feat: service inventory, ERP reports, sqlite-vec integration, visualize tool

- Add SERVICE_INVENTORY_V1.0.0.md (25 source-verified tools, 3.7GB)
- Add ERP_SELECTION_REPORT.md (Odoo CE vs ERPNext comparison)
- Add SFTPGO_ODOO_REPLACEMENT.md (SFTPGo migration plan)
- Add SERVICE_GO_GITEA_BUILD.md (Go compiler + Gitea build report)
- Add release visualize command (face trace heatmap + identity filter)
- Add sqlite-vec integration (160MB SQLite with vec0 vector tables)
- Add export_identities.py, export_sqlite.py, render_face_heatmap.py
- Add Go, Gitea, Rust/Cargo, Swift, yt-dlp, SQLite, sqlite-vec to service CLI
- Fix package to include identities and identity_bindings in data.sql
- Update release list to show all deployed video stats
- Add V1.0.0 YAML frontmatter to all docs (DOCS_STANDARD compliant)

scripts/vectorize_chunks.py

@@ -0,0 +1,69 @@
+#!/opt/homebrew/bin/python3.11
+"""Vectorize sentence chunks via Ollama mxbai-embed-large and store in DB + Qdrant."""
+import json, sys, time
+import psycopg2
+from urllib.request import Request, urlopen
+
+DB = "dbname=momentry user=accusys"
+UUID = sys.argv[1] if len(sys.argv) > 1 else "23b1c872379d4ec06479e5ed39eef4c5"
+OLLAMA = "http://localhost:11434/api/embeddings"
+QDRANT = "http://localhost:6333"
+
+conn = psycopg2.connect(DB)
+cur = conn.cursor()
+
+cur.execute("""
+    SELECT chunk_id, text_content FROM dev.chunk
+    WHERE file_uuid = %s AND chunk_type = 'sentence'
+    AND (text_content IS NOT NULL AND text_content != '')
+    ORDER BY id
+""", (UUID,))
+rows = cur.fetchall()
+print(f"Vectorizing {len(rows)} chunks for {UUID}...")
+
+stored = 0
+batch = []
+for chunk_id, text in rows:
+    req = Request(OLLAMA, data=json.dumps({
+        "model": "nomic-embed-text-v2-moe:latest",
+        "prompt": text
+    }).encode(), headers={"Content-Type": "application/json"})
+    resp = json.loads(urlopen(req).read())
+    embedding = resp["embedding"]
+    
+    # Store in PostgreSQL chunk_vectors
+    cur.execute("""
+        INSERT INTO dev.chunk_vectors (chunk_id, uuid, chunk_type, embedding)
+        VALUES (%s, %s, 'sentence', %s::jsonb)
+        ON CONFLICT (chunk_id, uuid) DO UPDATE SET embedding = EXCLUDED.embedding
+    """, (chunk_id, UUID, json.dumps(embedding)))
+    
+    # Batch for Qdrant
+    batch.append({
+        "id": int(chunk_id) + 1 if chunk_id.isdigit() else len(batch) + 10000,
+        "vector": embedding,
+        "payload": {"chunk_id": chunk_id, "chunk_type": "sentence"}
+    })
+    
+    if len(batch) >= 100:
+        req = Request(f"{QDRANT}/collections/momentry_dev_rule1_v2/points?wait=true",
+            data=json.dumps({"points": batch}).encode(),
+            headers={"Content-Type": "application/json"}, method="PUT")
+        urlopen(req)
+        batch = []
+    
+    stored += 1
+    if stored % 50 == 0:
+        print(f"  {stored}/{len(rows)}")
+        conn.commit()
+
+if batch:
+    req = Request(f"{QDRANT}/collections/momentry_dev_rule1_v2/points?wait=true",
+        data=json.dumps({"points": batch}).encode(),
+        headers={"Content-Type": "application/json"}, method="PUT")
+    urlopen(req)
+
+conn.commit()
+cur.close()
+conn.close()
+print(f"Done: {stored} vectors stored")