chore: update inference dependencies and refactor model loading logic

inference.py

@@ -15,6 +15,11 @@ import os
 import json
 import time
 import re
+from dotenv import load_dotenv
+
+# Load .env variables before anything else
+load_dotenv()
+
 import requests
 from openai import OpenAI
 

requirements.txt

@@ -3,3 +3,4 @@ uvicorn[standard]==0.30.6
 pydantic==2.7.4
 requests==2.32.3
 openai==1.40.0
+python-dotenv==1.0.1