加入日志管理

backend/schema/indexer.py

@@ -22,12 +22,8 @@ class SchemaIndexer:
     功能：
     1. 为表结构构建向量索引
     2. 基于问题的表检索
-<<<<<<< HEAD
     3. 默认使用 Chroma ``PersistentClient``，数据落在 ``persist_dir``（与 ``VECTOR_DB_PATH`` 一致）；
        仅当环境变量 ``SCHEMA_INDEXER_EPHEMERAL=true`` 或构造参数 ``use_ephemeral=True`` 时使用内存客户端。
-=======
-    3. Chroma 使用持久化（PersistentClient），向量与元数据写入 ``persist_dir``，进程重启后可复用
->>>>>>> 9369563942d8de442508613191670123d5ae9d08
     """
 
     def __init__(
@@ -43,11 +39,7 @@ class SchemaIndexer:
 
         Args:
             embedder: Embedding模型实例
-<<<<<<< HEAD
-            persist_dir: Chroma 持久化目录（默认与编排器 ``vector_db_path`` / ``VECTOR_DB_PATH`` 一致）
-=======
             persist_dir: Chroma 持久化根目录（磁盘路径）
->>>>>>> 9369563942d8de442508613191670123d5ae9d08
             collection_name: 集合名称
             use_ephemeral: 为 True 时使用内存 Chroma；为 None 时读环境变量 SCHEMA_INDEXER_EPHEMERAL
         """
@@ -56,17 +48,15 @@ class SchemaIndexer:
         self.persist_dir.mkdir(parents=True, exist_ok=True)
         self.collection_name = collection_name
 
-<<<<<<< HEAD
         env_ephemeral = os.getenv("SCHEMA_INDEXER_EPHEMERAL", "").lower() in (
             "1",
             "true",
             "yes",
-=======
+        )
         # 持久化 Chroma：数据落盘至 persist_dir
         self.client = chromadb.PersistentClient(
             path=str(self.persist_dir),
             settings=ChromaSettings(anonymized_telemetry=False),
->>>>>>> 9369563942d8de442508613191670123d5ae9d08
         )
         self._chroma_ephemeral = bool(use_ephemeral) if use_ephemeral is not None else env_ephemeral
 
@@ -90,13 +80,8 @@ class SchemaIndexer:
         )
 
         logger.info(
-<<<<<<< HEAD
             f"[OK] 初始化SchemaIndexer({backend_desc}): collection={self.collection_name}, "
             f"count={self.collection.count()}"
-=======
-            f"[OK] 初始化SchemaIndexer(Chroma持久化): collection={self.collection_name}, "
-            f"path={self.persist_dir}"
->>>>>>> 9369563942d8de442508613191670123d5ae9d08
         )
 
     def ensure_index_for_schema(
@@ -255,7 +240,14 @@ class SchemaIndexer:
                         "rank": idx + 1,
                     })
 
-        logger.debug(f"检索 '{query[:50]}...' -> 找到{len(formatted)}个相关表（阈值={score_threshold}）")
+        top = [(x["table_name"], round(float(x.get("score", 0.0)), 4)) for x in formatted[:15]]
+        logger.info(
+            "Schema 向量检索: query_chars=%s 命中=%s（阈值=%s）top=%s",
+            len(query or ""),
+            len(formatted),
+            score_threshold,
+            top,
+        )
         return formatted
 
     def search_by_table_names(self, table_names: List[str]) -> List[Dict]:
@@ -332,9 +324,5 @@ class SchemaIndexer:
             "total_columns": total_columns,
             "avg_columns": total_columns / count if count > 0 else 0,
             "persist_dir": str(self.persist_dir),
-<<<<<<< HEAD
             "chroma_mode": "memory" if self._chroma_ephemeral else "persistent",
-=======
-            "chroma_mode": "persistent",
->>>>>>> 9369563942d8de442508613191670123d5ae9d08
         }