feat(rfdetr): add object detection API

[mudler]

Description

This PR fixes #5907 - It adds object detection endpoint and the model rfdetr-base to the gallery.

In short:

• Creates a new /v1/detection endpoint that takes as input an image and return list of identified objects
• Adds a new object-detection category across the code
• Adds rfdetr as backend in the gallery
• Updates CI accordingly to push new images
• Add to the model gallery the rfdetr-base model, after this is is merged it can be installed with: rfdetr-base

Testing with:

make backends/rfdetr build
./local-ai run --debug
curl -X POST http://localhost:8080/v1/detection -H "Content-Type: application/json" -d '{
    "model": "rfdetr",
    "image": "https://media.roboflow.com/dog.jpeg"
  }'

model file:

name: rfdetr
backend: rfdetr
parameters:
  model: rfdetr-base

Notes for Reviewers

Tested, works also on CPU quite well.

Signed commits

• Yes, I signed my commits.

[netlify]

✅ Deploy Preview for localai ready!

Name	Link
🔨 Latest commit	317f022
🔍 Latest deploy log	https://app.netlify.com/projects/localai/deploys/688685d2dfa70e0008f49783
😎 Deploy Preview	https://deploy-preview-5923--localai.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify project configuration.