Skip to content
  1. Home
  2. AI tools
  3. Docling

Docling

Parse PDFs, Office files and more into structured data for LLMs

What it is

A Python library and CLI that parses many document formats, including PDF, DOCX, PPTX, XLSX, HTML, audio and images, into one structured document representation. Its PDF handling covers layout, reading order, tables, code and formulas, and it exports to Markdown, HTML and other formats. For people preparing documents for RAG.

Good for

  • Convert PDFs with tables into Markdown
  • Prepare mixed-format documents for RAG
  • Extract reading order from scanned layouts

Install or run

pip install docling

Command as given in the project README. Read the repository before you run anything on your machine.

What you need

Python

Worth knowingLayout models make it heavier and slower than plain-text converters, especially on large PDFs without a GPU.

Sources

The summary is ours, written from the README. Spotted an error? See how we work.

More for data & research

See the topic →
  • MarkItDown

    microsoft/markitdown

    Lightweight Python utility that converts files to Markdown for LLMs

    ToolGitHub stars: 195k
  • RAGFlow

    infiniflow/ragflow

    Self-hosted RAG engine with document parsing and agent templates

    ToolGitHub stars: 94k
  • serviette

    pathwaycom/serviette

    No-code RAG server that keeps answers in sync with a document folder

    ToolGitHub stars: 59k
  • LightRAG

    HKUDS/LightRAG

    Graph-based RAG library and server with pluggable storage backends

    ToolGitHub stars: 41k