few more changes

question.py

@@ -50,7 +50,11 @@ async def ask_question(input: QuestionInput):
     # Build prompt
     prompt = f"<s>[INST] Use the context below to answer the question. If the context is insufficient, say 'I am unable to answer'.\n\nContext:\n{context}\n\nQuestion: {question} [/INST]"
 
-    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": "user", "content": prompt}]
+    )
 
     return {
         "question": question,