LLM Experiments

This project is designed to experiment with language models using a Streamlit app interface. It allows users to interact with a language model chain to generate responses based on input messages.

Setup

To set up the project, ensure you have Python 3.12 installed. Use Poetry to manage dependencies.

1. Install dependencies:

   poetry install

2. Set OPENAI_API_KEY as an environment variable:

Running

To run the Streamlit app, execute the following command:

streamlit run app.py

This will start a local server, and you can interact with the app through your web browser.

Testing

To run the tests, use pytest:

pytest tests/

This will execute the test suite to ensure the chain invocation works as expected.

Building and Running the Docker Image

To build the Docker image, use the following command:

docker build --target development -t chat-dev .

To run the app in the container, use:

docker run --env OPENAI_API_KEY=$Env:OPENAI_API_KEY -p 8501:8501 chat-dev

Or to run the unit tests in the container, use:

docker run chat-dev pytest /app/tests/unit