changes v3

question.py

@@ -52,7 +52,14 @@ async def ask_question(input: QuestionInput):
 
     # result = client.text_generation(prompt, max_new_tokens=256, temperature=0.7)
 
-    result = client.text_generation(prompt, max_new_tokens=256, temperature=0.7)
+    result = client.conversational(
+        messages=[
+            {"role": "system", "content": "You are a helpful assistant that uses provided news context to answer questions."},
+            {"role": "user", "content": f"Context:\n{context}\n\nQuestion: {question}"}
+        ],
+        max_new_tokens=256,
+        temperature=0.7
+    )
 
     return {
         "question": question,