Harden image generation as remote inference calls with provider fallback

Upgrade to Gradio 5.x to fix api-schema startup crash

Pin huggingface_hub<1.0 for gradio 4.44 compatibility

Set SEARXNG_SETTINGS_PATH at runtime, not build time

Fix SearXNG editable install: use --no-build-isolation

Rebuild image on python:3.11-slim with isolated venvs

Add grounded blog-post generator pipeline

initial commit