https://github.com/alanvww/ollama-llama-3.2-vision-p5js-chatbot

https://github.com/alanvww/ollama-llama-3.2-vision-p5js-chatbot

Last synced: about 2 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/alanvww/ollama-llama-3.2-vision-p5js-chatbot
• Owner: alanvww
• Created: 2024-11-23T06:58:26.000Z (6 months ago)
• Default Branch: main
• Last Pushed: 2024-11-23T21:24:33.000Z (6 months ago)
• Last Synced: 2025-03-26T02:45:29.640Z (about 2 months ago)
• Language: JavaScript
• Size: 1.35 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Ollama-Llama-3.2-Vision-p5js-Chatbot

A web interface for interacting with Ollama's Llama 3.2 Vision model, built with p5.js. This application allows you to chat with an AI assistant and share images for visual analysis.

## Preview

![Ollama Llama 3.2 Vision p5.js Chatbot](./asset/preview.png)

## Prerequisites

1. Download and install from [Ollama.com](https://ollama.com)

2. Pull and run the Llama 3.2 Vision model:

   ```sh

   ollama run llama3.2-vision

   ```

## Setup

1. Clone this repository.

2. Ensure Ollama is running with the llama3.2-vision model.

3. Open index.html in your browser (using a local server).

## Usage

1. Type messages in the input field.

2. Upload images by clicking the upload button or drag-and-drop.

3. Press Enter or click Send to submit your message.

4. The AI will respond to both text and images.

## Note

Make sure the Ollama service is running on localhost:11434 before using the interface.

For more details about the Llama 3.2 Vision model and Ollama, visit [Ollama.com](https://ollama.com/blog/llama3.2-vision).