快速搭建大语言聊天界面 Streamlit + LangChain + Ollama

快速搭建语言聊天界面

快速搭建大语言聊天界面能快速测试我们选用的模型，通过命令行测试不是很直观。
本文采用 Streamlit + LangChain + Ollama 搭建，10 行代码搞定。

创建 Streamlit App.py

修改Ollama IP 地址 和端口到你本地的 Ollama

#app.py

from langchain_community.llms import Ollama
import streamlit as st
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler

llm = Ollama(model="testllama3", base_url="http://10.91.3.116:11434", verbose=True)

def sendPrompt(prompt):
    global llm
    response = llm.invoke(prompt)
    return response

st.title("Chat with Ollama")
if "messages" not in st.session_state.keys(): 
    st.session_state.messages = [
        {"role": "assistant", "content": "Ask me a question !"}
    ]

if prompt := st.chat_input("Your question"): 
    st.session_state.messages.append({"role": "user", "content": prompt})

for message in st.session_state.messages: 
    with st.chat_message(message["role"]):
        st.write(message["content"])
        
if st.session_state.messages[-1]["role"] != "assistant":
    with st.chat_message("assistant"):
        with st.spinner("Thinking..."):
            response = sendPrompt(prompt)
            print(response)
            st.write(response)
            message = {"role": "assistant", "content": response}
            st.session_state.messages.append(message)   

安装依赖

pip install streamlit langchain langchain-community

运行

streamlit  run app.py

Dockerfile

也可以创建容器，方便后续使用。

FROM python:latest
# Create app directory
WORKDIR / app
# Copy the files
COPY requirements.txt ./
COPY app.py ./
#install the dependecies
RUN pip install -i https://pypi.tuna.tsinghua.edu.cn/simple -r requirements.txt
EXPOSE 8501
ENTRYPOINT ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0"]