Use LLM_MODEL env var in Azure OpenAI function

- Remove model parameter from azure_openai_complete (all LLM complete functions must have the same parameter structure)
- Use LLM_MODEL env var in Azure OpenAI function
- Comment out Lollms example in .env.example (duplication with Ollama example)

lightrag/llm.py

@@ -622,11 +622,11 @@ 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,