Minipilot

This application implements a chatbot you can train with your data. From the GUI you will be able to:

• Upload CSV data
• Create an index
• Edit the system and user prompt
• Ask questions in natural language

The system uses:

• Redis Stack as a vector database to store the dataset and vectorize the content for RAG using Redis vector search capabilities.
• OpenAI ChatGPT Large Language Model (LLM) ChatCompletion API

Quickstart

Follow these instructions to build and start Minipilot and a Redis Stack database as containers on your laptop. For more installation methods, refer to the docs.

1. git clone https://github.com/redis/minipilot.git
2. export OPENAI_API_KEY="your-openai-key"
3. cd minipilot
4. docker compose build --no-cache && docker compose up -d and wait a couple of minutes until Redis loads the IMDB movies dataset in memory
5. Point your browser to http://127.0.0.1:5007/, tune the prompt and start chatting
6. Browse your data with Redis Insight at http://127.0.0.1:8099

Troubleshooting

For troubleshooting, you can copy the execution log from the container to the host.

docker cp minipilot:/app/gunicorn.log .

Note that if your OpenAI key is not valid or expired, set the correct key as environment variable and restart the Minipilot container (or rebuild it).

Documentation

• Installation Guide
• Usage Guide
• API Documentation
• Architecture Overview
• FAQ