Update src/app.py

src/app.py

@@ -1,19 +1,19 @@
 import os
 import chainlit as cl
 from langchain_community.llms import Ollama
-from langchain_core.callbacks import CallbackManager, StreamingStdOutCallbackHandler
 
 # Get the Ollama URL from the environment, defaulting to localhost if not found
 OLLAMA_BASE_URL = os.getenv("OLLAMA_BASE_URL", "https://thanthamky-ollama-api-analytic.hf.space")
 # Define the model you want to use (make sure you pull it first!)
 MODEL_NAME = "qwen3:0.6b" 
+
+
 @cl.on_chat_start
 async def on_chat_start():
-    # Initialize the Ollama LLM
+    # Initialize the Ollama LLM without the forbidden callback_manager
     llm = Ollama(
         base_url=OLLAMA_BASE_URL,
-        model=MODEL_NAME,
-        callback_manager=CallbackManager([StreamingStdOutCallbackHandler()])
+        model=MODEL_NAME
     )
     
     # Store the LLM in the user session
@@ -32,7 +32,7 @@ async def on_message(message: cl.Message):
     msg = cl.Message(content="")
     await msg.send()
     
-    # Stream the response from Ollama
+    # Stream the response natively to the Chainlit UI
     async for chunk in llm.astream(message.content):
         if chunk:
             await msg.stream_token(chunk)