Merge pull request #1097 from danielaskdd/main

Adjust concurrency limits  more LLM friendly settings for new comers

lightrag/api/README.md

@@ -224,7 +224,7 @@ LightRAG supports binding to various LLM/Embedding backends:
 Use environment variables  `LLM_BINDING` or CLI argument `--llm-binding` to select LLM backend type. Use environment variables  `EMBEDDING_BINDING` or CLI argument `--embedding-binding` to select LLM backend type.
 
 ### Entity Extraction Configuration
-* ENABLE_LLM_CACHE_FOR_EXTRACT: Enable LLM cache for entity extraction (default: false)
+* ENABLE_LLM_CACHE_FOR_EXTRACT: Enable LLM cache for entity extraction (default: true)
 
 It's very common to set `ENABLE_LLM_CACHE_FOR_EXTRACT` to true for test environment to reduce the cost of LLM calls.
 

lightrag/api/utils_api.py

@@ -364,7 +364,7 @@ def parse_args(is_uvicorn_mode: bool = False) -> argparse.Namespace:
 
     # Inject LLM cache configuration
     args.enable_llm_cache_for_extract = get_env_value(
-        "ENABLE_LLM_CACHE_FOR_EXTRACT", False, bool
+        "ENABLE_LLM_CACHE_FOR_EXTRACT", True, bool
     )
 
     # Select Document loading tool (DOCLING, DEFAULT)

lightrag/lightrag.py

@@ -214,7 +214,7 @@ class LightRAG:
     llm_model_max_token_size: int = field(default=int(os.getenv("MAX_TOKENS", 32768)))
     """Maximum number of tokens allowed per LLM response."""
 
-    llm_model_max_async: int = field(default=int(os.getenv("MAX_ASYNC", 16)))
+    llm_model_max_async: int = field(default=int(os.getenv("MAX_ASYNC", 4)))
     """Maximum number of concurrent LLM calls."""
 
     llm_model_kwargs: dict[str, Any] = field(default_factory=dict)
@@ -238,7 +238,7 @@ class LightRAG:
     # Extensions
     # ---
 
-    max_parallel_insert: int = field(default=int(os.getenv("MAX_PARALLEL_INSERT", 20)))
+    max_parallel_insert: int = field(default=int(os.getenv("MAX_PARALLEL_INSERT", 2)))
     """Maximum number of parallel insert operations."""
 
     addon_params: dict[str, Any] = field(