Langchain agent streamlit callback Handler

[okbro9]

I’m creating a SQL agent using

from langchain.agents import create_agent

from langchain_community.agent_toolkits import SQLDatabaseToolkit

from langchain_community.callbacks import StreamlitCallbackHandler

from langchain_community.utilities import SQLDatabase

from langchain_groq import ChatGroq

i converted the DB into SQLDatabaseToolkit and passed it to the create_agent.
The problem I’m facing is, that I the model thinking and reasoning is not visible in streamlit UI, I tried many times but it’s not working instead of showing the “thinking” it is just blank and at last it provides the output in end. I tried with llama, GPToss and qwen models

code snippet:

with st.chat_message("ai"):

        st_callback = StreamlitCallbackHandler(st.container())

        # response = agent.invoke({

        #     "messages": [{"role": "user", "content": user_query}]

        # }, config={"callbacks": [st_callback]})


        for event in agent.stream(

            {"messages": [{"role": "user", "content": user_query}]},

            config={"callbacks": [st_callback]},

            stream_mode="messages"

        ):
            pass

[okbro9]

nothing is shown inside container!