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>
Replace HTTP server with Reticulum-native architecture. The server
now speaks only Reticulum, with a client-side gateway providing
browser access by translating HTTP to/from RNS requests.
- Extract db layer (db.py), templates (templates.py), handlers (handlers.py)
- app.py is now the RNS server with persistent identity and destination
- gateway.py bridges HTTP on localhost:8080 to RNS link requests
- Add rns dependency, add .gitignore
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
