How to use Docling: what you can do with it

3 use cases

• Convert a complex PDF with tables into clean Markdown

  Install Docling and convert a paper or report, keeping layout, reading order and tables intact.

  • REPO docling-project/docling
  • Claude Code
  • Codex
  • Cursor
  • Research
  • Beginner
  View prompt

  Install docling-project/docling and convert <pdf path or URL> to Markdown with the docling CLI. Then run it again with the granite_docling VLM pipeline and tell me which version handled the tables better.

  Share Email me this

• Prepare a document folder for a RAG index

  Use the Python API to convert mixed documents into Markdown before chunking them into your retriever.

  • REPO docling-project/docling
  • Claude Code
  • Codex
  • Cursor
  • Research
  • Intermediate
  View prompt

  Using docling-project/docling, write a Python script that converts every file in <folder> with DocumentConverter, saves the Markdown with export_to_markdown, and loads the results into <LangChain or LlamaIndex> for retrieval. Run it and report any files that failed.

  Share Email me this

• Let your AI agent read documents through Docling

  Connect Docling to an agent through its MCP server or run it as a service with docling-serve.

  • REPO docling-project/docling
  • Claude Code
  • Codex
  • Cursor
  • Research
  • Intermediate
  View prompt

  Set up docling-project/docling for my agent using its MCP server, following the Docling MCP docs. Then parse <document> through it and summarise the tables it found.

  Share Email me this

Quick start with Docling

1. Check you have what it needs: Python 3.10 or higher; macOS, Linux or Windows on x86_64 or arm64; Optional: a GPU for faster VLM pipelines such as GraniteDocling.
2. Open docling-project/docling on GitHub and read the README and license.
3. Install with pip install docling
4. Convert a document from a URL or a local path with docling https://arxiv.org/pdf/2206.01062
5. Open the generated .md file in the current directory
6. Try the visual language model pipeline with docling --pipeline vlm --vlm-model granite_docling https://arxiv.org/pdf/2206.01062 and compare

These steps come from our top use case, Convert a complex PDF with tables into clean Markdown, which also has a copy-paste agent prompt.

Using the Deduped MCP, get the setup steps for docling-project/docling

claude mcp add --transport http deduped https://dedupedai.com/mcp

Best AI repos for Research

About this repo

• Who it is forDevelopers building RAG, search or agent pipelines who need complex PDFs and office files turned into structured, faithful text.
• Why it is hot70k stars, talked about in 2 AI sources we track
• LanguagePython
• Sourcegithub.com/docling-project/docling · Back to Hot repos

Requirements

• Python 3.10 or higher
• macOS, Linux or Windows on x86_64 or arm64
• Optional: a GPU for faster VLM pipelines such as GraniteDocling

Related repos

• Trended earlier REPO lxsssssss/pdf-translate PDF Translate A Python agent skill that rebuilds a translated document as a layout-preserving vector PDF through a headless browser, then audits the result against the original PDF.
• Trended earlier REPO firecrawl/firecrawl Firecrawl Firecrawl is an API that searches, scrapes, crawls and interacts with the web and returns clean markdown, structured JSON or screenshots for AI agents. It handles JavaScript-heavy pages, proxies and rate limits, parses PDFs and DOCX, can click and type before extracting, and plugs into agents as a skill or an MCP server. It is open source and also offered as a hosted service with an API key.
• Trended earlier REPO opendatalab/MinerU MinerU MinerU turns PDFs, images and office documents into LLM-ready Markdown and JSON. Version 4 adds four parsing tiers (Flash, Basic, Standard, Advanced), a local document library with search and stable citation locators for page and block continuation, a Python SDK, a V1 API, a Gradio WebUI and an agent skill, with CPU inference plus automatic GPU acceleration on Intel, AMD, NVIDIA and Apple Silicon.