Update LLM class to use environment variables for server and port configuration

_llm.py

@@ -5,6 +5,12 @@ import queue
 import threading
 from pprint import pprint
 import re
+from dotenv import load_dotenv
+import os
+
+
+load_dotenv()
+
 
 class LLM:
     def __init__(
@@ -28,8 +34,8 @@ class LLM:
                                      which processes requests concurrently. Defaults to False.
         """
 
-        self.server = "192.168.1.12"
+        self.server = os.getenv("LLM_URL")
-        self.port = 3300  # 11440 All 4 GPU # 4500 "SW" 3300 balancer
+        self.port = os.getenv("LLM_PORT")
         self.model = model
         self.temperature = temperature
         self.system_message = {"role": "system", "content": system_prompt}