Add ENABLE_LLM_CACHE env support

env.example

@@ -40,7 +40,6 @@ WEBUI_DESCRIPTION="Simple and Fast Graph Based RAG System"
 # MAX_TOKEN_ENTITY_DESC=4000
 
 ### Settings for document indexing
-ENABLE_LLM_CACHE_FOR_EXTRACT=true
 SUMMARY_LANGUAGE=English
 # CHUNK_SIZE=1200
 # CHUNK_OVERLAP_SIZE=100
@@ -64,6 +63,8 @@ TEMPERATURE=0.5
 MAX_ASYNC=4
 ### Max tokens send to LLM (less than context size of the model)
 MAX_TOKENS=32768
+ENABLE_LLM_CACHE=true
+ENABLE_LLM_CACHE_FOR_EXTRACT=true
 
 ### Ollama example (For local services installed with docker, you can use host.docker.internal as host)
 LLM_BINDING=ollama