pre-commit run --all-files

lightrag/api/lightrag_server.py

@@ -33,6 +33,7 @@ from dotenv import load_dotenv
 
 load_dotenv()
 
+
 def estimate_tokens(text: str) -> int:
     """Estimate the number of tokens in text
     Chinese characters: approximately 1.5 tokens per character
@@ -587,9 +588,12 @@ def create_app(args):
     # Initialize document manager
     doc_manager = DocumentManager(args.input_dir)
 
-
     async def openai_alike_model_complete(
-        prompt, system_prompt=None, history_messages=[], keyword_extraction=False, **kwargs
+        prompt,
+        system_prompt=None,
+        history_messages=[],
+        keyword_extraction=False,
+        **kwargs,
     ) -> str:
         return await openai_complete_if_cache(
             args.llm_model,
@@ -602,7 +606,11 @@ def create_app(args):
         )
 
     async def azure_openai_model_complete(
-        prompt, system_prompt=None, history_messages=[], keyword_extraction=False, **kwargs
+        prompt,
+        system_prompt=None,
+        history_messages=[],
+        keyword_extraction=False,
+        **kwargs,
     ) -> str:
         return await azure_openai_complete_if_cache(
             args.llm_model,
@@ -642,7 +650,7 @@ def create_app(args):
     )
 
     # Initialize RAG
-    if args.llm_binding in ["lollms", "ollama"] :
+    if args.llm_binding in ["lollms", "ollama"]:
         rag = LightRAG(
             working_dir=args.working_dir,
             llm_model_func=lollms_model_complete
@@ -658,7 +666,7 @@ def create_app(args):
             },
             embedding_func=embedding_func,
         )
-    else :
+    else:
         rag = LightRAG(
             working_dir=args.working_dir,
             llm_model_func=azure_openai_model_complete