refactor: model naming v1(base)/v2, Qdrant collection naming

- Phase 1 = v1 (base model, sentence chunk embedding)
- Phase 2 = v2 (full pipeline + 5W1H)
- Naming leaves room for v3, v4, etc.
- Qdrant collection: momentry_dev_v1 (active model under dev)
- Release packaging exports Qdrant points snapshot

.env.development

@@ -29,7 +29,7 @@ REDIS_PASSWORD=accusys
 # Qdrant Vector Database - Collection isolation
 QDRANT_URL=http://localhost:6333
 QDRANT_API_KEY=Test3200Test3200Test3200
-QDRANT_COLLECTION=momentry_dev_rule1
+QDRANT_COLLECTION=momentry_dev_v1
 
 # Paths
 MOMENTRY_OUTPUT_DIR=/Users/accusys/momentry/output_dev

.env.example

@@ -24,7 +24,7 @@ MONGODB_DATABASE=momentry
 # ===========================================
 QDRANT_URL=http://localhost:6333
 QDRANT_API_KEY=your_qdrant_api_key
-QDRANT_COLLECTION=momentry_rule1
+QDRANT_COLLECTION=momentry_v2_full
 
 # ===========================================
 # API Server Configuration

docs/RELEASE_PHASES.md

@@ -22,18 +22,19 @@ Search / Query / Identity APIs
 - **Model** = 每部影片的產出 package（output_json + chunks + vectors）
 - **Engine** = momentry core，吃 model 提供 API（search, trace, identity）
 
-如同模型的 tiny / small / medium / large，每個影片可有多個 model 版本：
+每個影片可有多個 model 版本，命名保留升級空間：
 
-| Model 版本 | 內容 | 觸發時機 |
-|-----------|------|---------|
-| `{uuid}_v1_tiny` | sentence chunk embedding | ASR + ASRX + Rule 1 完成 |
-| `{uuid}_v2_full` | 完整 pipeline + 5W1H | 全部完成 |
+| Model 版本 | Qdrant Collection | 內容 | 觸發時機 |
+|-----------|------------------|------|---------|
+| `{uuid}_v1` | `momentry_dev_v1` | sentence chunk embedding（base） | ASR + ASRX + Rule 1 完成 |
+| `{uuid}_v2` | `momentry_dev_v2` | 完整 pipeline + 5W1H | 全部完成 |
+| `{uuid}_v3` | - | 預留後續升級 | - |
 
 各版本共存不覆蓋。
 
 ## 階段劃分
 
-### Phase 1：Sentence Chunk Embedding（tiny model）
+### Phase 1：Sentence Chunk Embedding（base model）
 
 **觸發時機**: ASR + ASRX 完成 + Rule 1 Ingestion + vectorize 完成
 
@@ -45,7 +46,7 @@ Search / Query / Identity APIs
 
 **用途**: 終端使用者可進行語意搜尋
 
-### Phase 2：完整 Pipeline（full model）
+### Phase 2：完整 Pipeline（v2 model）
 
 **觸發時機**: 全部 processor 完成 + Rule 3 Ingestion + 5W1H Agent
 
@@ -69,7 +70,7 @@ Rule 1 Ingestion (sentence chunks)
   ↓
 vectorize_chunks (sentence embedding)
   ↓
-📦 Phase 1 release  ───→ release/phase1/latest/  (tiny model)
+📦 Phase 1 release  ───→ release/phase1/latest/  (base model)
   ↓
 其他 processors 繼續 (yolo, face, pose, ocr, ...)
   ↓
@@ -109,5 +110,5 @@ release/
 | 類比 | 訓練好的 weights | inference engine |
 | 內容 | `.json` + chunks + vectors | Rust binary |
 | 生命週期 | 每部影片產出一個 | 一個 binary 服務所有影片 |
-| 版本 | `{uuid}_v1_tiny` / `{uuid}_v2_full` | `momentry_playground` / `momentry` |
+| 版本 | `{uuid}_v1`（base） / `{uuid}_v2` | `momentry_playground` / `momentry` |
 | 交付對象 | 終端使用者 | 部署工程師 |

scripts/release_pack.py

@@ -24,6 +24,8 @@ VERSION = "v1.0.0"
 
 DB_USER = os.environ.get("USER", "accusys")
 DB_NAME = "momentry"
+QDRANT_URL = os.environ.get("QDRANT_URL", "http://localhost:6333")
+QDRANT_COLLECTION = os.environ.get("QDRANT_COLLECTION", "momentry_dev_rule1_v2")
 
 
 def ts():
@@ -74,18 +76,51 @@ def pack_phase(file_uuid: str, phase: int) -> Path:
         idents_csv = pkg_dir / "identities.csv"
         run_sql(f"\\COPY (SELECT * FROM dev.identities) TO '{idents_csv}' CSV HEADER")
 
+    # 匯出 Qdrant collection 快照
+    import urllib.request
+    qdrant_path = pkg_dir / "qdrant_points.jsonl"
+    try:
+        offset = None
+        with open(qdrant_path, "w") as qf:
+            while True:
+                params = f"limit=1000&with_payload=true&with_vectors=true"
+                if offset is not None:
+                    params += f"&offset={offset}"
+                url = f"{QDRANT_URL}/collections/{QDRANT_COLLECTION}/points/scroll?{params}"
+                req = urllib.request.Request(url)
+                with urllib.request.urlopen(req, timeout=30) as resp:
+                    data = json.loads(resp.read())
+                pts = data.get("result", {}).get("points", [])
+                if not pts:
+                    break
+                for p in pts:
+                    qf.write(json.dumps(p, ensure_ascii=False) + "\n")
+                # 從回傳的 next_page_offset 取得下一頁偏移量
+                offset = data.get("result", {}).get("next_page_offset")
+                if offset is None:
+                    break
+        n_points = sum(1 for _ in open(qdrant_path) if _.strip())
+        print(f"[RELEASE]   Qdrant: {n_points} points exported from '{QDRANT_COLLECTION}'")
+    except Exception as e:
+        print(f"[RELEASE]   Qdrant export skipped: {e}")
+        if qdrant_path.exists():
+            qdrant_path.unlink()
+
     # RELEASE_INFO
     git_commit = subprocess.run(
         ["git", "-C", str(PROJECT), "rev-parse", "HEAD"],
         capture_output=True, text=True, timeout=10,
     ).stdout.strip()
 
+    model_name = f"{file_uuid}_v1" if phase == 1 else f"{file_uuid}_v2"
     info = pkg_dir / "RELEASE_INFO.txt"
     with open(info, "w") as fh:
+        fh.write(f"Model: {model_name}\n")
         fh.write(f"Phase: {phase}\n")
         fh.write(f"Version: {VERSION}\n")
         fh.write(f"Timestamp: {stamp}\n")
         fh.write(f"File UUID: {file_uuid}\n")
+        fh.write(f"Qdrant Collection: {QDRANT_COLLECTION}\n")
         fh.write(f"Git Commit: {git_commit}\n")
         fh.write(f"Packaged at: {datetime.now(timezone.utc).isoformat()}\n")