Difference between revisions of "Gallery Container"

From OSGeo
Jump to navigation Jump to search
(Created page with "Debian 12 (bookworm) container for AI/ML services, media, and experimental applications. Gallery is a container on OSGeo7 host. '''Resources:''' 8 vCPUs, 12GB RAM '''Syst...")
 
Line 11: Line 11:
  
 
'''Lorenzo's services (ominiverdi):'''
 
'''Lorenzo's services (ominiverdi):'''
* '''matrix-llmagent''' - Matrix chat bot with LLM integration (uses OpenRouter API)
+
* [[LLM-based Chat Assistant]]
** GitHub: https://github.com/ominiverdi/matrix-llmagent
 
 
* '''BGE-M3 Embedding Server''' - Semantic search embeddings via llama.cpp
 
* '''BGE-M3 Embedding Server''' - Semantic search embeddings via llama.cpp
 
** Port: 8094 (localhost only), Model: bge-m3-Q8_0.gguf
 
** Port: 8094 (localhost only), Model: bge-m3-Q8_0.gguf

Revision as of 07:28, 5 June 2026

Debian 12 (bookworm) container for AI/ML services, media, and experimental applications. Gallery is a container on OSGeo7 host.

Resources: 8 vCPUs, 12GB RAM System services: nginx, redis, PostgreSQL 17, turnserver, php-fpm

Brian's services (darkblueb):

  • GalleryVM media library
  • llamafile experiments
  • photoprism configuration

Lorenzo's services (ominiverdi):

The embedding model running on osgeo7-gallery is BGE-M3 (bge-m3-Q8_0.gguf), a multilingual model from BAAI supporting 100+ languages. It produces 1024-dimensional vectors and runs via llama-server on port 8094 (localhost only). The Q8_0 quantization keeps it light: 606 MB on disk, ~457 MB RAM, ~12ms per query.

Contact: darkblueb (Brian Hamlin), ominiverdi (Lorenzo Becchi) or SAC channel