当前位置：首页 > news >正文

小黑黑大模型应用日常摸索中：初次使用langchain智能体调用工具，准备继续深入

news 来源：原创 2025/5/29 12:01:10

定义模型

from langchain.schema import SystemMessage, HumanMessage
from langchain_openai import ChatOpenAI
from langchain_core.output_parsers import JsonOutputParser
from langchain_core.tools import tool
from langchain_core.utils.function_calling import convert_to_openai_tool
from operator import itemgetter
langchain_key = 'lsv2_pt_067c82bxxxxxxxxxxxxxxe_c2934a750d'
import os
os.environ['LANGCHAIN_TRACING_V2'] = 'true'
os.environ['LANGCHAIN_API_KEY'] = langchain_key
os.environ['LANGCHAIN_ENDPOINT'] = 'https://api.smith.langchain.com'
os.environ['LANGCHAIN_PROJECT'] = 'pr-upbeat-electrocardiogram-64'
zhipu_key = 'a66dbxxxxxxxxxxxxxxxxxxxxxxWpHQ9tC83zWJo'
# 创建模型
llm = ChatOpenAI(temperature=0.01,model="glm-4-flash",openai_api_key=zhipu_key,openai_api_base="https://open.bigmodel.cn/api/paas/v4/"
)

通过tool注解定义工具函数

@tool
def multiply(first_int: int, second_int: int) -> int:"""将两个整数相乘。"""print('---------multiply-----------------')return first_int * second_int@tool
def add(first_int: int, second_int: int) -> int:"将两个整数相加。"print('---------add-----------------')return first_int + second_int@tool
def exponentiate(base: int, exponent: int) -> int:"指数运算"print('---------exponentiate-----------------')return base**exponent

绑定工具

tools = [multiply, add, exponentiate]
llm_with_tools = llm.bind_tools(tools)

大模型通过query和绑定的tool进行分析，返回所需要的首个工具（并没有调用工具）

llm_with_tools.invoke('请使用工具计算，4+5*3是多少？')

在这里插入图片描述

通过构建智能体，封装工具和大模型，进行解决问题

from langchain.agents import initialize_agent
from langchain.agents import AgentType, initialize_agent  
agent_chain = initialize_agent(tools, llm, agent=AgentType.STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION, verbose=True)