实现大模型的流式输出

构建基本的LLM聊天应用程序 - Streamlit Docs --- Build a basic LLM chat app - Streamlit Docs

# Streamed response emulator
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)

# Display assistant response in chat message container
with st.chat_message("assistant"):
    response = st.write_stream(response_generator())
# Add assistant response to chat history
st.session_state.messages.append({"role": "assistant", "content": response})

    # Display assistant response in chat message container
    with st.chat_message("assistant"):
        stream = client.chat.completions.create(
            model=st.session_state["openai_model"],
            messages=[
                {"role": m["role"], "content": m["content"]}
                for m in st.session_state.messages
            ],
            stream=True,
        )
        response = st.write_stream(stream)
    st.session_state.messages.append({"role": "assistant", "content": response})

yield

一个函数里面如果被定义了yield

那么这个函数就是一个生成器函数

可以通过next方法来使用这个生成器

‍