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

lightrag/api/config.py

@@ -297,6 +297,9 @@ def parse_args() -> argparse.Namespace:
     args.enable_llm_cache_for_extract = get_env_value(
         "ENABLE_LLM_CACHE_FOR_EXTRACT", True, bool
     )
+    args.enable_llm_cache = get_env_value(
+        "ENABLE_LLM_CACHE", True, bool
+    )
 
     # Inject LLM temperature configuration
     args.temperature = get_env_value("TEMPERATURE", 0.5, float)

lightrag/api/lightrag_server.py

@@ -316,6 +316,7 @@ def create_app(args):
                 "cosine_better_than_threshold": args.cosine_threshold
             },
             enable_llm_cache_for_entity_extract=args.enable_llm_cache_for_extract,
+            enable_llm_cache=args.enable_llm_cache,
             embedding_cache_config={
                 "enabled": True,
                 "similarity_threshold": 0.95,
@@ -347,6 +348,7 @@ def create_app(args):
                 "cosine_better_than_threshold": args.cosine_threshold
             },
             enable_llm_cache_for_entity_extract=args.enable_llm_cache_for_extract,
+            enable_llm_cache=args.enable_llm_cache,
             embedding_cache_config={
                 "enabled": True,
                 "similarity_threshold": 0.95,
@@ -469,6 +471,7 @@ def create_app(args):
                     "graph_storage": args.graph_storage,
                     "vector_storage": args.vector_storage,
                     "enable_llm_cache_for_extract": args.enable_llm_cache_for_extract,
+                    "enable_llm_cache": args.enable_llm_cache,
                 },
                 "auth_mode": auth_mode,
                 "pipeline_busy": pipeline_status.get("busy", False),

lightrag/api/utils_api.py

@@ -229,8 +229,12 @@ def display_splash_screen(args: argparse.Namespace) -> None:
     ASCIIColors.yellow(f"{args.max_async}")
     ASCIIColors.white("    ├─ Max Tokens: ", end="")
     ASCIIColors.yellow(f"{args.max_tokens}")
-    ASCIIColors.white("    └─ Timeout: ", end="")
+    ASCIIColors.white("    ├─ Timeout: ", end="")
     ASCIIColors.yellow(f"{args.timeout if args.timeout else 'None (infinite)'}")
+    ASCIIColors.white("    ├─ LLM Cache Enabled: ", end="")
+    ASCIIColors.yellow(f"{args.enable_llm_cache}")
+    ASCIIColors.white("    └─ LLM Cache for Extraction Enabled: ", end="")
+    ASCIIColors.yellow(f"{args.enable_llm_cache_for_extract}")
 
     # Embedding Configuration
     ASCIIColors.magenta("\n📊 Embedding Configuration:")
@@ -257,10 +261,8 @@ def display_splash_screen(args: argparse.Namespace) -> None:
     ASCIIColors.yellow(f"{args.chunk_overlap_size}")
     ASCIIColors.white("    ├─ Cosine Threshold: ", end="")
     ASCIIColors.yellow(f"{args.cosine_threshold}")
-    ASCIIColors.white("    ├─ Top-K: ", end="")
+    ASCIIColors.white("    └─ Top-K: ", end="")
     ASCIIColors.yellow(f"{args.top_k}")
-    ASCIIColors.white("    └─ LLM Cache for Extraction Enabled: ", end="")
-    ASCIIColors.yellow(f"{args.enable_llm_cache_for_extract}")
 
     # System Configuration
     ASCIIColors.magenta("\n💾 Storage Configuration:")