👾💬 AI Code Assistant using Yi-Coder-9B

Inspired by Shubham Saboo's awesome-llm-apps

This project demonstrates how to build a ChatGPT-like code assistant using the Yi-Coder-9B model running locally on your computer. The application is built using Python and Streamlit, providing a user-friendly interface for interacting with the language model. Best of all, it's 100% free and doesn't require an internet connection!

Features

• Runs locally on your computer without the need for an internet connection and completely free to use.
• Utilizes the Yi-Coder-9B coding model from Yi, supporting a staggering 52 programming language, and featuring a max context length of 128k, making it great for ingesting large codebases
• Provides a chat-like interface for seamless interaction

How to get Started?

1. Clone the GitHub repository

   git clone https://github.com/andreaceto/local-code-assistant.git

2. Create a virtual environment and activate it

   python -m venv venv-name
   venv-name/Scripts/activate  # On MacOS use `source venv-name/bin/activate`

3. Install the required dependencies

   pip install -r requirements.txt

4. Download and install the LM Studio desktop app

5. Open LM Studio and download the Yi-Coder-9B model from the 'Discover' tab

6. Expose the Yi-Coder-9B model as an OpenAI API by starting the server in LM Studio. (Follow this video walkthrough).

7. Run the Streamlit App

   streamlit run ai_code_assistant.py