diff --git a/env.example b/env.example
index e4521132..01b87586 100644
--- a/env.example
+++ b/env.example
@@ -91,6 +91,8 @@ ENABLE_LLM_CACHE=true
 ### For rerank model deployed by vLLM use cohere binding
 #########################################################
 RERANK_BINDING=null
+### Enable rerank by default in query params
+# RERANK_BY_DEFAULT=True
 ### rerank score chunk filter(set to 0.0 to keep all chunks, 0.6 or above if LLM is not strong enought)
 # MIN_RERANK_SCORE=0.0
 
diff --git a/lightrag/api/lightrag_server.py b/lightrag/api/lightrag_server.py
index 7d94eec4..328e7953 100644
--- a/lightrag/api/lightrag_server.py
+++ b/lightrag/api/lightrag_server.py
@@ -391,7 +391,7 @@ def create_app(args):
         ),
     )
 
-    # Configure rerank function based on enable_rerank parameter
+    # Configure rerank function based on args.rerank_bindingparameter
     rerank_model_func = None
     if args.rerank_binding != "null":
         from lightrag.rerank import cohere_rerank, jina_rerank, ali_rerank
diff --git a/lightrag/base.py b/lightrag/base.py
index cfe48eea..fe92e785 100644
--- a/lightrag/base.py
+++ b/lightrag/base.py
@@ -157,7 +157,7 @@ class QueryParam:
     If proivded, this will be use instead of the default vaulue from prompt template.
     """
 
-    enable_rerank: bool = os.getenv("ENABLE_RERANK", "false").lower() == "true"
+    enable_rerank: bool = os.getenv("RERANK_BY_DEFAULT", "true").lower() == "true"
     """Enable reranking for retrieved text chunks. If True but no rerank model is configured, a warning will be issued.
     Default is True to enable reranking when rerank model is available.
     """