AI Text Generation with Ollama and Llama 3.2 Vision

This project demonstrates how to use the Ollama AI provider to generate descriptive text for an image using the llama3.2-vision:11b model. The script integrates AI and image analysis, allowing you to send both textual and visual data to the model for inference.

---

Features

• Uses Ollama AI provider to interact with the Llama model.
• Processes both text and image input.
• Outputs a descriptive text response from the model.
• Uses Tsup for TypeScript/JavaScript bundling and compilation.

---

Requirements

• Ollama server running locally or accessible via a specified URL
• The ai and ollama-ai-provider npm packages installed
• The tsup package for building the project
• A valid image file (image1.jpg) in the image directory

---

Installation

Install dependencies: npm install npx tsup src/index.ts --format esm --dts node dist/index.js