⚠️ 安全提示 ⚠️
赋予模型执行现实世界操作的自主权存在固有风险。请采取预防措施以降低这些风险：- 确保与工具相关的权限范围狭窄（例如，用于数据库操作或 API 请求）；
- 在需要时，利用Human in the Loop的工作流程。
设置
安装
此工具包位于langchain-community 包中：
pip install -qU langchain-community
os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")
os.environ["LANGSMITH_TRACING"] = "true"
实例化
首先，我们将演示一个最小示例。 注意：赋予模型执行现实世界操作的自主权存在固有风险。我们必须通过设置allow_dangerous_request=True 来“选择启用”这些风险，才能使用这些工具。
这可能对调用不需要的请求造成危险。请确保您的自定义 OpenAPI 规范 (yaml) 是安全的，并且与工具相关的权限范围狭窄。
ALLOW_DANGEROUS_REQUEST = True
from typing import Any, Dict, Union
import requests
import yaml
def _get_schema(response_json: Union[dict, list]) -> dict:
if isinstance(response_json, list):
response_json = response_json[0] if response_json else {}
return {key: type(value).__name__ for key, value in response_json.items()}
def _get_api_spec() -> str:
base_url = "https://jsonplaceholder.typicode.com"
endpoints = [
"/posts",
"/comments",
]
common_query_parameters = [
{
"name": "_limit",
"in": "query",
"required": False,
"schema": {"type": "integer", "example": 2},
"description": "限制结果数量",
}
]
openapi_spec: Dict[str, Any] = {
"openapi": "3.0.0",
"info": {"title": "JSONPlaceholder API", "version": "1.0.0"},
"servers": [{"url": base_url}],
"paths": {},
}
# 遍历端点以构建路径
for endpoint in endpoints:
response = requests.get(base_url + endpoint)
if response.status_code == 200:
schema = _get_schema(response.json())
openapi_spec["paths"][endpoint] = {
"get": {
"summary": f"获取 {endpoint[1:]}",
"parameters": common_query_parameters,
"responses": {
"200": {
"description": "成功响应",
"content": {
"application/json": {
"schema": {"type": "object", "properties": schema}
}
},
}
},
}
}
return yaml.dump(openapi_spec, sort_keys=False)
api_spec = _get_api_spec()
from langchain_community.agent_toolkits.openapi.toolkit import RequestsToolkit
from langchain_community.utilities.requests import TextRequestsWrapper
toolkit = RequestsToolkit(
requests_wrapper=TextRequestsWrapper(headers={}),
allow_dangerous_requests=ALLOW_DANGEROUS_REQUEST,
)
工具
查看可用工具：tools = toolkit.get_tools()
tools
[RequestsGetTool(requests_wrapper=TextRequestsWrapper(headers={}, aiosession=None, auth=None, response_content_type='text', verify=True), allow_dangerous_requests=True),
RequestsPostTool(requests_wrapper=TextRequestsWrapper(headers={}, aiosession=None, auth=None, response_content_type='text', verify=True), allow_dangerous_requests=True),
RequestsPatchTool(requests_wrapper=TextRequestsWrapper(headers={}, aiosession=None, auth=None, response_content_type='text', verify=True), allow_dangerous_requests=True),
RequestsPutTool(requests_wrapper=TextRequestsWrapper(headers={}, aiosession=None, auth=None, response_content_type='text', verify=True), allow_dangerous_requests=True),
RequestsDeleteTool(requests_wrapper=TextRequestsWrapper(headers={}, aiosession=None, auth=None, response_content_type='text', verify=True), allow_dangerous_requests=True)]
在代理中使用
from langchain_openai import ChatOpenAI
from langchain.agents import create_agent
model = ChatOpenAI(model="gpt-5.4-mini")
system_message = """
您可以访问一个 API 来帮助回答用户查询。
以下是 API 文档：
{api_spec}
""".format(api_spec=api_spec)
agent = create_agent(model, tools, system_prompt=system_message)
example_query = "获取前两篇文章。它们的标题是什么？"
events = agent.stream(
{"messages": [("user", example_query)]},
stream_mode="values",
)
for event in events:
event["messages"][-1].pretty_print()
================================ Human Message =================================
获取前两篇文章。它们的标题是什么？
================================== Ai Message ==================================
Tool Calls:
requests_get (call_RV2SOyzCnV5h2sm4WPgG8fND)
Call ID: call_RV2SOyzCnV5h2sm4WPgG8fND
Args:
url: https://jsonplaceholder.typicode.com/posts?_limit=2
================================= Tool Message =================================
Name: requests_get
[
{
"userId": 1,
"id": 1,
"title": "sunt aut facere repellat provident occaecati excepturi optio reprehenderit",
"body": "quia et suscipit\nsuscipit recusandae consequuntur expedita et cum\nreprehenderit molestiae ut ut quas totam\nnostrum rerum est autem sunt rem eveniet architecto"
},
{
"userId": 1,
"id": 2,
"title": "qui est esse",
"body": "est rerum tempore vitae\nsequi sint nihil reprehenderit dolor beatae ea dolores neque\nfugiat blanditiis voluptate porro vel nihil molestiae ut reiciendis\nqui aperiam non debitis possimus qui neque nisi nulla"
}
]
================================== Ai Message ==================================
前两篇文章的标题是：
1. "sunt aut facere repellat provident occaecati excepturi optio reprehenderit"
2. "qui est esse"
API 参考
有关所有 API 工具包功能和配置的详细文档，请前往 RequestsToolkit 的 API 参考。将这些文档 通过 MCP 连接到 Claude、VSCode
等，以获取实时答案。