rag_time

Simple Chat UI to chat about a private codebase using LLMs locally.

Technology:

• Ollama and llama3:8b as Large Language Model
• jina-embeddings-v2-base-code as Embedding Model
• LangChain as a framework for LLM
• Chainlit for the chat UI

Getting started

Prerequisites

1. Make sure you have Python 3.9 or later installed

2. Download and install Ollama

3. Pull the model:

   ollama pull llama:3b

Run the Chat bot

1. Create a Python virtual environment and activate it:

   python3 -m venv .venv && source .venv/bin/activate

2. Install Python dependencies:

   pip install -r requirements.txt

3. Clone an example repository to question the chat bot about:

   git clone https://github.com/discourse/discourse

4. Set up the vector database:

   python ingest-code.py

5. Start the chat bot:

   chainlit run main.py

6. To exit the Python virtual environment after you are done, run:

   deactivate

Make it your own

Modify the .env file to run the chat bot on your codebase and language.