors:
        print(f"  {error.error_message}")
else:  # FAILURE
    print("Conversion failed:")
    for error in result.errors:
        print(f"  {error.error_message}")

# Continue processing on errors
results = converter.convert_all(
    ["doc1.pdf", "doc2.pdf", "doc3.pdf"],
    raises_on_error=False
)

for result in results:
    if result.status == ConversionStatus.SUCCESS:
        result.document.save_as_markdown(f"{result.input.file.stem}.md")
    else:
        print(f"Failed: {result.input.file}")

# Basic conversion
docling document.pdf

# Convert to specific output
docling --to markdown document.pdf

# With custom model path
docling --artifacts-path /path/to/models document.pdf

# Using VLM pipeline
docling --pipeline vlm --vlm-model granite_docling document.pdf

from docling.document_converter import DocumentConverter
from langchain_text_splitters import MarkdownTextSplitter

converter = DocumentConverter()
result = converter.convert("document.pdf")
markdown = result.document.export_to_markdown()

splitter = MarkdownTextSplitter(chunk_size=1000)
chunks = splitter.split_text(markdown)

from docling.document_converter import DocumentConverter
from docling.chunking import HybridChunker
from llama_index.core import Document

converter = DocumentConverter()
result = converter.convert("document.pdf")

chunker = HybridChunker()
chunks = list(chunker.chunk(result.document))

documents = [
    Document(text=chunk.text, metadata=chunk.meta.export_json_dict())
    for chunk in chunks
]