在nodeJS 中实现langchain 的Agent （实验笔记）

在nodeJS 中实现langchain 的Agent 实验过程记录如下：

1 构建一个Agent ，使用两个工具 Calculator和TavilySearchResults

2 Tavily Search的API key 的获取

之前一直找不到一个合适的搜索引擎，Google Search 被墙，bing Search 获取API Key 过程麻烦，百度好像还没有这个服务。这一次终于获取了Tavily 免费的research  API Key，过程如下

    访问官网，点击 Get Started，选择Free，再次点击Get Started

 出现了你要的Key

点击Copy 就OK了

Agent 程序

import { initializeAgentExecutorWithOptions } from "langchain/agents";
import { OpenAI } from "@langchain/openai";
import { Calculator } from "@langchain/community/tools/calculator";
import { TavilySearchResults } from "@langchain/community/tools/tavily_search";
process.env['OPENAI_API_KEY']="sk-xxxxxxxxxx";
process.env['OPENAI_BASE_URL']="https://api.chatanywhere.tech/v1"
process.env['TAVILY_API_KEY']="tvly-xxxxxxxxx"
const openai = new OpenAI({apiKey: "sk-xxxxxxxxx",baseURL:"https://api.chatanywhere.tech/v1",model: "gpt-3.5-turbo",temperature: 0
});
const tools = [new TavilySearchResults(),new Calculator(),
];
const executor = await initializeAgentExecutorWithOptions(tools,openai,{ agentType: "chat-zero-shot-react-description", verbose: false });
//Who is Olivia Wilde's boyfriend? What is his current age raised to the 0.23 power?
const input = `无锡当前的天气如何？`;
const result = await executor.invoke({input: input,});
console.log(result.output);

运行结果 

PS E:\yao2024\nodeJS\langchainDemo> node kimiAgent.mjs
The current weather in Wuxi is partly cloudy with a temperature of 21.7°C (71.1°F).

注：同样的程序，kimi 好像有点问题。