added hybrid semantic search with 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)

app.py

@@ -72,8 +72,25 @@ def ensure_rns_config(config_dir):
     print(f"Created Reticulum config at {config_file}")
 
 
+def _preload_embeddings():
+    """Pre-load the embedding model and build the HNSW index in background."""
+    try:
+        from embeddings import _get_session, _get_reranker, build_index
+        _get_session()  # downloads model on first run, loads ONNX session
+        build_index()   # builds HNSW index from existing chunks
+        # Preload cross-encoder unless user has explicitly disabled it
+        if get_setting("use_reranker", "1") == "1":
+            _get_reranker()
+            print("Semantic search ready (with reranker).")
+        else:
+            print("Semantic search ready.")
+    except Exception as e:
+        print(f"Semantic search unavailable: {e}")
+
+
 def main():
     init_db()
+    threading.Thread(target=_preload_embeddings, daemon=True).start()
     config_dir = os.environ.get("RNS_CONFIG_DIR")
     ensure_rns_config(config_dir)
     reticulum = RNS.Reticulum(configdir=config_dir)