i ideas / repo launcher
docling-project avatar

docling-project/docling

★ 70,447PythonMIT94

Get your documents ready for gen AI

What it is

Docling simplifies document processing by parsing diverse formats — including advanced PDF understanding — and providing seamless integrations with the generative AI ecosystem. 🗂️ Parsing of multiple document formats including PDF, DOCX, PPTX, XLSX, HTML, EPUB, Apple Pages, Numbers & Keynote, WAV, MP3, WebVTT, Box Notes, email formats (EML, MSG), iCalendar (ICS), images (PNG, TIFF, JPEG, ...), LaTeX, DocLang, plain text, and more 📑 Advanced PDF understanding incl. page layout, reading order, table structure, code, formulas, image classification, and more 🧬 A unified, expressive DoclingDocument representation format ↪️ Various export formats and options, including Markdown, HTML, WebVTT,…

When to use it

Reach for docling when you need semantic search, embeddings, scraping or turning documents into LLM-ready data — it's written in Python and fits stacks tagged ai, convert, document-parser, document-parsing.

Category
RAG, Search & Data
Also in
—
Stars
70,447
Forks
5,312
Last push
today
Created
2024-07-09
Open issues
972
Website
docling-project.github.io/docling
#ai#convert#document-parser#document-parsing#documents#docx#html#markdown#pdf#pdf-converter#pdf-to-json#pdf-to-text#pptx#tables

Quick start

$ git clone https://github.com/docling-project/docling.git

Hand it to your AI

Read https://ideas.asveas.com/r/docling-project/docling.md and help me add docling-project/docling to my project. Explain the setup steps for my stack and show the minimal code to get it working.
RAG, Search & DataMarkdown .mdOpen on GitHub ↵

Alternatives to docling

All RAG, Search & Data →
firecrawl avatarfirecrawlSupercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥★ 201kinfiniflow avatarragflowRAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.★ 94kunclecode avatarcrawl4aiOfficial Crawl4AI Cloud: a hosted web scraping, extraction, and search API for AI agents. Free API key, 1,000 credits a month, no card. Fully open source: this repo is the Apache-2.0 crawler that powers it, and you can self-host it.★ 87.2kmem0ai avatarmem0The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.★ 68.8kmeilisearch avatarmeilisearchA lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications.★ 59.8krun-llama avatarllama_indexLlamaIndex is the document processing platform for AI★ 52.9k

Pairs well with

heygen-com avatarhyperframesWrite HTML. Render video. Built for agents.★ 82.8kprettier avatarprettierPrettier is an opinionated code formatter.★ 52.4kchroma-core avatarchromaSearch infrastructure for AI★ 29.7k

FAQ

What is docling?

docling-project/docling is a retrieval tool on GitHub: Get your documents ready for gen AI Docling simplifies document processing by parsing diverse formats — including advanced PDF understanding — and providing seamless integrations with the generative AI ecosystem.

When should I use docling?

Reach for docling when you need semantic search, embeddings, scraping or turning documents into LLM-ready data — it's written in Python and fits stacks tagged ai, convert, document-parser, document-parsing.

What are the best alternatives to docling?

Popular alternatives in RAG, Search & Data: firecrawl/firecrawl (201k★), infiniflow/ragflow (94k★), unclecode/crawl4ai (87.2k★), mem0ai/mem0 (68.8k★), meilisearch/meilisearch (59.8k★).

Is docling actively maintained?

docling-project/docling looks very actively maintained: the last push was today (2026-11-11), with 70,447 stars and 972 open issues.

What license does docling use?

docling-project/docling is published under the MIT license. Check the repository's LICENSE file before commercial use.