docetl 0.2.3

ETL with LLM operations.

📜 DocETL: Powering Complex Document Processing Pipelines

DocETL is a tool for creating and executing data processing pipelines, especially suited for complex document processing tasks. It offers:

1. An interactive UI playground for iterative prompt engineering and pipeline development
2. A Python package for running production pipelines from the command line or Python code

💡 Need Help Writing Your Pipeline?
Want to use an LLM like ChatGPT or Claude to help you write your pipeline? See docetl.org/llms.txt for a big prompt you can copy paste into ChatGPT or Claude, before describing your task.

🌟 Community Projects

• Conversation Generator
• Text-to-speech
• YouTube Transcript Topic Extraction

📚 Educational Resources

• UI/UX Thoughts
• Using Gleaning to Improve Output Quality
• Deep Dive on Resolve Operator

🚀 Getting Started

There are two main ways to use DocETL:

1. 🎮 DocWrangler, the Interactive UI Playground (Recommended for Development)

DocWrangler helps you iteratively develop your pipeline:

• Experiment with different prompts and see results in real-time
• Build your pipeline step by step
• Export your finalized pipeline configuration for production use

DocWrangler is hosted at docetl.org/playground. But to run the playground locally, you can either:

• Use Docker (recommended for quick start): make docker
• Set up the development environment manually

See the Playground Setup Guide for detailed instructions.

2. 📦 Python Package (For Production Use)

If you want to use DocETL as a Python package:

Prerequisites

• Python 3.10 or later
• OpenAI API key

pip install docetl

Create a .env file in your project directory:

OPENAI_API_KEY=your_api_key_here  # Required for LLM operations (or the key for the LLM of your choice)

To see examples of how to use DocETL, check out the tutorial.

2. 🎮 DocWrangler Setup

To run DocWrangler locally, you have two options:

Option A: Using Docker (Recommended for Quick Start)

The easiest way to get the DocWrangler playground running:

1. Create the required environment files:

Create .env in the root directory:

OPENAI_API_KEY=your_api_key_here
BACKEND_ALLOW_ORIGINS=http://localhost:3000,http://127.0.0.1:3000
BACKEND_HOST=0.0.0.0
BACKEND_PORT=8000
BACKEND_RELOAD=True
FRONTEND_HOST=0.0.0.0
FRONTEND_PORT=3000

Create .env.local in the website directory:

OPENAI_API_KEY=sk-xxx
OPENAI_API_BASE=https://api.openai.com/v1
MODEL_NAME=gpt-4o-mini

NEXT_PUBLIC_BACKEND_HOST=localhost
NEXT_PUBLIC_BACKEND_PORT=8000

2. Run Docker:

make docker

This will:

• Create a Docker volume for persistent data
• Build the DocETL image
• Run the container with the UI accessible at http://localhost:3000

To clean up Docker resources (note that this will delete the Docker volume):

make docker-clean

AWS Bedrock

This framework supports integration with AWS Bedrock. To enable:

1. Configure AWS credentials:

aws configure

2. Test your AWS credentials:

make test-aws

3. Run with AWS support:

AWS_PROFILE=your-profile AWS_REGION=your-region make docker

Or using Docker Compose:

AWS_PROFILE=your-profile AWS_REGION=your-region docker compose --profile aws up

Environment variables:

• AWS_PROFILE: Your AWS CLI profile (default: 'default')
• AWS_REGION: AWS region (default: 'us-west-2')

Bedrock models are pefixed with bedrock. See liteLLM docs for more details.

Option B: Manual Setup (Development)

For development or if you prefer not to use Docker:

1. Clone the repository:

git clone https://github.com/ucbepic/docetl.git
cd docetl

2. Set up environment variables in .env in the root/top-level directory:

OPENAI_API_KEY=your_api_key_here
BACKEND_ALLOW_ORIGINS=http://localhost:3000,http://127.0.0.1:3000
BACKEND_HOST=localhost
BACKEND_PORT=8000
BACKEND_RELOAD=True
FRONTEND_HOST=0.0.0.0
FRONTEND_PORT=3000

And create an .env.local file in the website directory with the following:

OPENAI_API_KEY=sk-xxx
OPENAI_API_BASE=https://api.openai.com/v1
MODEL_NAME=gpt-4o-mini

NEXT_PUBLIC_BACKEND_HOST=localhost
NEXT_PUBLIC_BACKEND_PORT=8000

3. Install dependencies:

make install      # Install Python package
make install-ui   # Install UI dependencies

Note that the OpenAI API key, base, and model name are for the UI assistant only; not the DocETL pipeline execution engine.

4. Start the development server:

make run-ui-dev

5. Visit http://localhost:3000/playground to access the interactive UI.

🛠️ Development Setup

If you're planning to contribute or modify DocETL, you can verify your setup by running the test suite:

make tests-basic  # Runs basic test suite (costs < $0.01 with OpenAI)

For detailed documentation and tutorials, visit our documentation.