Add embedding cache config and disable LLM cache for entity extraction for API Server

lightrag/api/lightrag_server.py

@@ -919,6 +919,12 @@ def create_app(args):
             vector_db_storage_cls_kwargs={
                 "cosine_better_than_threshold": args.cosine_threshold
             },
+            enable_llm_cache_for_entity_extract=False,
+            embedding_cache_config={
+                "enabled": True,
+                "similarity_threshold": 0.95,
+                "use_llm_check": False,
+            },
         )
     else:
         rag = LightRAG(
@@ -942,6 +948,12 @@ def create_app(args):
             vector_db_storage_cls_kwargs={
                 "cosine_better_than_threshold": args.cosine_threshold
             },
+            enable_llm_cache_for_entity_extract=False,
+            embedding_cache_config={
+                "enabled": True,
+                "similarity_threshold": 0.95,
+                "use_llm_check": False,
+            },
         )
 
     async def index_file(file_path: Union[str, Path]) -> None: