Difference between revisions of "OSGeo-Knowledge-Embedding-Server"

From OSGeo
Jump to navigation Jump to search
(Created page with "* '''BGE-M3 Embedding Server''' - Semantic search embeddings via llama.cpp ** Port: 8094 (localhost only), Model: bge-m3-Q8_0.gguf Runs in Gallery_Container The embeddin...")
 
Line 8: Line 8:
 
'''Contact:''' ominiverdi (Lorenzo Becchi) or SAC channel
 
'''Contact:''' ominiverdi (Lorenzo Becchi) or SAC channel
  
[[Category:Service]]
+
[[Category:Services]]
 +
[[Category:AI-Services]]

Revision as of 09:57, 5 June 2026

  • BGE-M3 Embedding Server - Semantic search embeddings via llama.cpp
    • Port: 8094 (localhost only), Model: bge-m3-Q8_0.gguf

Runs in Gallery_Container

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: ominiverdi (Lorenzo Becchi) or SAC channel