跳到主要内容
此代理可以向外部 API 发送请求。请谨慎使用,尤其是在授予用户访问权限时。请注意,此代理理论上可能会将提供的凭据或其他敏感数据发送到未经证实或潜在恶意 URL——尽管理论上它不应该这样做。考虑限制可通过代理执行的操作、它可以访问的 API、可以传递的标头等。此外,请考虑实施措施,在发送请求之前验证 URL,并安全地处理和保护凭据等敏感数据。
这将帮助您开始使用 OpenApiToolkit。有关所有 OpenApiToolkit 功能和配置的详细文档,请参阅 API 参考 `OpenAPIToolkit` 可以访问以下工具:
名称描述
requests_get互联网门户。当您需要从网站获取特定内容时使用此工具。输入应为 URL 字符串(例如“www.google.com”)。输出将是 GET 请求的文本响应。
requests_post当您想向网站 POST 数据时使用此工具。输入应为包含两个键的 JSON 字符串:“url”和“data”。“url”的值应为字符串,“data”的值应为键值对字典,您希望将这些键值对作为 JSON 主体 POST 到 URL。请注意在 JSON 字符串中始终使用双引号表示字符串。输出将是 POST 请求的文本响应。
json_explorer可用于回答有关 API 的 OpenAPI 规范的问题。在尝试发出请求之前始终使用此工具。此工具的示例输入:“对 /bar 端点进行 GET 请求所需的查询参数是什么?”“对 /foo 端点进行 POST 请求的请求体中所需的参数是什么?”始终向此工具提出具体问题。

设置

此工具包需要一个 OpenAPI 规范文件。LangChain.js 存储库在 `examples` 目录中有一个 示例 OpenAPI 规范文件。您可以使用此文件测试工具包。 如果您想从单个工具的运行中获取自动跟踪,您还可以通过取消注释以下内容来设置您的 LangSmith API 密钥:
process.env.LANGSMITH_TRACING="true"
process.env.LANGSMITH_API_KEY="your-api-key"

安装

此工具包位于 `langchain` 包中
npm install langchain @langchain/core

实例化

现在我们可以实例化我们的工具包。首先,我们需要定义我们希望在工具包中使用的 LLM。
// @lc-docs-hide-cell

import { ChatOpenAI } from "@langchain/openai";
const llm = new ChatOpenAI({
  model: "gpt-4o-mini",
  temperature: 0,
})
import { OpenApiToolkit } from "@langchain/classic/agents/toolkits"
import * as fs from "fs";
import * as yaml from "js-yaml";
import { JsonSpec, JsonObject } from "@langchain/classic/tools";

// Load & convert the OpenAPI spec from YAML to JSON.
const yamlFile = fs.readFileSync("../../../../../examples/openai_openapi.yaml", "utf8");
const data = yaml.load(yamlFile) as JsonObject;
if (!data) {
  throw new Error("Failed to load OpenAPI spec");
}

// Define headers for the API requests.
const headers = {
  "Content-Type": "application/json",
  Authorization: `Bearer ${process.env.OPENAI_API_KEY}`,
};

const toolkit = new OpenApiToolkit(new JsonSpec(data), llm, headers);

工具

查看可用工具
const tools = toolkit.getTools();

console.log(tools.map((tool) => ({
  name: tool.name,
  description: tool.description,
})))
[
  {
    name: 'requests_get',
    description: 'A portal to the internet. Use this when you need to get specific content from a website.\n' +
      '  Input should be a url string (i.e. "https://www.google.com"). The output will be the text response of the GET request.'
  },
  {
    name: 'requests_post',
    description: 'Use this when you want to POST to a website.\n' +
      '  Input should be a json string with two keys: "url" and "data".\n' +
      '  The value of "url" should be a string, and the value of "data" should be a dictionary of\n' +
      '  key-value pairs you want to POST to the url as a JSON body.\n' +
      '  Be careful to always use double quotes for strings in the json string\n' +
      '  The output will be the text response of the POST request.'
  },
  {
    name: 'json_explorer',
    description: '\n' +
      'Can be used to answer questions about the openapi spec for the API. Always use this tool before trying to make a request. \n' +
      'Example inputs to this tool: \n' +
      "    'What are the required query parameters for a GET request to the /bar endpoint?'\n" +
      "    'What are the required parameters in the request body for a POST request to the /foo endpoint?'\n" +
      'Always give this tool a specific question.'
  }
]

在代理中使用

首先,请确保您已安装 LangGraph
npm install @langchain/langgraph
import { createAgent } from "@langchain/classic"

const agentExecutor = createAgent({ llm, tools });
const exampleQuery = "Make a POST request to openai /chat/completions. The prompt should be 'tell me a joke.'. Ensure you use the model 'gpt-4o-mini'."

const events = await agentExecutor.stream(
  { messages: [["user", exampleQuery]]},
  { streamMode: "values", }
)

for await (const event of events) {
  const lastMsg = event.messages[event.messages.length - 1];
  if (lastMsg.tool_calls?.length) {
    console.dir(lastMsg.tool_calls, { depth: null });
  } else if (lastMsg.content) {
    console.log(lastMsg.content);
  }
}
[
  {
    name: 'requests_post',
    args: {
      input: '{"url":"https://api.openai.com/v1/chat/completions","data":{"model":"gpt-4o-mini","messages":[{"role":"user","content":"tell me a joke."}]}}'
    },
    type: 'tool_call',
    id: 'call_1HqyZrbYgKFwQRfAtsZA2uL5'
  }
]
{
  "id": "chatcmpl-9t36IIuRCs0WGMEy69HUqPcKvOc1w",
  "object": "chat.completion",
  "created": 1722906986,
  "model": "gpt-4o-mini-2024-07-18",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Why don't skeletons fight each other? \n\nThey don't have the guts!"
      },
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 15,
    "total_tokens": 27
  },
  "system_fingerprint": "fp_48196bc67a"
}

Here's a joke for you:

**Why don't skeletons fight each other?**
They don't have the guts!

API 参考

有关所有 OpenApiToolkit 功能和配置的详细文档,请参阅 API 参考
以编程方式连接这些文档到 Claude、VSCode 等,通过 MCP 获取实时答案。
© . This site is unofficial and not affiliated with LangChain, Inc.