- Type
- Individual project
- Role
- Sole developer: design, development and testing.
- Tech stack
- Links
- Demo video
Overview
A web app that describes any uploaded image in detail, using the Llava vision model running locally through Ollama.
Responses stream back as they are generated, so a long description starts appearing straight away.
Built
- A Flask back end that encodes the image and calls Ollama.
- Streaming responses rendered as they arrive.
- A Bootstrap front end in plain JavaScript.
Learned
- Building web applications with Flask.
- Integrating the Ollama AI service.
- Working with image analysis models.