https://github.com/redis/minipilot

MiniPilot is a GenAI-assisted chatbot backed by Redis. Chat with your documents
https://github.com/redis/minipilot

chatbot chatgpt flask flask-application genai genai-chatbot langchain langchain-python openai python real-time redis redisvl semantic vector-database vectorization

Last synced: 5 days ago
JSON representation

MiniPilot is a GenAI-assisted chatbot backed by Redis. Chat with your documents

• Host: GitHub
• URL: https://github.com/redis/minipilot
• Owner: redis
• License: mit
• Created: 2024-05-25T15:21:21.000Z (8 months ago)
• Default Branch: main
• Last Pushed: 2024-12-10T21:50:48.000Z (about 1 month ago)
• Last Synced: 2025-01-09T08:09:55.357Z (13 days ago)
• Topics: chatbot, chatgpt, flask, flask-application, genai, genai-chatbot, langchain, langchain-python, openai, python, real-time, redis, redisvl, semantic, vector-database, vectorization
• Language: HTML
• Homepage:
• Size: 131 MB
• Stars: 58
• Watchers: 4
• Forks: 6
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# 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

![demo](src/static/images/minipilot.gif)

The system uses:

- Redis Stack as a vector database to store the dataset and vectorize the content for RAG using Redis [vector search capabilities](https://redis.io/docs/latest/develop/interact/search-and-query/advanced-concepts/vectors/).

- OpenAI ChatGPT Large Language Model (LLM) [ChatCompletion API](https://platform.openai.com/docs/guides/gpt/chat-completions-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"`

2. `cd minipilot`

3. `docker compose build --no-cache && docker compose up -d` and wait a couple of minutes until Redis loads the [IMDB movies dataset](https://www.kaggle.com/datasets/ashpalsingh1525/imdb-movies-dataset) in memory

4.  Point your browser to [http://127.0.0.1:5007/](http://127.0.0.1:5007), tune the prompt and start chatting

5. Browse your data with Redis Insight at [http://127.0.0.1:8099](http://127.0.0.1:8099)

## Documentation

- [Installation Guide](docs/installation.md)

- [Usage Guide](docs/usage.md)

- [API Documentation](docs/api.md)

- [Architecture Overview](docs/architecture.md)

- [FAQ](docs/faq.md)