feat: Initial v0.9 release with API Key authentication

## v0.9.20260325_144654

### Features
- API Key Authentication System
- Job Worker System
- V2 Backup Versioning

### Bug Fixes
- get_processor_results_by_job column mapping

Co-authored-by: OpenCode

scripts/chinese_vector_test.py

@@ -0,0 +1,170 @@
+#!/opt/homebrew/bin/python3.11
+"""
+Natural Language Vector Search - Chinese Queries
+"""
+
+import time
+import requests
+import psycopg2
+
+
+VIDEO_UUID = "39567a0eb16f39fd"
+
+POSTGRES_CONFIG = {
+    "host": "localhost",
+    "port": 5432,
+    "user": "accusys",
+    "password": "Test3200",
+    "database": "momentry",
+}
+
+
+# Chinese natural language queries
+CHINESE_QUERIES = [
+    # Scene
+    "有人在說話",
+    "戶外場景",
+    "室內場景",
+    # Actions
+    "走路或移動",
+    "對話或交談",
+    "看著某樣東西",
+    # Emotions
+    "快樂或開心",
+    "嚴肅或戲劇性",
+    "喜劇或有趣",
+    # Objects
+    "戴著領帶",
+    "拿著東西",
+    "坐在椅子上",
+    # Locations
+    "城市或都市",
+    "建築物或房間",
+    "開放空間",
+]
+
+
+def get_embedding(text):
+    resp = requests.post(
+        "http://localhost:11434/api/embeddings",
+        json={"model": "nomic-embed-text", "prompt": text},
+    )
+    return resp.json()["embedding"]
+
+
+def test_qdrant(queries):
+    results = {}
+
+    for query in queries:
+        embedding = get_embedding(query)
+
+        start = time.time()
+        resp = requests.post(
+            "http://localhost:6333/collections/AccusysDB/points/search",
+            headers={"api-key": "Test3200Test3200Test3200"},
+            json={"vector": embedding, "limit": 10},
+        )
+        elapsed = (time.time() - start) * 1000
+
+        data = resp.json()
+        results[query] = {"ms": round(elapsed, 2), "results": data.get("result", [])}
+
+    return results
+
+
+def test_pgvector(queries):
+    results = {}
+    conn = psycopg2.connect(**POSTGRES_CONFIG)
+    cur = conn.cursor()
+
+    for query in queries:
+        embedding = get_embedding(query)
+        vector_str = "[" + ",".join(str(x) for x in embedding) + "]"
+
+        start = time.time()
+        cur.execute(
+            """
+            SELECT cv.chunk_id, (cv.embedding_vector <=> %s::vector) as distance,
+                   c.content->>'text' as text
+            FROM chunk_vectors cv
+            JOIN chunks c ON cv.chunk_id = c.chunk_id
+            WHERE cv.embedding_vector IS NOT NULL
+            ORDER BY cv.embedding_vector <=> %s::vector
+            LIMIT 10
+        """,
+            (vector_str, vector_str),
+        )
+
+        rows = cur.fetchall()
+        elapsed = (time.time() - start) * 1000
+
+        results[query] = {
+            "ms": round(elapsed, 2),
+            "results": [
+                {"chunk_id": r[0], "score": 1 - r[1], "text": r[2]} for r in rows
+            ],
+        }
+
+    cur.close()
+    conn.close()
+    return results
+
+
+def main():
+    print("=" * 80)
+    print("中文自然語言向量搜尋測試")
+    print("Chinese Natural Language Vector Search Test")
+    print("=" * 80)
+    print("\nVideo: Charade 1963")
+    print("Model: nomic-embed-text\n")
+
+    print("Running Qdrant searches...")
+    qdrant_results = test_qdrant(CHINESE_QUERIES)
+
+    print("Running pgvector searches...")
+    pgvector_results = test_pgvector(CHINESE_QUERIES)
+
+    qdrant_avg = sum(r["ms"] for r in qdrant_results.values()) / len(qdrant_results)
+    pgvector_avg = sum(r["ms"] for r in pgvector_results.values()) / len(
+        pgvector_results
+    )
+
+    print("\n" + "=" * 80)
+    print("平均回應時間 / AVERAGE RESPONSE TIME")
+    print("=" * 80)
+    print(f"  Qdrant:    {qdrant_avg:.2f}ms")
+    print(f"  pgvector:  {pgvector_avg:.2f}ms")
+
+    print("\n" + "=" * 80)
+    print("詳細結果 / DETAILED RESULTS")
+    print("=" * 80)
+
+    for query in CHINESE_QUERIES:
+        qd = qdrant_results[query]
+        pg = pgvector_results[query]
+
+        print(f"\n{'=' * 60}")
+        print(f'查詢 / Query: "{query}"')
+        print(f"{'=' * 60}")
+
+        print(f"\n[Qdrant] Time: {qd['ms']:.1f}ms")
+        print("-" * 60)
+        for i, r in enumerate(qd["results"][:5]):
+            text = pg["results"][i]["text"] if i < len(pg["results"]) else ""
+            text_display = (
+                text[:50] + "..." if text and len(text) > 50 else (text if text else "")
+            )
+            print(f"  {i + 1:2}. [{r['score']:.3f}] {text_display}")
+
+        print(f"\n[pgvector] Time: {pg['ms']:.1f}ms")
+        print("-" * 60)
+        for i, r in enumerate(pg["results"][:5]):
+            text = r["text"]
+            text_display = (
+                text[:50] + "..." if text and len(text) > 50 else (text if text else "")
+            )
+            print(f"  {i + 1:2}. [{r['score']:.3f}] {text_display}")
+
+
+if __name__ == "__main__":
+    main()