#1313th of 16 in Data and scraping for AI
unstructured
Python library that parses PDFs, Office files and HTML into typed elements
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 15.6k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- HTML
Missed the latest GitHub check; these facts may be older.
Overview
The unstructured library parses documents such as PDF, HTML, Word, email and images into typed elements (titles, narrative text, tables). A single `partition` function detects the file type and routes it to a format-specific parser. It installs from PyPI with per-format extras or runs from a Docker image, and some formats need system packages such as poppler, tesseract and libreoffice.
Who it is for: Developers building RAG or LLM ingestion pipelines over mixed document formats
Strengths
- One `partition` call auto-detects file type and dispatches to format-specific parsers
- Per-format pip extras (docx, pptx, pdf) keep installs smaller for narrow use cases
- Apache-2.0 licensed; multi-platform Docker images for x86_64 and Apple silicon
- Batch ingestion and connectors are available through the separate unstructured-ingest project
Weaknesses
- README's own benchmark lists table cell content accuracy of 0.426 versus 0.866 for the paid API
- PDF, image and Office parsing needs system packages: poppler, tesseract, libreoffice
- Sends anonymous telemetry by default; opt out with DO_NOT_TRACK or SCARF_NO_ANALYTICS
- Highest-quality output is only in the hosted Transform API, not this library
What it needs
- Docker
- Needs poppler-utils, tesseract-ocr, libmagic-dev, libreoffice
Also in Data and scraping for AI
See all 16| Rank | Project | Score |
|---|---|---|
| 1 | mineruDocument parser that converts PDFs, images and Office files to Markdown and JSON | 80 out of 100 |
| 2 | Crawl4AIPython web crawler that converts pages to LLM-ready Markdown and JSON | 78 out of 100 |
| 3 | doclingPython library and CLI that converts PDFs, Office files and more into structured text | 77 out of 100 |
| #4 | markitdownPython tool that converts PDF, Office, HTML and audio files to Markdown for LLMs | 71 out of 100 |
| #5 | FirecrawlWeb scraping and crawling API that returns LLM-ready markdown | 67 out of 100 |