Unstructured
Parse and prepare raw documents for machine learning and data processing.
Scraping, browsers and parsing PyPI Apache-2.0 OCR and document parsing
How Unstructured is used
Unstructured is a dependency in 10 of the 6,211 public GitHub projects set up for AI coding agents that we scanned, too few to describe it from them alone. Our scan also samples projects by dependency (Solana 2,717, Ethereum and EVM 1,533, 3D and games 2,862, agent frameworks and SDKs 11,237); counting those, it appears in 231 projects, and what it is used with below comes from all of them. Projects that use it most often also use LangChain (92.6%), python-dotenv (89.2%), OpenAI Python Library (79.7%).
Unstructured popularity over time
Gid Score 59: downloads 60, use in agent projects 63, GitHub stars 57, downloads trend 53 (each 0-100). How it is calculated.
Often used with Unstructured
| LangChain | 92.6% of Unstructured projects · 45.7× more than average |
|---|---|
| python-dotenv | 89.2% of Unstructured projects · 9.7× more than average |
| OpenAI Python Library | 79.7% of Unstructured projects · 20.2× more than average |
| Pydantic | 76.6% of Unstructured projects · 8.9× more than average |
| Requests | 74.9% of Unstructured projects · 11.0× more than average |
| tiktoken (Python) | 73.6% of Unstructured projects · 80.2× more than average |
| Beautiful Soup | 70.1% of Unstructured projects · 32.5× more than average |
| PyYAML | 65.8% of Unstructured projects · 11.1× more than average |
From all 231 projects in our scan that use Unstructured, including the dependency samples.
By coding agent
| GitHub Copilot | 0.2% of projects set up for it |
|---|
Share of public repos configured for each agent that list Unstructured as a dependency.
Install
| Package | pip install unstructured |
|---|---|
| Main stacks | Python (228), Next.js (3) |
| Example projects | assafelovic/gpt-researcher, onlyphantom/llm-python, Azure/intro-to-intelligent-apps, aihes/LangChain-Tutorials-and-Examples, OPPO-PersonalAI/TaskCraft |
Alternatives to Unstructured
In our scan, none of the most used tools in Scraping, browsers and parsing does the same job as Unstructured: they are add-ons, companions or tools for a different task.
More in Scraping, browsers and parsing: Beautiful Soup Puppeteer lxml Playwright Core Playwright (Python) Cheerio fast-xml-parser jsonc-parser