二、安装gradio 一句命令搞定 pip install gradio
chat.py代码如下：
[Python] 纯文本查看 复制代码from sparkai.llm.llm import ChatSparkLLM, ChunkPrintHandler
from sparkai.core.messages import ChatMessage
import gradio as gr
#星火认知大模型Spark3.5 Max的URL值，其他版本大模型URL值请前往文档（https://www.xfyun.cn/doc/spark/Web.html）查看
SPARKAI_URL = 'ws(s)://spark-api.xf-yun.com/v1.1/chat'
#星火认知大模型调用秘钥信息，请前往讯飞开放平台控制台（https://console.xfyun.cn/services/bm35）查看
SPARKAI_APP_ID = '替换成自己的appid'
SPARKAI_API_SECRET = '替换成自己的secret'
SPARKAI_API_KEY = '替换成自己的key'
#星火认知大模型Spark3.5 Max的domain值，其他版本大模型domain值请前往文档（https://www.xfyun.cn/doc/spark/Web.html）查看
SPARKAI_DOMAIN = 'general'
with gr.Blocks() as demo:
chatbot = gr.Chatbot()
msg = gr.Textbox()
clear = gr.Button("清除")
def respond(message, chat_history):
spark = ChatSparkLLM(
spark_api_url=SPARKAI_URL,
spark_app_id=SPARKAI_APP_ID,
spark_api_key=SPARKAI_API_KEY,
spark_api_secret=SPARKAI_API_SECRET,
spark_llm_domain=SPARKAI_DOMAIN,
streaming=False,
)
messages = [ChatMessage(
role="user",
content=message
)]
handler = ChunkPrintHandler()
a = spark.generate([messages], callbacks=[handler])
print(a.generations[0][0].text)
chat_history.append((message, a.generations[0][0].text))
return "", chat_history
msg.submit(respond, [msg, chatbot], [msg, chatbot])
clear.click(lambda: None, None, chatbot, queue=False)
demo.launch()
三、运行代码，python chat.py
显示如下信息即成功：
Running on local URL: http://127.0.0.1:7860
To create a public link, set `share=True` in `launch()`.
四、打开浏览器 输入http://127.0.0.1:7860 界面如下：
[i]
[i]
Chatbox显示聊天的记录，Textbox为输入框
