Docling
Hacker ApprovedRanked 3 of 8 document parsers by recommenders
Free open-source tool that turns PDFs and tables into markdown and text with traceable positions. Complex tables and multi-column layouts can lose structure, and it is slow.
Free open-source tool that turns PDFs and tables into markdown and text with traceable positions. Complex tables and multi-column layouts can lose structure, and it is slow.
23 people gave an opinion
- recommend it
- 19
- criticize it
- 4
- approval share
- 83%
Recommended in 10 of 13 months
- November 2025: recommended
- December 2025: recommended
- January 2026: not recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: not recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: recommended
- September 2026: recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 19 people recommend itNeeds 10 or more, met.
- 4.8 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 10 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Good at PDF and table extraction
“I was shocked at how good it was at the couple document extraction tasks I threw it at.”
Comment from 30 Apr 2026 in “Granite 4.1: IBM's 8B Model Matching 32B MoE” “Docling and MinerU are great for structured output like markdown and table extraction”
Comment from 13 Apr 2026 in “TurboOCR: 270–1200 img/s OCR with Paddle and TensorRT (C++/CUDA, FP16)” “it works well for parsing PDF and XLSX”
Comment from 12 Aug 2026 in “LLM Is Not a PDF Parser: Use OpenDataLoader First” - Comment from 29 Nov 2025 in “Show HN: Self-hosted RAG for docs and code (FastAPI, Docling, ChromaDB)”
Recommended as a starting point
“I suggest take a look at this https://github.com/docling-project/docling”
Comment from 4 Sep 2026 in “Ask HN: Who is using MCP in production?” “there are options like Docling or LlamaParse for proper preprocessing”
Comment from 13 Jun 2026 in “A PDF that changes based on who is reading” “If you are starting new I would recommend looking at docling.”
Comment from 2 Apr 2026 in “Google releases Gemma 4 open models” Converts documents to markdown and text
“Docling and MinerU are great for structured output like markdown and table extraction”
Comment from 13 Apr 2026 in “TurboOCR: 270–1200 img/s OCR with Paddle and TensorRT (C++/CUDA, FP16)” “did an astounding job of converting it all into .txt and .md”
Comment from 20 Jul 2026 in “Qwen3.8 is launching and going open-weight soon” Loads many formats including spreadsheets
“It loads .xls, .xlsx, .csv and 50+ more formats”
Comment from 26 Oct 2026 on Hacker News “it works well for parsing PDF and XLSX”
Comment from 12 Aug 2026 in “LLM Is Not a PDF Parser: Use OpenDataLoader First”
What people warn about
Each mark is one comment
Poor results with other models
“Using docling with different models has produced much worse results.”
Comment from 15 Jan 2026 in “Ask HN: How are you doing RAG locally?” “docling (gives me garbage, I must use it wrong)”
Comment from 23 Jun 2026 in “Unlimited OCR: One-Shot Long-Horizon Parsing”
Other document parsers people recommend
The four most recommended other document parsers, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Pandoc | 142 | 28 | 84% | 13 | 10 yrs6 owners | Approved |
| Tesseract OCR | 32 | 28 | 53% | 12 | — | — |
| DoclingThis page | 19 | 4 | 83% | 10 | — | Approved |
| Mozilla Readability | 10 | 1 | 91% | 6 | — | Approved |
| Zpdf | 8 | 6 | 57% | 1 | — | — |
What people said
20 of the 24 comments that mention it, newest first. Each links to the original comment.
“It loads .xls, .xlsx, .csv and 50+ more formats”
“purely local, even though it's now AI-friendly too”
“I suggest take a look at this https://github.com/docling-project/docling”
“it works well for parsing PDF and XLSX”
“the former feels like a bunch of scripts and glue logic”
“did an astounding job of converting it all into .txt and .md”
“smaller, specialized models with the right tooling might be more effective (and efficient) at this than throwing everything at Opus”
“docling (gives me garbage, I must use it wrong)”
“there are options like Docling or LlamaParse for proper preprocessing”
“I was shocked at how good it was at the couple document extraction tasks I threw it at.”
“Docling and MinerU are great for structured output like markdown and table extraction”
“If you are starting new I would recommend looking at docling.”
“Docling and Marker work pretty well but are very slow”
“preserving page numbers and bounding boxes so you can trace any extracted value back to its exact position in the original document”
“Using docling with different models has produced much worse results.”
“works well for simpler text-heavy docs without complex layouts, but the moment you introduce tables or multi-column stuff it doesn't maintain layout well”
“Docs said it was VLM-ready, which I spent lots of hours finding out was not true”
“handles PDFs/Tables really well”
“to simplify document processing with advanced PDF understanding, OCR support, and seamless AI integrations”
“docling finished in 20s (with pretty good results)”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.