Update rag_engine.py

rag_engine.py

@@ -126,8 +126,10 @@ class RAGEngine:
         return answer
 
     def stream_answer(self, query):
-        """Streamed generation for Streamlit."""
-        answer = self.answer_query(query)
-        for word in answer.split():
-            yield word + " "
-            time.sleep(0.02)  # Feel free to tweak typing speed
+        # Simulate streaming response, yielding chunks of text
+        # (This is just an example of how you'd stream chunks of data)
+        result = self.get_answer(query)  # Retrieve the full answer
+        # Here you can yield chunks of the answer instead of returning it all at once.
+        chunk_size = 1000  # Define the chunk size
+        for i in range(0, len(result), chunk_size):
+            yield result[i:i + chunk_size]  # Yield parts of the response