https://github.com/heaversm/llamafile-code-completion

Use llamafile to generate inline code completions in react / next.js apps.
https://github.com/heaversm/llamafile-code-completion

Last synced: about 2 months ago
JSON representation

Use llamafile to generate inline code completions in react / next.js apps.

• Host: GitHub
• URL: https://github.com/heaversm/llamafile-code-completion
• Owner: heaversm
• Created: 2024-11-21T21:18:00.000Z (about 2 months ago)
• Default Branch: main
• Last Pushed: 2024-11-21T21:44:06.000Z (about 2 months ago)
• Last Synced: 2024-11-21T22:30:02.551Z (about 2 months ago)
• Language: TypeScript
• Size: 188 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Llamafile Code Completion App

This app is a demo of using [Mozilla's Llamafile](https://github.com/Mozilla-Ocho/llamafile) to do inline code completion within a web app using a free, locally running AI model.

## Getting Started

Download an AI model in Llamafile format, for example [deepseek-coder](https://huggingface.co/raincoder/deepseek-coder-1.3b-llamafile/tree/main). Make sure the model has a llamafile extension, is not an "instruct" model, and supports FIM (fill in the middle) code completion.

Then, open a terminal to wherever you downloaded your llamafile to, and run: `./[name_of_model].llamafile --nobrowser --server`.

Then run `npm install`

Then, run the development server: `npm run dev`.

Open [http://localhost:3000](http://localhost:3000) with your browser to see the app.

You can edit the app from the `app/components/CodeCompletionApp.tsx` file.