Requests Toolkit
We can use the Requeststoolkit to construct agents that generate HTTP requests.
For detailed documentation of all API toolkit features and configurations head to the API reference forRequestsToolkit.
⚠️ Security note ⚠️
There are inherent risks in giving models discretion to execute real-world actions. Take precautions to mitigate these risks:
- Make sure that permissions associated with the tools are narrowly-scoped (e.g., for database operations or API requests);
- When desired, make use of human-in-the-loop workflows.
Setup
Installation
This toolkit lives in thelangchain-community package:
%pip install-qU langchain-community
To enable automated tracing of individual tools, set yourLangSmith API key:
# os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")
# os.environ["LANGSMITH_TRACING"] = "true"
Instantiation
First we will demonstrate a minimal example.
NOTE: There are inherent risks in giving models discretion to execute real-world actions. We must "opt-in" to these risks by settingallow_dangerous_request=True to use these tools.This can be dangerous for calling unwanted requests. Please make sure your custom OpenAPI spec (yaml) is safe and that permissions associated with the tools are narrowly-scoped.
ALLOW_DANGEROUS_REQUEST=True
We can use theJSONPlaceholder API as a testing ground.
Let's create (a subset of) its API spec:
from typingimport Any, Dict, Union
import requests
import yaml
def_get_schema(response_json: Union[dict,list])->dict:
ifisinstance(response_json,list):
response_json= response_json[0]if response_jsonelse{}
return{key:type(value).__name__for key, valuein 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":"Limit the number of results",
}
]
openapi_spec: Dict[str, Any]={
"openapi":"3.0.0",
"info":{"title":"JSONPlaceholder API","version":"1.0.0"},
"servers":[{"url": base_url}],
"paths":{},
}
# Iterate over the endpoints to construct the paths
for endpointin endpoints:
response= requests.get(base_url+ endpoint)
if response.status_code==200:
schema= _get_schema(response.json())
openapi_spec["paths"][endpoint]={
"get":{
"summary":f"Get{endpoint[1:]}",
"parameters": common_query_parameters,
"responses":{
"200":{
"description":"Successful response",
"content":{
"application/json":{
"schema":{"type":"object","properties": schema}
}
},
}
},
}
}
return yaml.dump(openapi_spec, sort_keys=False)
api_spec= _get_api_spec()
Next we can instantiate the toolkit. We require no authorization or other headers for this API:
from langchain_community.agent_toolkits.openapi.toolkitimport RequestsToolkit
from langchain_community.utilities.requestsimport TextRequestsWrapper
toolkit= RequestsToolkit(
requests_wrapper=TextRequestsWrapper(headers={}),
allow_dangerous_requests=ALLOW_DANGEROUS_REQUEST,
)
API Reference:RequestsToolkit |TextRequestsWrapper
Tools
View available tools:
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)]
Use within an agent
from langchain_openaiimport ChatOpenAI
from langgraph.prebuiltimport create_react_agent
llm= ChatOpenAI(model="gpt-4o-mini")
system_message="""
You have access to an API to help answer user queries.
Here is documentation on the API:
{api_spec}
""".format(api_spec=api_spec)
agent_executor= create_react_agent(llm, tools, prompt=system_message)
API Reference:ChatOpenAI |create_react_agent
example_query="Fetch the top two posts. What are their titles?"
events= agent_executor.stream(
{"messages":[("user", example_query)]},
stream_mode="values",
)
for eventin events:
event["messages"][-1].pretty_print()
================================[1m Human Message [0m=================================
Fetch the top two posts. What are their titles?
==================================[1m Ai Message [0m==================================
Tool Calls:
requests_get (call_RV2SOyzCnV5h2sm4WPgG8fND)
Call ID: call_RV2SOyzCnV5h2sm4WPgG8fND
Args:
url: https://jsonplaceholder.typicode.com/posts?_limit=2
=================================[1m Tool Message [0m=================================
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"
}
]
==================================[1m Ai Message [0m==================================
The titles of the top two posts are:
1. "sunt aut facere repellat provident occaecati excepturi optio reprehenderit"
2. "qui est esse"
API reference
For detailed documentation of all API toolkit features and configurations head to the API reference forRequestsToolkit.
Related
- Toolconceptual guide
- Toolhow-to guides