Skip to main content
FME Hub user kailinatsafe just uploaded a new transformer to the FME Hub.

Description

The ImageIdentifier is designed for use with Ollamas' Llava 7B parameter model, leveraging its API endpoint for image classification. It is intended for use with JPEG and PNG image formats.

Installing Ollama and Llava 7B

This transformer will need an instance of Ollama running on a machine.

Ollama

Windows/Mac OS/Linux: https://ollama.com/download

Instructions can be found here: https://github.com/ollama/ollama?tab=readme-ov-file#ollama

Llava 7B Model

Instructions: https://ollama.com/library/llava:7b

Details

This transformer uses the URL from an Ollama instance and leverages Ollamas' Llava 7B API via its model. A prompt is used to make an HTTP GET Request. This is then returned to the user by attribute.

Photo by Robson Hatsukami Morgan on Unsplash



Would you like to know more? Click here to find out more details!