Skip to main content

人工干预的工具验证

本教程演示了如何为任何工具添加人工验证。我们将使用HumanApprovalCallbackhandler来实现这一点。

假设我们需要使用ShellTool。将此工具添加到自动化流程中明显存在风险。让我们看看如何强制对进入此工具的输入进行人工手动审批。

注意：我们通常不建议使用ShellTool。滥用它的方法有很多，而且大多数用例都不需要它。我们在此只是为了演示目的使用它。

from langchain.callbacks import HumanApprovalCallbackHandler  
from langchain.tools import ShellTool

API Reference:​

tool = ShellTool()  
print(tool.run("echo Hello World!"))  
    Hello World!

添加人工审批​

将默认的HumanApprovalCallbackHandler添加到工具中将确保用户必须手动批准工具的每一个输入，然后命令才会真正执行。

tool = ShellTool(callbacks=[HumanApprovalCallbackHandler()])

同意的案例

print(tool.run("ls /usr"))  
Do you approve of the following input? Anything except 'Y'/'Yes' (case-insensitive) will be treated as a no.  
  
ls /usr  
yes  

X11  
X11R6  
bin  
lib  
libexec  
local  
sbin  
share  
standalone

不同意的案例：

print(tool.run("ls /private"))
   
Do you approve of the following input? Anything except 'Y'/'Yes' (case-insensitive) will be treated as a no.

ls /private
no

---------------------------------------------------------------------------

HumanRejectedException                    Traceback (most recent call last)

Cell In[17], line 1
----> 1 print(tool.run("ls /private"))

File ~/langchain/langchain/tools/base.py:257, in BaseTool.run(self, tool_input, verbose, start_color, color, callbacks, **kwargs)
255 # TODO: maybe also pass through run_manager is _run supports kwargs
256 new_arg_supported = signature(self._run).parameters.get("run_manager")
--> 257 run_manager = callback_manager.on_tool_start(
258     {"name": self.name, "description": self.description},
259     tool_input if isinstance(tool_input, str) else str(tool_input),
260     color=start_color,
261     **kwargs,
262 )
263 try:
264     tool_args, tool_kwargs = self._to_args_and_kwargs(parsed_input)

配置人工审批​

假设我们有一个代理，它接受多个工具，我们希望它只在某些工具和某些输入上触发人工审批请求。我们可以配置回调处理器来实现这一点。

from langchain.agents import load_tools  
from langchain.agents import initialize_agent  
from langchain.agents import AgentType  
from langchain.llms import OpenAI

API Reference:​

def _should_check(serialized_obj: dict) -> bool:  
    # Only require approval on ShellTool.  
    return serialized_obj.get("name") == "terminal"  
def _approve(_input: str) -> bool:  
    if _input == "echo 'Hello World'":  
        return True  
    msg = (  
        "Do you approve of the following input? "  
        "Anything except 'Y'/'Yes' (case-insensitive) will be treated as a no."  
    )  
    msg += "\n\n" + _input + "\n"  
    resp = input(msg)  
    return resp.lower() in ("yes", "y")  
callbacks = [HumanApprovalCallbackHandler(should_check=_should_check, approve=_approve)]  

llm = OpenAI(temperature=0)  
tools = load_tools(["wikipedia", "llm-math", "terminal"], llm=llm)  
agent = initialize_agent(  
    tools,  
    llm,  
    agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,  
)  

agent.run(  
    "It's 2023 now. How many years ago did Konrad Adenauer become Chancellor of Germany.",  
    callbacks=callbacks,  
)  
        'Konrad Adenauer became Chancellor of Germany in 1949, 74 years ago.'  
agent.run("print 'Hello World' in the terminal", callbacks=callbacks)  
 'Hello World'  
agent.run("list all directories in /private", callbacks=callbacks)  
 Do you approve of the following input? Anything except 'Y'/'Yes' (case-insensitive) will be treated as a no.  
          
ls /private  
no  

---------------------------------------------------------------------------  

HumanRejectedException                    Traceback (most recent call last)  

Cell In[39], line 1  
----> 1 agent.run("list all directories in /private", callbacks=callbacks)  


File ~/langchain/langchain/chains/base.py:236, in Chain.run(self, callbacks, *args, **kwargs)  
    234     if len(args) != 1:  
    235         raise ValueError("`run` supports only one positional argument.")  
--> 236     return self(args[0], callbacks=callbacks)[self.output_keys[0]]  
    238 if kwargs and not args:  
    239     return self(kwargs, callbacks=callbacks)[self.output_keys[0]]  
HumanRejectedException: Inputs ls /private to tool {'name': 'terminal', 'description': 'Run shell commands on this MacOS machine.'} were rejected.