Merge branch 'main' into main

lightrag-server.service.example

@@ -9,7 +9,7 @@ User=netman
 MemoryHigh=8G
 MemoryMax=12G
 WorkingDirectory=/home/netman/lightrag-xyj
-ExecStart=/home/netman/lightrag-xyj/lightrag/api/start_lightrag_server.sh
+ExecStart=/home/netman/lightrag-xyj/start_lightrag_server.sh
 Restart=always
 RestartSec=10
 

lightrag/api/README.md

@@ -427,7 +427,7 @@ This intelligent caching mechanism:
 
 ## Install Lightrag as a Linux Service
 
-Create your service file: `lightrag.sevice`. Modified the following lines from `lightrag.sevice.example`
+Create your service file: `lightrag-server.sevice`. Modified the following lines from `lightrag-server.sevice.example`
 
 ```text
 Description=LightRAG Ollama Service

lightrag/llm.py

@@ -626,16 +626,11 @@ async def nvidia_openai_complete(
 
 
 async def azure_openai_complete(
-    model: str = "gpt-4o-mini",
-    prompt="",
-    system_prompt=None,
-    history_messages=[],
-    keyword_extraction=False,
-    **kwargs,
+    prompt, system_prompt=None, history_messages=[], keyword_extraction=False, **kwargs
 ) -> str:
     keyword_extraction = kwargs.pop("keyword_extraction", None)
     result = await azure_openai_complete_if_cache(
-        model,
+        os.getenv("LLM_MODEL", "gpt-4o-mini"),
         prompt,
         system_prompt=system_prompt,
         history_messages=history_messages,