人在循环中

有些工具我们不相信模型能够独立执行。在这种情况下，我们可以要求在调用工具之前进行人工批准。

设置

我们需要安装以下软件包：

%pip install --upgrade --quiet langchain

并设置以下环境变量：

import getpass
import os
 
# If you'd like to use LangSmith, uncomment the below:
# os.environ ["LANGCHAIN_TRACING_V2"] = "true"
# os.environ ["LANGCHAIN_API_KEY"] = getpass.getpass()

链

假设我们有以下（虚拟的）工具和工具调用链：

from langchain_anthropic import ChatAnthropic
 
llm = ChatAnthropic(model="claude-3-sonnet-20240229", temperature=0)

from operator import itemgetter
from typing import Dict, List
 
from langchain_core.messages import AIMessage
from langchain_core.runnables import Runnable, RunnablePassthrough
from langchain_core.tools import tool
 
 
@tool
def count_emails(last_n_days: int) -> int:
    """Multiply two integers together."""
    return last_n_days * 2
 
 
@tool
def send_email(message: str, recipient: str) -> str:
    "Add two integers."
    return f"Successfully sent email to {recipient}."
 
 
tools = [count_emails, send_email]
llm_with_tools = llm.bind_tools(tools)
 
 
def call_tools(msg: AIMessage) -> List[Dict]:
    """Simple sequential tool calling helper."""
    tool_map = {tool.name: tool for tool in tools}
    tool_calls = msg.tool_calls.copy()
    for tool_call in tool_calls:
        tool_call["output"] = tool_map[tool_call["name"]].invoke(tool_call["args"])
    return tool_calls
 
 
chain = llm_with_tools | call_tools
chain.invoke("how many emails did i get in the last 5 days?")

[{'name': 'count_emails',
  'args': {'last_n_days': 5},
  'id': 'toolu_012VHuh7vk5dVNct5SgZj3gh',
  'output': 10}]

添加人工批准

我们可以将一个简单的人工批准步骤添加到我们的 tool_chain 函数中：

import json
 
 
def human_approval(msg: AIMessage) -> Runnable:
    tool_strs = "\n\n".join(
        json.dumps(tool_call, indent=2) for tool_call in msg.tool_calls
    )
    input_msg = (
        f"Do you approve of the following tool invocations\n\n{tool_strs}\n\n"
        "Anything except 'Y'/'Yes' (case-insensitive) will be treated as a no."
    )
    resp = input(input_msg)
    if resp.lower() not in ("yes", "y"):
        raise ValueError(f"Tool invocations not approved:\n\n{tool_strs}")
    return msg

chain = llm_with_tools | human_approval | call_tools
chain.invoke("how many emails did i get in the last 5 days?")

Do you approve of the following tool invocations

{
  "name": "count_emails",
  "args": {
    "last_n_days": 5
  },
  "id": "toolu_01LCpjpFxrRspygDscnHYyPm"
}

Anything except 'Y'/'Yes' (case-insensitive) will be treated as a no. yes

[{'name': 'count_emails',
  'args': {'last_n_days': 5},
  'id': 'toolu_01LCpjpFxrRspygDscnHYyPm',
  'output': 10}]

chain.invoke("Send sally@gmail.com an email saying 'What's up homie'")

Do you approve of the following tool invocations

{
  "name": "send_email",
  "args": {
    "message": "What's up homie",
    "recipient": "sally@gmail.com"
  },
  "id": "toolu_0158qJVd1AL32Y1xxYUAtNEy"
}

Anything except 'Y'/'Yes' (case-insensitive) will be treated as a no. no

快速开始（Quickstart）多工具（MultipleTools）