Phase 3: Memory & Growth - Multi-file fusion, Entity alignment with embedding, Document import, Knowledge base panel

backend/db_manager.py

@@ -1,7 +1,8 @@
 #!/usr/bin/env python3
 """
-InsightFlow Database Manager
+InsightFlow Database Manager - Phase 3
 处理项目、实体、关系的持久化
+支持文档类型和多文件融合
 """
 
 import os
@@ -166,6 +167,18 @@ class DatabaseManager:
             (target_id, source_id)
         )
         
+        # 更新关系 - source 作为 source_entity_id
+        conn.execute(
+            "UPDATE entity_relations SET source_entity_id = ? WHERE source_entity_id = ?",
+            (target_id, source_id)
+        )
+        
+        # 更新关系 - source 作为 target_entity_id
+        conn.execute(
+            "UPDATE entity_relations SET target_entity_id = ? WHERE target_entity_id = ?",
+            (target_id, source_id)
+        )
+        
         # 删除源实体
         conn.execute("DELETE FROM entities WHERE id = ?", (source_id,))
         
@@ -222,13 +235,13 @@ class DatabaseManager:
         return [EntityMention(**dict(r)) for r in rows]
 
     # Transcript operations
-    def save_transcript(self, transcript_id: str, project_id: str, filename: str, full_text: str):
+    def save_transcript(self, transcript_id: str, project_id: str, filename: str, full_text: str, transcript_type: str = "audio"):
         """保存转录记录"""
         conn = self.get_conn()
         now = datetime.now().isoformat()
         conn.execute(
-            "INSERT INTO transcripts (id, project_id, filename, full_text, created_at) VALUES (?, ?, ?, ?, ?)",
-            (transcript_id, project_id, filename, full_text, now)
+            "INSERT INTO transcripts (id, project_id, filename, full_text, type, created_at) VALUES (?, ?, ?, ?, ?, ?)",
+            (transcript_id, project_id, filename, full_text, transcript_type, now)
         )
         conn.commit()
         conn.close()
@@ -388,6 +401,58 @@ class DatabaseManager:
         conn.close()
         
         return dict(row) if row else None
+    
+    # Phase 3: Glossary operations
+    def add_glossary_term(self, project_id: str, term: str, pronunciation: str = "") -> str:
+        """添加术语到术语表"""
+        conn = self.get_conn()
+        
+        # 检查是否已存在
+        existing = conn.execute(
+            "SELECT * FROM glossary WHERE project_id = ? AND term = ?",
+            (project_id, term)
+        ).fetchone()
+        
+        if existing:
+            # 更新频率
+            conn.execute(
+                "UPDATE glossary SET frequency = frequency + 1 WHERE id = ?",
+                (existing['id'],)
+            )
+            conn.commit()
+            conn.close()
+            return existing['id']
+        
+        term_id = str(uuid.uuid4())[:8]
+        conn.execute(
+            "INSERT INTO glossary (id, project_id, term, pronunciation, frequency) VALUES (?, ?, ?, ?, ?)",
+            (term_id, project_id, term, pronunciation, 1)
+        )
+        conn.commit()
+        conn.close()
+        return term_id
+    
+    def list_glossary(self, project_id: str) -> List[dict]:
+        """列出项目术语表"""
+        conn = self.get_conn()
+        rows = conn.execute(
+            "SELECT * FROM glossary WHERE project_id = ? ORDER BY frequency DESC",
+            (project_id,)
+        ).fetchall()
+        conn.close()
+        return [dict(r) for r in rows]
+    
+    def delete_glossary_term(self, term_id: str):
+        """删除术语"""
+        conn = self.get_conn()
+        conn.execute("DELETE FROM glossary WHERE id = ?", (term_id,))
+        conn.commit()
+        conn.close()
+    
+    # Phase 3: Get all entities for embedding
+    def get_all_entities_for_embedding(self, project_id: str) -> List[Entity]:
+        """获取所有实体用于 embedding 计算"""
+        return self.list_project_entities(project_id)
 
 
 # Singleton instance