https://github.com/chanulee/coreollama

Locally run your own LLM - easy, simple, lightweight
https://github.com/chanulee/coreollama

ollama ollama-gui

Last synced: 19 days ago
JSON representation

Locally run your own LLM - easy, simple, lightweight

• Host: GitHub
• URL: https://github.com/chanulee/coreollama
• Owner: chanulee
• License: mit
• Created: 2024-11-17T23:48:07.000Z (about 1 month ago)
• Default Branch: main
• Last Pushed: 2024-11-22T22:50:11.000Z (30 days ago)
• Last Synced: 2024-12-03T17:15:02.274Z (19 days ago)
• Topics: ollama, ollama-gui
• Language: JavaScript
• Homepage:
• Size: 28.3 KB
• Stars: 36
• Watchers: 1
• Forks: 4
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# coreOllama

The most easy-to-use, simple and lightweight interface to run your local LLM, for everyone. 



## Features

- Generate

  - model selection

  - temperature

  - Image input for [llama3.2-vision:latest](https://ollama.com/library/llama3.2-vision)

- Model Management

  - View and delete models

  - Pull new model

- Local server status

- Dark mode

- Include Context: Full or selection

- Clear chat history

## Versions

- 0-basic: Basic proof of concept of ollama-gui

- chat: main project

#### Advanced Apps

- [persona-studio](https://github.com/chanulee/persona-studio): Build and manage your own personas

- [everychat](https://github.com/chanulee/everychat): your AI chat multiverse

## Beginner's guide

1. Ollama setup - install ollama app for mac (You can download model or just proceed and use gui)

2. Quit the app (check on your status bar). 

3. Open terminal and enter `ollama serve`. Keep that terminal window open.

4. Check http://localhost:11434/, it should say "Ollama is running".

5. Download the repo and open `web/chat/index.html`