Update app.py

app.py

@@ -23,11 +23,26 @@ llm = Llama(
 @app.get("/")
 async def generate_text():
     try:
+        """
         output = llm(
           "Q: Name the planets in the solar system? A: ", 
           max_tokens=32, 
           stop=["Q:", "\n"], 
           echo=True)
+        """
+        output = llm.create_chat_completion(
+        messages=[
+        {
+            "role": "system",
+            "content": "You are a helpful assistant that outputs in JSON.",
+        },
+        {"role": "user", "content": "Who won the world series in 2020"},
+    ],
+    response_format={
+        "type": "json_object",
+    },
+    temperature=0.7,
+)
         return output
     except Exception as e:
         raise HTTPException(status_code=500, detail=str(e))