Streamlit 聊天窗体界面

上一篇 《Streamlit 页面处理流程》中简要介绍了 Streamlit 页面的处理流程，接下来我们就看一下如何使用 Streamlit 构建一个常见的AI聊天窗体界面。这篇文章的代码源自Streamlit官方文档（Build a basic LLM chat app），额外使用了container空间。

Streamlit有专门用于构建聊天窗口的widget，例如 chat_input、chat_message、st.write_stream 等，下面的代码，综合使用了这些widget，模拟了一个常见的AI聊天窗体界面。

import streamlit as st import random import time def response_generator(): response = random.choice( [ "Hello there! How can I assist you today?", "Hi, human! Is there anything I can help you with?", "Do you need help?", ] ) for word in response.split(): yield word + " " time.sleep(0.05) st.title("Simple chat") chat_container = st.container() with chat_container: if "msgs" not in st.session_state: st.session_state.msgs = [] for msg in st.session_state.msgs: with st.chat_message(msg["role"]): st.markdown(msg["content"]) prompt = st.chat_input("有什么问题，尽管提问吧（shift + enter换行）") if prompt : with st.chat_message("user") : st.markdown(prompt) st.session_state.msgs.append({ "role": "user", "content": prompt }) with st.chat_message("assistant"): response = st.write_stream(response_generator()) st.session_state.msgs.append({"role":"assistant", "content":response})

感谢阅读，希望这篇文章能给你带来帮助！