This project consists of several components for processing, analyzing, and exploring Supreme Court cases. The main components are:
- MongoDB Database
- Neo4j Account
- Pinecone Account
- Clone the repository
- Install dependencies:
- In the root directory, install Python dependencies using Poetry:
poetry install
- In the
explorer
directory, install Node.js dependencies:cd explorer pnpm install
- In the root directory, install Python dependencies using Poetry:
- Set up environment variables in a
.env
file:- NEO4J_URI
- NEO4J_USERNAME
- NEO4J_PASSWORD
- MONGODB_USERNAME
- MONGODB_PASSWORD
- MONGODB_HOST
- MONGODB_DATABASE
- PINECONE_API_KEY
- OPENAI_API_KEY
The data processing scripts are located in Jupyter notebooks:
process_raw.ipynb
: Fetches and processes raw case dataprocess_scotus.ipynb
: Processes SCOTUS cases and generates embeddings
Once you complete processing the data, you can start the application by running the following in the explorer
directory:
pnpm dev