{"slug": "docling", "name": "Docling", "category": "selfhosted", "category_name": "Self-hosted and home server", "description": "", "recommenders": 4, "commenters": 6, "warners": 0, "score": 4.216, "rising": 2.35, "first": "2026-02-22", "latest": "2026-09-04", "why": "I tested docling by giving it the Ronin TTRPG rulebook PDF and it did an astounding job of converting it all into .txt and .md.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 5, "neutral": 1, "compare": 1, "warn": 0}, "spark": [0, 0, 0, 0, 0, 0, 0, 1, 1, 2, 1, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "I tested docling by giving it the Ronin TTRPG rulebook PDF and it did an astounding job of converting it all into .txt and .md.", "icon": true, "domain": null, "github_repo": "github.com/docling-project/docling", "official_url": "https://github.com/docling-project/docling", "pricing": "", "aliases": ["Docling", "docling"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 793004177, "item_id": 49562761, "url": "https://news.ycombinator.com/item?id=49562761", "by": "navigate8310", "date": "2026-09-04", "stance": "recommend", "quote": "I suggest take a look at this https://github.com/docling-project/docling as well.", "excerpt": "I used Mistral 3. It costed me literally pennies. My workflow was kinda rudimentary but it worked really well. I suggest take a look at this https://github.com/docling-project/docling as well.", "context": "", "use_case": "document OCR/parsing", "switched_from": "", "story": "Ask HN: Who is using MCP in production?"}, {"id": 788337392, "item_id": 49271087, "url": "https://news.ycombinator.com/item?id=49271087", "by": "Schlagbohrer", "date": "2026-08-12", "stance": "recommend", "quote": "I use docling and it works well for parsing PDF and XLSX", "excerpt": "I use docling and it works well for parsing PDF and XLSX", "context": "", "use_case": "parsing PDF and XLSX", "switched_from": "", "story": "LLM Is Not a PDF Parser: Use OpenDataLoader First"}, {"id": 786973984, "item_id": 49185874, "url": "https://news.ycombinator.com/item?id=49185874", "by": "Gayithri2026", "date": "2026-08-05", "stance": "recommend", "quote": "Docling for structure-aware parsing", "excerpt": "Location: San Jose, CA (SF Bay Area) Remote: Yes Willing to relocate: No Technologies: Python, FastAPI, PostgreSQL/pgvector, RAG, LangChain, PydanticAI, Celery, Redis, Docker, AWS, Langfuse, Java, Spring Boot R\u00e9sum\u00e9/CV: https://github.com/Gayithri606/resume/blob/main/GayithriPonnapalli-Resume.pdf Email: gayithri@pojoai.com AI engineer building RAG chatbots and AI-driven workflow automation. Five years of production J", "context": "AI engineer building RAG chatbots", "use_case": "document parsing for RAG", "switched_from": "", "story": "Ask HN: Who wants to be hired? (August 2026)"}, {"id": 783628992, "item_id": 48976812, "url": "https://news.ycombinator.com/item?id=48976812", "by": "Schlagbohrer", "date": "2026-07-20", "stance": "recommend", "quote": "I tested docling by giving it the Ronin TTRPG rulebook PDF and it did an astounding job of converting it all into .txt and .md.", "excerpt": "I have been using the docling software for PDF and XLSX reading/viewing/comprehension by my local qwen3.6. Claude was telling me that docling includes within it a very small LLM model just to assist with what is basically \"super OCR\". We are definitely in this era of ultra-mega-huge frontier models and super-tiny-micro models, all finding their uses. On an aside I tested docling by giving it the Ronin TTRPG rulebook ", "context": "", "use_case": "PDF and XLSX reading/conversion", "switched_from": "", "story": "Qwen3.8 is launching and going open-weight soon"}, {"id": 774574609, "item_id": 48410913, "url": "https://news.ycombinator.com/item?id=48410913", "by": "blfr", "date": "2026-06-05", "stance": "recommend", "quote": "with a docling container for large pdfs. Works like a charm. I highly recommend it.", "excerpt": "I would rather we be great at tech and sovereign as byproduct than try to copy Americans, poorly. Trump's admin is trying to put breaks on new AI models. Meanwhile we will make procurement even heavier and slower with additional requirements and add more regulation for checkbox enforcement so massive inefficient enterprises can keep newcomers out. That said it was a cool material to test my new open webui setup with ", "context": "", "use_case": "parsing large PDFs", "switched_from": "", "story": "Communication on European Tech Sovereignty, and an EU Open-Source Strategy"}]}], "caveats": [], "who": [{"by": "Gayithri2026", "context": "AI engineer building RAG chatbots", "url": "https://news.ycombinator.com/item?id=49185874", "date": "2026-08-05"}], "tags": [], "use_cases": ["document ocr/parsing", "parsing pdf and xlsx", "document parsing for rag", "document extraction", "pdf and xlsx reading/conversion", "parsing large pdfs"], "compared": [{"slug": "gemini", "name": "Gemini", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "open-webui", "name": "Open WebUI", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=48966120", "title": "Qwen3.8 is launching and going open-weight soon", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=49548600", "title": "Ask HN: Who is using MCP in production?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49270775", "title": "LLM Is Not a PDF Parser: Use OpenDataLoader First", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49156682", "title": "Ask HN: Who wants to be hired? (August 2026)", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48410602", "title": "Communication on European Tech Sovereignty, and an EU Open-Source Strategy", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47111402", "title": "FORTHought: Self hosted AI stack for physics labs (and more) built on OpenWebUI", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {"neutral": 1}, "2026-03": {}, "2026-04": {}, "2026-05": {}, "2026-06": {"recommend": 1}, "2026-07": {"recommend": 1, "compare": 1}, "2026-08": {"recommend": 2}, "2026-09": {"recommend": 1}, "2026-10": {}}, "quotes": [{"id": 793004177, "item_id": 49562761, "url": "https://news.ycombinator.com/item?id=49562761", "by": "navigate8310", "date": "2026-09-04", "stance": "recommend", "quote": "I suggest take a look at this https://github.com/docling-project/docling as well.", "excerpt": "I used Mistral 3. It costed me literally pennies. My workflow was kinda rudimentary but it worked really well. I suggest take a look at this https://github.com/docling-project/docling as well.", "context": "", "use_case": "document OCR/parsing", "switched_from": "", "story": "Ask HN: Who is using MCP in production?"}, {"id": 788337392, "item_id": 49271087, "url": "https://news.ycombinator.com/item?id=49271087", "by": "Schlagbohrer", "date": "2026-08-12", "stance": "recommend", "quote": "I use docling and it works well for parsing PDF and XLSX", "excerpt": "I use docling and it works well for parsing PDF and XLSX", "context": "", "use_case": "parsing PDF and XLSX", "switched_from": "", "story": "LLM Is Not a PDF Parser: Use OpenDataLoader First"}, {"id": 786973984, "item_id": 49185874, "url": "https://news.ycombinator.com/item?id=49185874", "by": "Gayithri2026", "date": "2026-08-05", "stance": "recommend", "quote": "Docling for structure-aware parsing", "excerpt": "Location: San Jose, CA (SF Bay Area) Remote: Yes Willing to relocate: No Technologies: Python, FastAPI, PostgreSQL/pgvector, RAG, LangChain, PydanticAI, Celery, Redis, Docker, AWS, Langfuse, Java, Spring Boot R\u00e9sum\u00e9/CV: https://github.com/Gayithri606/resume/blob/main/GayithriPonnapalli-Resume.pdf Email: gayithri@pojoai.com AI engineer building RAG chatbots and AI-driven workflow automation. Five years of production J", "context": "AI engineer building RAG chatbots", "use_case": "document parsing for RAG", "switched_from": "", "story": "Ask HN: Who wants to be hired? (August 2026)"}, {"id": 783671969, "item_id": 48979498, "url": "https://news.ycombinator.com/item?id=48979498", "by": "jchoksi", "date": "2026-07-20", "stance": "compare", "quote": "the former feels like a bunch of scripts and glue logic", "excerpt": "An alternative to Docling is Xberg: https://github.com/xberg-io/xberg \"A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured information from PDFs, Office documents, images, and 97+ formats. Available for Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, R, C, TypeScript (Node/Bun/Wasm/Deno)- or use via CLI, REST API, or MCP server.\" Amongst other things, you can use", "context": "layman", "use_case": "document extraction", "switched_from": "", "story": "Qwen3.8 is launching and going open-weight soon"}, {"id": 783628992, "item_id": 48976812, "url": "https://news.ycombinator.com/item?id=48976812", "by": "Schlagbohrer", "date": "2026-07-20", "stance": "recommend", "quote": "I tested docling by giving it the Ronin TTRPG rulebook PDF and it did an astounding job of converting it all into .txt and .md.", "excerpt": "I have been using the docling software for PDF and XLSX reading/viewing/comprehension by my local qwen3.6. Claude was telling me that docling includes within it a very small LLM model just to assist with what is basically \"super OCR\". We are definitely in this era of ultra-mega-huge frontier models and super-tiny-micro models, all finding their uses. On an aside I tested docling by giving it the Ronin TTRPG rulebook ", "context": "", "use_case": "PDF and XLSX reading/conversion", "switched_from": "", "story": "Qwen3.8 is launching and going open-weight soon"}, {"id": 774574609, "item_id": 48410913, "url": "https://news.ycombinator.com/item?id=48410913", "by": "blfr", "date": "2026-06-05", "stance": "recommend", "quote": "with a docling container for large pdfs. Works like a charm. I highly recommend it.", "excerpt": "I would rather we be great at tech and sovereign as byproduct than try to copy Americans, poorly. Trump's admin is trying to put breaks on new AI models. Meanwhile we will make procurement even heavier and slower with additional requirements and add more regulation for checkbox enforcement so massive inefficient enterprises can keep newcomers out. That said it was a cool material to test my new open webui setup with ", "context": "", "use_case": "parsing large PDFs", "switched_from": "", "story": "Communication on European Tech Sovereignty, and an EU Open-Source Strategy"}, {"id": 753782451, "item_id": 47111403, "url": "https://news.ycombinator.com/item?id=47111403", "by": "MariosAdamidis", "date": "2026-02-22", "stance": "neutral", "quote": "I try to run most stuff locally, for example docling, embed rerank vlm", "excerpt": "In the past year i have been learning and experimenting, and have assembled a stack which now seems to me like a solid foundation for lab applications such as data processing. As a PhD student in the Greek reality, my budget was tight especially initially so i have made my basis mostly on the free vertex gemini trial. I have customized an existing gemini pipeline (thank you owndev) to better handle multi-round native", "context": "", "use_case": "local document processing", "switched_from": "", "story": "FORTHought: Self hosted AI stack for physics labs (and more) built on OpenWebUI"}]}