diff --git a/lightrag/api/lightrag_server.py b/lightrag/api/lightrag_server.py
index 12ee9a03..af413f58 100644
--- a/lightrag/api/lightrag_server.py
+++ b/lightrag/api/lightrag_server.py
@@ -753,13 +753,15 @@ def create_app(args):
     async def openai_alike_model_complete(
         prompt,
         system_prompt=None,
-        history_messages=[],
+        history_messages=None,
         keyword_extraction=False,
         **kwargs,
     ) -> str:
         keyword_extraction = kwargs.pop("keyword_extraction", None)
         if keyword_extraction:
             kwargs["response_format"] = GPTKeywordExtractionFormat
+        if history_messages is None:
+            history_messages = []
         return await openai_complete_if_cache(
             args.llm_model,
             prompt,
@@ -773,13 +775,15 @@ def create_app(args):
     async def azure_openai_model_complete(
         prompt,
         system_prompt=None,
-        history_messages=[],
+        history_messages=None,
         keyword_extraction=False,
         **kwargs,
     ) -> str:
         keyword_extraction = kwargs.pop("keyword_extraction", None)
         if keyword_extraction:
             kwargs["response_format"] = GPTKeywordExtractionFormat
+        if history_messages is None:
+            history_messages = []
         return await azure_openai_complete_if_cache(
             args.llm_model,
             prompt,
diff --git a/lightrag/llm/openai.py b/lightrag/llm/openai.py
index 4eaca093..4ba06d2a 100644
--- a/lightrag/llm/openai.py
+++ b/lightrag/llm/openai.py
@@ -89,11 +89,13 @@ async def openai_complete_if_cache(
     model,
     prompt,
     system_prompt=None,
-    history_messages=[],
+    history_messages=None,
     base_url=None,
     api_key=None,
     **kwargs,
 ) -> str:
+    if history_messages is None:
+        history_messages = []
     if api_key:
         os.environ["OPENAI_API_KEY"] = api_key
 
@@ -146,8 +148,14 @@ async def openai_complete_if_cache(
 
 
 async def openai_complete(
-    prompt, system_prompt=None, history_messages=[], keyword_extraction=False, **kwargs
+    prompt,
+    system_prompt=None,
+    history_messages=None,
+    keyword_extraction=False,
+    **kwargs,
 ) -> Union[str, AsyncIterator[str]]:
+    if history_messages is None:
+        history_messages = []
     keyword_extraction = kwargs.pop("keyword_extraction", None)
     if keyword_extraction:
         kwargs["response_format"] = "json"
@@ -162,8 +170,14 @@ async def openai_complete(
 
 
 async def gpt_4o_complete(
-    prompt, system_prompt=None, history_messages=[], keyword_extraction=False, **kwargs
+    prompt,
+    system_prompt=None,
+    history_messages=None,
+    keyword_extraction=False,
+    **kwargs,
 ) -> str:
+    if history_messages is None:
+        history_messages = []
     keyword_extraction = kwargs.pop("keyword_extraction", None)
     if keyword_extraction:
         kwargs["response_format"] = GPTKeywordExtractionFormat
@@ -177,8 +191,14 @@ async def gpt_4o_complete(
 
 
 async def gpt_4o_mini_complete(
-    prompt, system_prompt=None, history_messages=[], keyword_extraction=False, **kwargs
+    prompt,
+    system_prompt=None,
+    history_messages=None,
+    keyword_extraction=False,
+    **kwargs,
 ) -> str:
+    if history_messages is None:
+        history_messages = []
     keyword_extraction = kwargs.pop("keyword_extraction", None)
     if keyword_extraction:
         kwargs["response_format"] = GPTKeywordExtractionFormat
@@ -192,8 +212,14 @@ async def gpt_4o_mini_complete(
 
 
 async def nvidia_openai_complete(
-    prompt, system_prompt=None, history_messages=[], keyword_extraction=False, **kwargs
+    prompt,
+    system_prompt=None,
+    history_messages=None,
+    keyword_extraction=False,
+    **kwargs,
 ) -> str:
+    if history_messages is None:
+        history_messages = []
     keyword_extraction = kwargs.pop("keyword_extraction", None)
     result = await openai_complete_if_cache(
         "nvidia/llama-3.1-nemotron-70b-instruct",  # context length 128k