Update app.py

app.py

@@ -40,5 +40,20 @@ def root():
 async def generate(request: Request):
     data = await request.json()
     prompt = data.get("prompt", "")
-    response = llm(prompt, max_tokens=128, temperature=0.7)
-    return {"response": response["choices"][0]["text"]}
+
+    print("🧾 Received prompt:", prompt)
+
+    response = llm.create_chat_completion(
+        messages=[
+            {"role": "system", "content": "You are a helpful assistant."},
+            {"role": "user", "content": prompt}
+        ],
+        max_tokens=1024,
+        temperature=0.7,
+    )
+
+    print("📤 Raw model response:", response)
+
+    return {
+        "response": response["choices"][0]["message"]["content"].strip()
+    }