diff --git a/README-zh.md b/README-zh.md
index 5603ad99..d0de20da 100644
--- a/README-zh.md
+++ b/README-zh.md
@@ -334,7 +334,8 @@ class QueryParam:
     Format: [{"role": "user/assistant", "content": "message"}].
     """
 
-    history_turns: int = 3
+    # Deprated: history message have negtive effect on query performance
+    history_turns: int = 0
     """Number of complete conversation turns (user-assistant pairs) to consider in the response context."""
 
     ids: list[str] | None = None
diff --git a/README.md b/README.md
index a3abefd8..664a852e 100644
--- a/README.md
+++ b/README.md
@@ -335,7 +335,8 @@ class QueryParam:
     Format: [{"role": "user/assistant", "content": "message"}].
     """
 
-    history_turns: int = 3
+    # Deprated: history message have negtive effect on query performance
+    history_turns: int = 0
     """Number of complete conversation turns (user-assistant pairs) to consider in the response context."""
 
     ids: list[str] | None = None
@@ -614,7 +615,6 @@ conversation_history = [
 query_param = QueryParam(
     mode="mix",  # or any other mode: "local", "global", "hybrid"
     conversation_history=conversation_history,  # Add the conversation history
-    history_turns=3  # Number of recent conversation turns to consider
 )
 
 # Make a query that takes into account the conversation history
diff --git a/env.example b/env.example
index 850538fa..0b863c9b 100644
--- a/env.example
+++ b/env.example
@@ -53,7 +53,6 @@ OLLAMA_EMULATING_MODEL_TAG=latest
 ########################
 # LLM responde cache for query (Not valid for streaming response)
 ENABLE_LLM_CACHE=true
-# HISTORY_TURNS=0
 # COSINE_THRESHOLD=0.2
 ### Number of entities or relations retrieved from KG
 # TOP_K=40
diff --git a/lightrag/base.py b/lightrag/base.py
index 35d5caae..fff7557d 100644
--- a/lightrag/base.py
+++ b/lightrag/base.py
@@ -100,6 +100,7 @@ class QueryParam:
     Format: [{"role": "user/assistant", "content": "message"}].
     """
 
+    # Deprecated: history message have negtive effect on query performance
     history_turns: int = int(os.getenv("HISTORY_TURNS", str(DEFAULT_HISTORY_TURNS)))
     """Number of complete conversation turns (user-assistant pairs) to consider in the response context."""
 
diff --git a/lightrag/constants.py b/lightrag/constants.py
index bea8a00f..9f066ec5 100644
--- a/lightrag/constants.py
+++ b/lightrag/constants.py
@@ -25,9 +25,10 @@ DEFAULT_CHUNK_TOP_K = 10
 DEFAULT_MAX_ENTITY_TOKENS = 10000
 DEFAULT_MAX_RELATION_TOKENS = 10000
 DEFAULT_MAX_TOTAL_TOKENS = 30000
-DEFAULT_HISTORY_TURNS = 0
 DEFAULT_COSINE_THRESHOLD = 0.2
 DEFAULT_RELATED_CHUNK_NUMBER = 5
+# Deprated: history message have negtive effect on query performance
+DEFAULT_HISTORY_TURNS = 0
 
 # Rerank configuration defaults
 DEFAULT_ENABLE_RERANK = True