Difference between revisions of "Gallery Container"
Jump to navigation
Jump to search
| Line 1: | Line 1: | ||
Debian 12 (bookworm) container for AI/ML services, media, and experimental applications. | Debian 12 (bookworm) container for AI/ML services, media, and experimental applications. | ||
| − | Gallery is a container on [[ | + | Gallery is a container on [[SAC_Service_Status#osgeo7|osgeo7]] host. |
'''Resources:''' 8 vCPUs, 12GB RAM | '''Resources:''' 8 vCPUs, 12GB RAM | ||
Revision as of 08:21, 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):
- LLM-based Chat Assistant
- BGE-M3 Embedding Server - Semantic search embeddings via llama.cpp
- Port: 8094 (localhost only), Model: bge-m3-Q8_0.gguf
- osgeo-library - PDF figure/table/equation extraction and semantic search
- GitHub: https://github.com/ominiverdi/osgeo-library
- CLI command:
osgeo-library(as ominiverdi user)
- osgeo_wiki_bot - Automated wiki/WordPress/Planet content sync and processing
- GitHub: https://github.com/ominiverdi/osgeo_wiki_bot
- Cron: wiki (6h), WordPress (daily), Planet (4h), chunk processing (hourly)
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