LexAI is a proof-of-concept AI-powered legal research assistant that helps users access location-specific legal information through a simple web interface. By combining large language models with structured jurisdictional data, LexAI delivers clear, tailored answers to everyday legal questions.

• GPT-4 Integration: Uses OpenAI's GPT-4 to generate concise, relevant legal responses.
• Jurisdiction-Specific Search: Preloaded embeddings for Boulder County and Denver, Colorado.
• Semantic Search Engine: Uses cosine similarity for embedding-based document retrieval.
• Modern Web Interface: Built with Gradio for real-time interaction.
• Modular Design: Clean separation of logic for UI, inference, and API handling.
• Fully Tested: Unit tests cover embedding loading, matching logic, and OpenAI API integration.
• Developer Ready: Comes with dev tools like Ruff, Black, pytest, mypy, and test coverage support.

LexAI is an AI-powered legal research assistant that helps users access location-specific legal information through a simple web interface. By combining large language models with structured jurisdictional data, LexAI delivers clear, tailored answers to everyday legal questions.

• GPT-4 Integration: Uses OpenAI's GPT-4 to generate concise, relevant legal responses.
• Jurisdiction-Specific Search: Preloaded embeddings for Boulder County and Denver, Colorado.
• Semantic Search Engine: Uses cosine similarity for embedding-based document retrieval.
• Modern Web Interface: Built with Gradio for real-time interaction.
• Modular Design: Clean separation of logic for UI, inference, and API handling.
• Fully Tested: Unit tests cover embedding loading, matching logic, and OpenAI API integration.
• Developer Friendly: Includes dev tools like Ruff, Black, pytest, mypy, and coverage reports.

git clone https://github.com/alexulanch/lexai.git
cd lexai

This project uses Git LFS to manage large files such as .npz embedding data.

git lfs install
git lfs pull

pip install -r requirements.txt
# For development tools:
pip install -r dev-requirements.txt

Copy the template and add your API key:

cp .env.example .env

Then edit .env and set:

OPENAI_API_KEY=your_openai_api_key

python -m lexai

Then open http://127.0.0.1:7860 in your browser.

.
├── LICENSE
├── README.md
├── assets/
│   └── screenshot.png
├── dev-requirements.txt
├── .env.example
├── lexai/
│   ├── __main__.py
│   ├── config.py
│   ├── core/
│   │   ├── data_loader.py
│   │   ├── match_engine.py
│   │   └── matcher.py
│   ├── data/
│   │   ├── boulder_embeddings.npz
│   │   └── denver_embeddings.npz
│   ├── services/
│   │   ├── lexai_service.py
│   │   └── openai_client.py
│   └── ui/
│       ├── formatters.py
│       └── gradio_interface.py
├── pyproject.toml
├── pytest.ini
├── requirements.txt
└── tests/
    ├── test_data_loader.py
    ├── test_matcher.py
    └── test_openai_client.py

To run tests:

pytest

To check code coverage:

pytest --cov=lexai --cov-report=term

To lint:

ruff check .

To format code:

black .

MIT License

• Built with Gradio
• Powered by OpenAI