- 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
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)
With share_instance = Yes, announces weren't being sent over TCP
in Docker environments. Setting it to No ensures each TinyWeb
instance manages its own Reticulum interfaces directly.
New TinyWeb instances now auto-connect to rnode.bre.land:4242
so users get internet mesh connectivity out of the box without any
manual Reticulum configuration. Env var overrides still supported.
Replaces static CMD with an entrypoint that generates RNS config from
environment variables (RNS_TCP_HOST/PORT), enabling TCP transport for
environments without LAN auto-discovery (e.g. Docker on macOS).
- SSRF: disable automatic redirects, manually follow up to 5 hops with
IP re-validation at each step to prevent redirect-to-localhost bypass
- Identity file: enforce 0600 permissions on tinyweb_identity at load
and creation to prevent other users from reading the private key
- Error messages: replace raw exception strings with generic messages
to avoid leaking internal paths/hostnames to the UI
- DB connections: wrap all get_db() usage in try/finally to guarantee
close() even when handlers throw mid-operation
Shows instance stats, destination hash for subscribing, and explains
the slow web movement and how TinyWeb works. Destination hash is
stored in settings on startup so the about page can display it.
app.py now auto-starts the gateway HTTP server in a daemon thread,
so users only need `python app.py` to get everything running. The
gateway calls dispatch_request directly when co-located (local mode)
instead of trying to establish an RNS link to itself. Bookmarklet
hardcoded to localhost:8080. gateway.py still works standalone for
connecting to remote instances.
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
Makes the server accessible from other devices on the network
instead of only localhost. The bookmarklet now uses the Host header
from the request so it works regardless of how the server is accessed.
