Files
Dominik Schmidt 4993c9c487 feat(search): semantic image search with CLIP embeddings
semantic:"..." in KQL embeds the query text (immich-ml, multilingual CLIP)
and ranks image vectors by cosine similarity: bleve via faiss KNN behind the
new vectors build tag (RRF fusion, vector round-trip through a stored-only
field), OpenSearch via knn_vector plus client-side RRF. The filter part of
the query keeps its meaning and stays the only source of totals and facets.
2026-09-03 10:28:19 +02:00
..
2026-08-28 23:17:11 +00:00
2026-08-18 17:17:30 +02:00
2026-06-03 16:28:44 +02:00
2026-08-03 13:20:03 +02:00
2026-09-02 23:18:41 +00:00
2026-07-14 18:12:24 +02:00
2026-06-18 15:05:49 +02:00
2026-08-25 09:55:39 +02:00