LangChain-10(2) 加餐 编写Agent获取本地Docker运行情况 无技术含量只是思 ...

可以先查看 上一节内容，会对本节有更好的理解。
安装依赖

1. pip install langchainhub

复制代码

编写代码

核心代码

1. @tool
2. def get_docker_info(docker_name: str) -> str:
3.     """Get information about a docker pod container info."""
4.     result = subprocess.run(['docker', 'inspect', str(docker_name)], capture_output=True, text=True)
5.     return result.stdout

复制代码

这里是通过执行 Shell的方式来获取状态的。
通过执行Docker指令之后，可以获取到一大段的文本内容，此时把这些内容交给大模子去处理，大模子对内容进行提取和推理，最终答复我们。

• 注意@tool注解，没有这个注解的话，无法使用
  
• 注意要写"""xxx""" 要写明该工具的先容，大模子将根据先容来选择是否调用
  
• 如果3.5的效果不好，可以尝试使用4
  

1. from langchain import hubfrom langchain.agents import AgentExecutor, toolfrom langchain.agents.output_parsers import XMLAgentOutputParserfrom langchain_openai import ChatOpenAIimport subprocessmodel = ChatOpenAI(    model="gpt-3.5-turbo",)@tooldef search(query: str) -> str:    """Search things about current events."""    return "32 degrees"@tool
2. def get_docker_info(docker_name: str) -> str:
3.     """Get information about a docker pod container info."""
4.     result = subprocess.run(['docker', 'inspect', str(docker_name)], capture_output=True, text=True)
5.     return result.stdout
6. tool_list = [search, get_docker_info]# Get the prompt to use - you can modify this!prompt = hub.pull("hwchase17/xml-agent-convo")# Logic for going from intermediate steps to a string to pass into model# This is pretty tied to the promptdef convert_intermediate_steps(intermediate_steps):    log = ""    for action, observation in intermediate_steps:        log += (            f"<tool>{action.tool}</tool><tool_input>{action.tool_input}"            f"</tool_input><observation>{observation}</observation>"        )    return log# Logic for converting tools to string to go in promptdef convert_tools(tools):    return "\n".join([f"{tool.name}: {tool.description}" for tool in tools])agent = (    {        "input": lambda x: x["input"],        "agent_scratchpad": lambda x: convert_intermediate_steps(            x["intermediate_steps"]        ),    }    | prompt.partial(tools=convert_tools(tool_list))    | model.bind(stop=["</tool_input>", "</final_answer>"])    | XMLAgentOutputParser())agent_executor = AgentExecutor(agent=agent, tools=tool_list)message1 = agent_executor.invoke({"input": "whats the weather in New york?"})print(f"message1: {message1}")message2 = agent_executor.invoke({"input": "what is docker pod which name 'lobe-chat-wzk' info? I want to know it 'Image' url"})print(f"message2: {message2}")

复制代码

执行代码

1. ➜ python3 test10.py
2. message1: {'input': 'whats the weather in New york?', 'output': 'The weather in New York is 32 degrees'}
3. message2: {'input': "what is docker pod which name 'lobe-chat-wzk' info? I want to know it 'Image' url", 'output': 'The Image URL for the docker pod named \'lobe-chat-wzk\' is "lobehub/lobe-chat"'}

复制代码

免责声明：如果侵犯了您的权益，请联系站长，我们会及时删除侵权内容，谢谢合作！更多信息从访问主页：qidao123.com:ToB企服之家，中国第一个企服评测及商务社交产业平台。