README.md

metadata

title: TherapyNote
app_file: app.py
sdk: gradio
sdk_version: 5.9.0
organization: pxpab

Therapy Session Analysis Pipeline

A Python project that downloads YouTube therapy session captions and extracts structured information using LLMs, LangChain, and LangGraph.

Features

• Downloads captions from YouTube therapy sessions
• Extracts structured information using LLMs and LangChain
• Supports multiple note formats (SOAP, DAP, BIRP, etc.)
• Uses LangGraph for data extraction workflows
• Manages prompts in a dedicated "langhub" directory
• Integrates with LangSmith for conversation and run logging

Prerequisites

• Python 3.9+
• uv package manager
• OpenAI API key
• LangChain API key (for logging)

Installation

1. Clone the repository:

git clone https://github.com/yourusername/therapy-session-analysis.git
cd therapy-session-analysis

2. Install dependencies using uv:

uv pip install -r requirements.txt

3. Set up environment variables:

export OPENAI_API_KEY="your-openai-key"
export LANGCHAIN_API_KEY="your-langchain-key"
export LANGCHAIN_TRACING_V2="true"

Project Structure

project/
├── config/
│   ├── __init__.py
│   └── settings.py
├── langhub/
│   ├── __init__.py
│   └── prompts/
│       ├── __init__.py
│       └── therapy_extraction_prompt.yaml
├── forms/
│   ├── __init__.py
│   └── schemas.py
├── utils/
│   ├── __init__.py
│   ├── youtube.py
│   └── text_processing.py
├── models/
│   ├── __init__.py
│   └── llm_provider.py
├── main.py
├── requirements.txt
└── README.md

Usage

Run the main script:

python main.py

Note Formats

The system supports multiple therapy note formats:

• SOAP (Subjective, Objective, Assessment, Plan)
• DAP (Data, Assessment, Plan)
• BIRP (Behavior, Intervention, Response, Plan)
• And more...

Contributing

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add some amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.