并行工具使用

在带有多个工具的链指南中，我们看到了如何构建在多个工具之间进行选择的函数调用链。一些模型，比如 2023 年秋季发布的 OpenAI 模型，还支持并行函数调用，这允许你在单个模型调用中调用多个函数（或多次调用同一个函数）。我们在多工具指南中的先前链实际上已经支持了这一点。

设置

我们需要为本指南安装以下软件包：

%pip install --upgrade --quiet langchain-core

如果你想在 LangSmith 中追踪你的运行，请取消注释并设置以下环境变量：

import getpass
import os
 
# os.environ ["LANGCHAIN_TRACING_V2"] = "true"
# os.environ ["LANGCHAIN_API_KEY"] = getpass.getpass()

工具

from langchain_core.tools import tool
 
 
@tool
def multiply(first_int: int, second_int: int) -> int:
    """Multiply two integers together."""
    return first_int * second_int
 
 
@tool
def add(first_int: int, second_int: int) -> int:
    "Add two integers."
    return first_int + second_int
 
 
@tool
def exponentiate(base: int, exponent: int) -> int:
    "Exponentiate the base to the exponent power."
    return base**exponent

链

from langchain_openai import ChatOpenAI
 
llm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)

from operator import itemgetter
from typing import Dict, List, Union
 
from langchain_core.messages import AIMessage
from langchain_core.runnables import (
    Runnable,
    RunnableLambda,
    RunnableMap,
    RunnablePassthrough,
)
 
tools = [multiply, exponentiate, add]
llm_with_tools = llm.bind_tools(tools)
tool_map = {tool.name: tool for tool in tools}
 
 
def call_tools(msg: AIMessage) -> Runnable:
    """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(
    "What's 23 times 7, and what's five times 18 and add a million plus a billion and cube thirty-seven"
)

[{'name': 'multiply',
  'args': {'first_int': 23, 'second_int': 7},
  'id': 'call_22tgOrsVLyLMsl2RLbUhtycw',
  'output': 161},
 {'name': 'multiply',
  'args': {'first_int': 5, 'second_int': 18},
  'id': 'call_EbKHEG3TjqBhEwb7aoxUtgzf',
  'output': 90},
 {'name': 'add',
  'args': {'first_int': 1000000, 'second_int': 1000000000},
  'id': 'call_LUhu2IT3vINxlTc5fCVY6Nhi',
  'output': 1001000000},
 {'name': 'exponentiate',
  'args': {'base': 37, 'exponent': 3},
  'id': 'call_bnCZIXelOKkmcyd4uGXId9Ct',
  'output': 50653}]

多工具（MultipleTools）代理（Agents）