Reverting to non-streaming version

app.py

@@ -157,31 +157,15 @@ async def start_chat():
 # (2) Invokes the RAG chain with the user's message
 # (3) Extracts the content from the response and sends it back to the user
 
-@cl.on_message
+@cl.on_message 
 async def handle_message(message: cl.Message):
     settings = cl.user_session.get("settings")
 
-    # Initialize the stream message in Chainlit
-    stream_msg = cl.Message(content="")
-    await stream_msg.send()  # Send initial empty message to start the stream
+    response = retrieval_augmented_qa_chain.invoke({"question": message.content})
 
-    # Create a generator from the RAG chain
-    response_generator = retrieval_augmented_qa_chain.stream({"question": message.content})
 
-    # Use a standard for loop instead of async for
-    for response_chunk in response_generator:
-        # Extract the content from the chunk
-        chunk_content = response_chunk.get("response", {}).get("content", "")
-        if chunk_content:
-            # Stream the chunk to Chainlit
-            await stream_msg.stream_token(chunk_content)
+    # Extracting and sending just the content
+    content = response["response"].content
+    pretty_content = content.strip()  # Remove any leading/trailing whitespace
 
-    ## Remove to stream the response
-    # response = retrieval_augmented_qa_chain.invoke({"question": message.content})
-
-
-##    # Extracting and sending just the content
-##    content = response["response"].content
-##    pretty_content = content.strip()  # Remove any leading/trailing whitespace
-
-##   await cl.Message(content=pretty_content).send()
+    await cl.Message(content=pretty_content).send()