docling-project/docling

Get your documents ready for gen AI

What it solves

Docling simplifies the process of converting diverse and complex document formats into a structured, machine-readable format suitable for generative AI applications. It addresses the challenge of parsing advanced PDF layouts, tables, and multimodal content (like images and audio) that are typically difficult to extract from legacy document formats.

How it works

Docling uses a unified representation format called DoclingDocument to parse various file types—including PDFs, Office documents, images, and even video/audio files—and export them into formats like Markdown, HTML, or JSON. It leverages Visual Language Models (VLMs) such as GraniteDocling for advanced PDF understanding (layout, reading order, and table structure) and Automatic Speech Recognition (ASR) for audio and video transcripts.

Who it’s for

It is designed for developers building AI agents, RAG (Retrieval-Augmented Generation) pipelines, and document processing workflows that need to ingest a wide variety of unstructured data sources.

Highlights

  • Wide Format Support: Parses PDF, DOCX, PPTX, XLSX, HTML, EPUB, Apple Pages, email formats, and video/audio files.
  • Advanced PDF Analysis: Extracts page layout, reading order, table structures, and formulas.
  • Multimodal Capabilities: Includes OCR for scanned documents, ASR for audio/video, and chart understanding to convert charts into tables or code.
  • AI Ecosystem Integration: Native plug-and-play integrations with LangChain, LlamaIndex, Crew AI, and Haystack.
  • Flexible Deployment: Supports local execution for air-gapped environments, an API server, and a CLI.

Related

  • Project
    docling-project/docling-parse

    Docling Parse is a fast, configurable PDF‑parsing library (Python API with a C++ core) that extracts text, words, lines, vector shapes and bitmap images together with their coordinates. It supports both sequential and multi‑threaded parsing, lets you choose what to compute or materialize per page, and includes rendering utilities. Ideal for AI workflows that need layout‑aware document data.

  • Project
    docling-project/docling-graph

    A toolkit that transforms unstructured documents into validated Pydantic objects and directed knowledge graphs for high-precision entity relationship extraction.

  • Dispatch
    Hugging Face Accelerating Document AI

    Hugging Face provides a comprehensive guide to using open-source multimodal models to automate document classification, parsing, and visual question answering for enterprise workflows.

  • Project
    harshankur/officeParser

    officeParser is a TypeScript‑based Node.js and browser library that parses many office file formats (DOCX, PPTX, PDF, LaTeX, etc.) into a strict abstract syntax tree (AST) and can generate the same content back into formats like DOCX, HTML, PDF, Markdown, LaTeX, EPUB and RAG‑ready chunks. It includes a CLI, OCR support, password handling, template‑based mail‑merge, a native PDF engine, and an interactive web visualiser.

  • Project
    magicrew/doc7

    A document conversion tool that turns PDFs, Office files, and images into AI-ready Markdown using multimodal vision models, supporting local inference for privacy and cost-efficiency.