temp-file

gistfile1.txt

import streamlit as st
import boto3
import json

# import random
# import string

region = boto3.Session(profile_name="interbank-poc").region_name
session = boto3.Session(profile_name="interbank-poc", region_name=region)
lambda_client = session.client("lambda")

st.title("Interbank Asistant")

sessionId = ""
# sessionId = ''.join(random.choices(string.ascii_uppercase + string.digits, k=12))
print(sessionId)

# Initialize chat history
if "messages" not in st.session_state:
    st.session_state.messages = []

# Initialize session id
if "sessionId" not in st.session_state:
    st.session_state["sessionId"] = sessionId

# Display chat messages from history on app rerun
for message in st.session_state.messages:
    with st.chat_message(message["role"]):
        st.markdown(message["content"])

# React to user input
if prompt := st.chat_input("En que te puedo ayudar?"):

    # Display user input in chat message container
    question = prompt
    st.chat_message("user").markdown(question)

    # Call lambda function to get response from the model
    payload = json.dumps(
        {
            "question": "<br><br>you are the virtual assistant to the martech team in interbank, interbank is the number one financial institution in peru. <br>your job is to provide answers to this team regarding the usage of Adobe experience manager. <br>Do not hallucinate any answer, always provide answers contained in the knowledge base. <br> always ask a follow up question. <br> the client needs the answer to this query: "
            + prompt
            + "<br><br>return response in markdown format",
            "sessionId": st.session_state["sessionId"],
        }
    )
    print(payload)
    result = lambda_client.invoke(FunctionName="InvokeKnowledgeBase", Payload=payload)

    result = json.loads(result["Payload"].read().decode("utf-8"))
    print(result)

    answer = result["body"]["answer"]
    sessionId = result["body"]["sessionId"]

    st.session_state["sessionId"] = sessionId

    # Add user input to chat history
    st.session_state.messages.append({"role": "user", "content": question})

    # Display assistant response in chat message container
    with st.chat_message("assistant"):
        st.markdown(answer)

    # Add assistant response to chat history
    st.session_state.messages.append({"role": "assistant", "content": answer})