kb_workflow/pipeline/processors/srt.py

@@ -49,7 +49,8 @@ class SRTProcessor(BaseProcessor):
         self,
         state_manager: Optional[WorkflowStateManager] = None,
         enable_correction: bool = True,
-        enable_semantic_segmentation: bool = False
+        enable_semantic_segmentation: bool = False,
+        enable_cache: bool = True
     ):
         """初始化 SRT 处理器
 
@@ -57,6 +58,7 @@ class SRTProcessor(BaseProcessor):
             state_manager: 状态管理器
             enable_correction: 是否启用 ASR 纠错（默认 True）
             enable_semantic_segmentation: 是否启用 LLM 语义分段（默认 False）
+            enable_cache: 是否启用缓存（默认 True，仅在启用语义分段时有效）
         """
         super().__init__(state_manager)
         self.enable_correction = enable_correction
@@ -74,10 +76,19 @@ class SRTProcessor(BaseProcessor):
                 # 创建 AI 客户端
                 ai_client = SimpleAIClient()
                 if ai_client.api_key:
-                    # 创建统一策略，传入 AI 客户端
-                    strategy = UnifiedSegmentationStrategy(ai_client=ai_client)
+                    # 初始化缓存
+                    cache = None
+                    if enable_cache:
+                        from kb_workflow.srt.cache import SemanticCache
+                        cache = SemanticCache()
+
+                    # 创建统一策略，传入 AI 客户端和缓存
+                    strategy = UnifiedSegmentationStrategy(
+                        ai_client=ai_client,
+                        cache=cache
+                    )
                     self.segmenter = SemanticSegmentationEngine(strategy=strategy)
-                    logger.info("Semantic segmentation enabled")
+                    logger.info(f"Semantic segmentation enabled (cache={'enabled' if cache else 'disabled'})")
                 else:
                     logger.info("AI API key not configured, using rule-based segmenter")
                     self.segmenter = SemanticSegmenter()