Improving Qwen-VL Structured Output with Image Cropping

Explaining how I'm improving structured output results from Qwen-VL with image cropping in Sparrow.

 

 

Apple MLX Vision LLM Server with Ngrok, FastAPI and Sparrow

I show how I run Apple MLX backend on my local Mac Mini M4 Pro 64GB and access it from the Web through Ngrok, with automatically provisioned HTTPS certificate. 

 

Vision LLM Structured Output with Sparrow

I show how Sparrow UI Shell works with both image and PDF docs to process and extract structured data with Vision LLM (Qwen2) in the MLX backend.