feat: add migrations, test scripts, and utility tools

- Add database migrations (006-028) for face recognition, identity, file_uuid
- Add test scripts for ASR, face, search, processing
- Add portal frontend (Tauri)
- Add config, benchmark, and monitoring utilities
- Add model checkpoints and pretrained model references

test_chinese_embed.py

@@ -0,0 +1,56 @@
+import json
+import requests
+import sys
+
+
+def get_embedding(text, prefix="search_query: "):
+    url = "http://localhost:11434/api/embeddings"
+    payload = {"model": "nomic-embed-text-v2-moe:latest", "prompt": f"{prefix}{text}"}
+    response = requests.post(url, json=payload)
+    if response.status_code != 200:
+        print(f"Error: {response.status_code} - {response.text}")
+        return None
+    data = response.json()
+    return data["embedding"]
+
+
+def search_qdrant(vector, limit=10):
+    url = "http://127.0.0.1:6333/collections/momentry_rule1/points/search"
+    headers = {
+        "Content-Type": "application/json",
+        "api-key": "Test3200Test3200Test3200",
+    }
+    payload = {"vector": vector, "limit": limit, "with_payload": True}
+    response = requests.post(url, json=payload, headers=headers)
+    if response.status_code != 200:
+        print(f"Qdrant error: {response.status_code} - {response.text}")
+        return None
+    return response.json()
+
+
+if __name__ == "__main__":
+    # Test Chinese text
+    text = "檔案傳輸"
+    print(f"Testing embedding for: '{text}'")
+    vector = get_embedding(text)
+    if vector:
+        print(f"Vector length: {len(vector)}")
+        print(f"First 5 values: {vector[:5]}")
+
+        # Search Qdrant
+        print("\nSearching Qdrant...")
+        results = search_qdrant(vector, limit=5)
+        if results:
+            print(f"Found {len(results['result'])} results")
+            for i, r in enumerate(results["result"]):
+                payload = r.get("payload", {})
+                text = payload.get("text", "No text")
+                chunk_id = payload.get("chunk_id", "N/A")
+                uuid = payload.get("uuid", "N/A")
+                score = r.get("score", 0)
+                print(f"{i + 1}. Score: {score:.4f}, UUID: {uuid}, Chunk: {chunk_id}")
+                print(f"   Text: {text[:100]}...")
+        else:
+            print("No results")
+    else:
+        print("Failed to get embedding")