GPT-Clone with subscription logic

Using Streamlit
1

I want to develop a noob subscription logic. You get free 3 messages with chatGPT
Couldn’t figure out how the message history is carried on the UI in the doc

  • accept the prompt from chat_input and show reponse

carry the message history in the UI and st.session_state["messages"]


import streamlit as st
import openai
import requests
import os
import random
import time

import uuid



messages_ls=[
        {"role": "system", "content": "You are a helpful, pattern-following assistant."},
        {"role": "user", "content": "Help me translate the following corporate jargon into plain English."},
        {"role": "assistant", "content": "Sure, I'd be happy to!"},
        {"role": "user", "content": "New synergies will help drive top-line growth."},
        {"role": "assistant", "content": "Things working well together will increase revenue."},
        {"role": "user", "content": "Let's circle back when we have more bandwidth to touch base on opportunities for increased leverage."},
        {"role": "assistant", "content": "Let's talk later when we're less busy about how to do better."},
        {"role": "user", "content": "This late pivot means we don't have time to boil the ocean for the client deliverable."},
    ]


openai.api_key = 'sk-I3xxxxxxhdfeh34l4gj4r4jffifen'


st.title("ChatGPT-like clone")


if "openai_model" not in st.session_state:
    st.session_state["openai_model"] = "gpt-3.5-turbo"
# d={} , st.session_state
if "messages" not in st.session_state:
    st.session_state["messages"] = messages_ls

## to create list of tuple
## ask for creating a user id for session


user_id=uuid.uuid4().hex
# if started the chat -- provide 3 responses

if prompt:= st.chat_input(" "):
    with st.chat_message("user"):
        st.markdown(prompt)
    with st.chat_message("assistant"):
        response=openai.ChatCompletion.create(model=st.session_state["openai_model"],messages=st.session_state["messages"],temperature=0.7,)
        st.markdown(response["choices"][0]["message"]["content"])
    st.session_state["messages"].append({"role":"assistant", "content":response["choices"][0]["message"]["content"]})
2

Hi @x31

The chat history is saved to the messages Session State:

while new messages are added to the chat history via the append method once the LLM response has been generated:

Perhaps you can implement a counter that counts the number of assistant generated responses up until a certain threshold and once that is reached, then perform the specific task that you’d like it to do such as informing the user that their trial period has been reached.

3

Hi @dataprofessor

Thank you for response. I would really appreciate if you can explain once I have the prompt from user, how can I apply a loop to get next 3 inputs from user. --given that st.chat_input() can be used only 1 time.


##for loop somewhere here
if prompt:= st.chat_input(" "):
    with st.chat_message("user"):
        st.markdown(prompt)
    with st.chat_message("assistant"):
        response=openai.ChatCompletion.create(model=st.session_state["openai_model"],messages=st.session_state["messages"],temperature=0.7,)
        st.markdown(response["choices"][0]["message"]["content"])
    st.session_state["messages"].append({"role":"assistant", "content":response["choices"][0]["message"]["content"]})
4

This topic was automatically closed 180 days after the last reply. New replies are no longer allowed.