Turn Messy Document Collections Into Structured Rows With Docetl

---
name: "Turn messy document collections into structured rows with DocETL"
slug: "turn-messy-document-collections-into-structured-rows-with-docetl"
description: "Define repeatable extraction pipelines that pull fields from large document collections, normalize outputs, and audit failures across the corpus."
github_stars: 3707
verification: "security_reviewed"
source: "https://github.com/ucbepic/docetl"
author: "UCB EPIC"
publisher_type: "organization"
category: "Data Extraction & Transformation"
framework: "Multi-Framework"
tool_ecosystem:
  github_repo: "ucbepic/docetl"
  github_stars: 3707
---

# Turn messy document collections into structured rows with DocETL

Define repeatable extraction pipelines that pull fields from large document collections, normalize outputs, and audit failures across the corpus.

## Prerequisites

Python 3.10+, DocETL, document corpus, extraction configuration

## Installation

Use the upstream install or setup path that matches your environment:
- Use Docker (recommended for quick start): make docker
- pip install docetl
- Run Docker:
- make docker

Requirements and caveats from upstream:
- A Python package for running production pipelines from the command line or Python code
- ### 2. 📦 Python Package (For Production Use)
- If you want to use DocETL as a Python package:

Basic usage or getting-started notes:
- ## 🚀 Getting Started
- DocWrangler is hosted at [docetl.org/playground](https://docetl.org/playground). But to run the playground locally, you can either:
- OpenAI API key

- Source: https://github.com/ucbepic/docetl
- Extracted from upstream docs: https://raw.githubusercontent.com/ucbepic/docetl/HEAD/README.md

## Documentation

- https://docetl.org/

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/turn-messy-document-collections-into-structured-rows-with-docetl/)