容器处理

test/test_dqrant.py

@@ -0,0 +1,66 @@
+"""检查 Qdrant 中存储的向量质量。"""
+
+import os
+import sys
+import numpy as np
+from dotenv import load_dotenv
+from qdrant_client import QdrantClient
+
+# 添加项目根目录和 backend 目录到 Python 路径
+project_root = os.path.join(os.path.dirname(__file__), "..")
+backend_dir = os.path.join(project_root, "backend")
+sys.path.insert(0, project_root)
+sys.path.insert(0, backend_dir)
+load_dotenv()
+
+from rag_core import LlamaCppEmbedder
+
+QDRANT_URL = os.getenv("QDRANT_URL", "http://127.0.0.1:6333")
+QDRANT_API_KEY = os.getenv("QDRANT_API_KEY")
+COLLECTION_NAME = "rag_documents"
+
+client = QdrantClient(url=QDRANT_URL, api_key=QDRANT_API_KEY)
+embedder = LlamaCppEmbedder()
+
+# 获取样本
+points, _ = client.scroll(
+    collection_name=COLLECTION_NAME,
+    limit=1,
+    with_vectors=True,
+    with_payload=True,
+)
+
+if not points:
+    print(f"集合 '{COLLECTION_NAME}' 为空")
+    exit()
+
+sample = points[0]
+raw_vec = sample.vector
+if isinstance(raw_vec, dict):
+    stored_vec = list(raw_vec.values())[0]
+elif isinstance(raw_vec, list):
+    stored_vec = raw_vec
+else:
+    stored_vec = []
+
+stored_payload = sample.payload or {}
+stored_text = str(stored_payload.get("page_content", ""))[:200]
+
+print(f"内容预览:\n{stored_text}...\n")
+print(f"向量维度: {len(stored_vec)}")  # type: ignore
+print(f"前5个值: {stored_vec[:5]}")  # type: ignore
+print(f"是否全零: {all(v == 0.0 for v in stored_vec)}")  # type: ignore
+
+# 重新编码对比
+if stored_text:
+    new_vec = embedder.embed_query(stored_text)
+    similarity = np.dot(stored_vec, new_vec) / (np.linalg.norm(stored_vec) * np.linalg.norm(new_vec))  # type: ignore
+    print(f"\n重新编码前5个值: {new_vec[:5]}")
+    print(f"余弦相似度: {similarity:.4f}")
+
+    if similarity < 0.8:
+        print("\n⚠️  相似度过低，建议删除集合并重建索引")
+    else:
+        print("\n✅ 向量一致")
+else:
+    print("\n⚠️  样本无文本内容")