lichenblankie/tinyweb
1
0
Fork 0
Code Issues Pull requests Projects 1 Releases 1 Packages Wiki Activity Actions

added hybrid semantic search with reranking

Browse source 
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)
This commit is contained in:
lichenblankie 2026-03-27 03:24:41 -07:00
parent 212e9a017d
commit 5ded9f1339
6 changed files with 839 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

5
requirements.txt
View file

@ -1,3 +1,8 @@
requests
beautifulsoup4
rns
onnxruntime
tokenizers
hnswlib
numpy
huggingface_hub