Look-here

This is a utility for using a local llm + vision model with Ollama for asking questions about screenshots

Built with Meta LLama 3.2

Steps to run

1. Install requirements

pip install -r requirements.txt

2. Install Ollama

For linux:

curl -fsSL https://ollama.com/install.sh | sh

For windows: https://ollama.com/download/windows

3. Run Ollama if its not already running

ollama serve

4. pull llama vision model

ollama pull llama3.2-vision

5. Take a screenshot

6. Start the ui and ask a question

python look_here.py 

Licensing:

This project uses the LLaMA 3.2 model by Meta , which is provided under the terms of Meta's license. Please review Meta's license before using this project.