Update app.py

app.py

@@ -23,13 +23,21 @@ def query_llm(prompt, model_name=None):
         response = requests.post("http://localhost:11434/api/generate", json={"model": model_name, "prompt": prompt, "stream": False})
         return response.json().get("response", "")
     else:
-        import openai
-        openai.api_key = "your-api-key"  # Replace or load from environment
-        response = openai.ChatCompletion.create(
-            model="gpt-4",
-            messages=[{"role": "user", "content": prompt}],
-            temperature=0.7
-        )
+        # Replace or load from environment
+        client = OpenAI(
+    base_url="https://api.studio.nebius.com/v1/",
+    api_key=os.environ.get("NEBIUS_API_KEY")
+)
+        response = client.chat.completions.create(
+    model="meta-llama/Llama-3.3-70B-Instruct",
+    max_tokens=512,
+    temperature=0.6,
+    top_p=0.9,
+    extra_body={
+        "top_k": 50
+    },
+    messages=[]
+)
         return response["choices"][0]["message"]["content"]
 
 # === Step 1: Parse intent ===