Streamlit Chat Demo

stream chat

from langchain_community.chat_models.tongyi import ChatTongyi
import streamlit as st
from openai import OpenAI

st.title("ChatGPT-like clone")

# Set OpenAI API key from Streamlit secrets
# client = OpenAI(api_key=st.secrets["OPENAI_API_KEY"])
client = ChatTongyi(model='qwen2-72b-instruct', top_p=0.8, streaming=True)

# Set a default model
if "openai_model" not in st.session_state:
    st.session_state["openai_model"] = "gpt-3.5-turbo"

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

# 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"])

# Accept user input
if prompt := st.chat_input("Please type a message..."):
    # Add user message to chat history
    st.session_state.messages.append({"role": "user", "content": prompt})
    # Display user message in chat message container
    with st.chat_message("user"):
        st.markdown(prompt)
    # Display assistant response in chat message container
    with st.chat_message("assistant"):
        stream = client.stream(
            input=[
                {"role": m["role"], "content": m["content"]}
                for m in st.session_state.messages
            ],
            streaming=True,
        )
        response = st.write_stream(stream)
    st.session_state.messages.append({"role": "assistant", "content": response})

onechat

import streamlit as st
from langchain_community.chat_models.tongyi import ChatTongyi
from langchain.prompts import ChatPromptTemplate
from langchain.output_parsers import ResponseSchema, StructuredOutputParser
from langchain.memory import ConversationBufferMemory
from langchain.chains import SequentialChain, ConversationChain
from dotenv import load_dotenv
import json
load_dotenv()

st.title('Router Mode')

llm = ChatTongyi(model='qwen2-72b-instruct', top_p=0.8, streaming=True)


def generate_response(input_text):
    # resp = llm.invoke(input_text).content
    chunks = ""
    obj = st.empty()
    for chunk in llm.stream(input_text):
        chunks += chunk.content
        print(chunk.content, end='', flush=True)
        obj.info(chunks)
    

with st.form('my_form'):
    text = st.text_area('Enter text:', 'What are the three key pieces of advice for learning how to code?')
    submitted = st.form_submit_button('Submit')
    if submitted:
        generate_response(text)