Custom Tools

[gnoviawan]

How to create Custom tools using LCToolComponent class ?
the tools is simple post http request to API Endpoint

[dosubot[bot]]

Hey @gnoviawan! I'm here to help you with any bugs, questions, or contributions you have. Let's tackle this together!

To create custom tools using the LCToolComponent class for sending a simple POST HTTP request to an API endpoint, you can utilize the RequestsPostTool class in the LangChain framework. Here's a basic implementation:

from langchain_community.tools.requests.tool import RequestsPostTool
from langchain_community.utilities.requests import TextRequestsWrapper
import json

# Initialize the requests wrapper
requests_wrapper = TextRequestsWrapper(headers={})

# Create an instance of the RequestsPostTool
post_tool = RequestsPostTool(
    requests_wrapper=requests_wrapper,
    allow_dangerous_requests=True  # Ensure this is set to True
)

# Define the input as a JSON string with "url" and "data" keys
input_data = json.dumps({
    "url": "https://api.example.com/endpoint",
    "data": {"key1": "value1", "key2": "value2"}
})

# Use the tool to send a POST request
response = post_tool._run(input_data)

print(response)

Replace "https://api.example.com/endpoint" and the data dictionary with your actual API endpoint and data. The allow_dangerous_requests parameter must be set to True to enable the tool, as it involves making HTTP requests which can be potentially dangerous ^[1].

To continue talking to Dosu, mention @dosu.

[piligrinik]

@dosu, how do you integrate this tool into the LLM?