Source: https://seerepo.com/r/Unstructured-IO/unstructured/built
Markdown source: https://seerepo.com/r/Unstructured-IO/unstructured/built.md
Description: unstructured is an HTML repo. It uses AI through langdetect, spaCy, and unstructured-client. It has 285,496 written lines, with 131 test files.

# What is unstructured built with?

unstructured is an HTML repo. It uses AI through langdetect, spaCy, and unstructured-client, makes its content with html5lib, python-oxmsg, lxml, beautifulsoup4, python-magic, and 2 more, and deploys with psutil. It has 285,496 written lines, with 131 test files.

Read on November 7, 2026, at commit 293d235.

Repository: https://github.com/Unstructured-IO/unstructured

## Backend

### AI

- **langdetect**: 2 files
- **[spaCy](https://seerepo.com/uses/spacy)**: 1 file
- **unstructured-client**: 1 file

## Support

### Content

- **html5lib**
- **python-oxmsg**
- **[lxml](https://seerepo.com/uses/lxml)**: 9 files
- **[beautifulsoup4](https://seerepo.com/uses/beautifulsoup4)**: 5 files
- **python-magic**: 2 files
- **[filetype](https://seerepo.com/uses/filetype)**: 1 file
- **[nh3](https://seerepo.com/uses/nh3)**: 1 file

### Deploy

- **[psutil](https://seerepo.com/uses/psutil)**: 1 file

### Tools

- **memray**
- **py-spy**
- **snakeviz**
- **typing-extensions**: 13 files
- **Numba**: 2 files
- **installer**: 1 file

### Other

- **certifi**
- **python-iso639**
- **NumPy**: 24 files
- **requests**: 4 files
- **tqdm**: 2 files
- **charset-normalizer**: 1 file
- **emoji**: 1 file
- **filelock**: 1 file
- **rapidfuzz**: 1 file
- **regex**: 1 file
- **wrapt**: 1 file

## Other repos with a similar stack

- [assafelovic/gpt-researcher](https://seerepo.com/r/assafelovic/gpt-researcher/built): langdetect, unstructured-client, html5lib, python-oxmsg, lxml, beautifulsoup4, python-magic, filetype, psutil · [Compare](https://seerepo.com/compare/assafelovic/gpt-researcher/vs/Unstructured-IO/unstructured)
- [bojieli/ai-agent-book](https://seerepo.com/r/bojieli/ai-agent-book/built): lxml, beautifulsoup4, python-magic, psutil · [Compare](https://seerepo.com/compare/bojieli/ai-agent-book/vs/Unstructured-IO/unstructured)
- [run-llama/llama_index](https://seerepo.com/r/run-llama/llama_index/built): lxml, beautifulsoup4, filetype, psutil · [Compare](https://seerepo.com/compare/run-llama/llama_index/vs/Unstructured-IO/unstructured)
- [ray-project/ray](https://seerepo.com/r/ray-project/ray/built): lxml, beautifulsoup4, nh3, psutil · [Compare](https://seerepo.com/compare/ray-project/ray/vs/Unstructured-IO/unstructured)
- [HKUDS/Vibe-Trading](https://seerepo.com/r/HKUDS/Vibe-Trading/built): html5lib, lxml, beautifulsoup4, nh3 · [Compare](https://seerepo.com/compare/HKUDS/Vibe-Trading/vs/Unstructured-IO/unstructured)
- [onyx-dot-app/onyx](https://seerepo.com/r/onyx-dot-app/onyx/built): unstructured-client, lxml, beautifulsoup4, psutil · [Compare](https://seerepo.com/compare/onyx-dot-app/onyx/vs/Unstructured-IO/unstructured)

## Frequently asked questions

### What language is unstructured written in?

unstructured is written in HTML, with 285,496 written lines.

### Does unstructured use AI?

Yes. unstructured uses AI through langdetect, spaCy, and unstructured-client.

### Does unstructured have tests?

Yes. unstructured has 131 test files.

### Which repos have a stack like unstructured's?

The ones that share most of its stack: assafelovic/gpt-researcher, bojieli/ai-agent-book, and run-llama/llama_index.

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.