Commit graph

5 commits

Author SHA1 Message Date
lichenblankie
8ecb963be4 Optimized storage and updated readme
All checks were successful
/ build (push) Successful in 2m19s
2026-04-11 21:59:55 +00:00
Test User
57a79e5e8e Add PyInstaller builds, AGPLv3 license, transport node selection, and rmap.world link
- Add pyinstaller.spec and GitHub/Forgejo CI workflows for cross-platform builds
- Add AGPLv3 license
- Move data storage to ~/.tinyweb/
- Add --version and --port CLI flags
- Add transport node selection in /style (smart regeneration preserves Reticulum config)
- Add discover more nodes link to rmap.world
2026-04-08 04:36:28 +00:00
Derick Phan
c959ee98ae
Make semantic search and reranking optional, use site meta descriptions for snippets
- Add semantic_search setting to toggle AI-powered search on/off
- Skip embedding generation, hybrid search, and model preloading when disabled
- Use site owner's meta description as snippet instead of heuristic extraction
- Remove _generate_summary() and snippet() - no more generated snippets
- Show reranker/reindex controls grayed out when semantic search is off
- AI dependencies (onnxruntime, hnswlib, etc.) are now fully optional

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-28 20:58:04 -07:00
Derick Phan
fd20454fa4
Fix reindex to re-embed all pages and preserve existing summaries
Previously reindex skipped pages that already had chunks, leaving stale
embeddings in place. It also overwrote good meta description summaries
with auto-generated ones. Now it clears all chunks first so everything
is re-embedded, and only generates summaries for pages missing one.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-27 14:08:04 -07:00
Derick Phan
395fc17092
Add hybrid semantic search with optional cross-encoder reranking
Implements a three-stage search pipeline:
1. BM25 keyword search via FTS5 with column weights
2. Semantic search via Snowflake arctic-embed-s bi-encoder + HNSW index
3. Optional cross-encoder reranking (on by default, toggleable in settings)

Top 20 results are reranked for precision, next 10 appended from RRF
for coverage, giving 30 total results across 3 pages.

- New embeddings.py with ONNX Runtime inference, text chunking, HNSW
  index management, RRF fusion, and cross-encoder reranking
- Meta description extraction for authentic page snippets with centroid
  extractive fallback
- Stopword filtering in FTS5 queries to avoid overly strict matching
- /reindex page for batch embedding of existing pages
- Semantic embedding of remote pages during subscription sync
- ~125MB dependency footprint (onnxruntime, tokenizers, hnswlib, numpy)
- Models: 34MB bi-encoder + 22MB cross-encoder (downloaded on first use)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-27 03:24:41 -07:00