Using Composio With IBM

Composio enables IBM’s Granite Models to connect with many tools!

Goal: Star a repository on GitHub with natural language

Video Guide

Install Packages & Connect a Tool

Ensure you have the necessary packages installed and connect your GitHub account to allow your IBM agents to utilize GitHub functionalities.

Run command

$ pip install composio-langchain
> pip install langchain-ibm
> 
> #  Connect your GitHub so agents can use it. 
> composio add github
> #  Check all different apps which you can connect with
> composio apps

Goal: Prepare your environment by initializing necessary imports from Composio & IBM.

Import Base Packages

Prepare your environment by initializing necessary imports from Composio & IBM.

Default Imports

1 from composio_langchain import ComposioToolSet, Action
2 from langchain_ibm import ChatWatsonx
3 import os
4 
5 os.environ['WATSONX_API_KEY'] = '<ibm_api_key>' #add your ibm api key here
6 if not os.environ.get('WATSONX_API_KEY'):
7     raise ValueError("WATSONX_API_KEY environment variable is not set")

Integrating GitHub Tools with Composio

This step involves fetching and integrating GitHub tools provided by Composio, enabling enhanced functionality for Agent operations.

IBM Supported tools from Composio

1 composio_toolset = ComposioToolSet()
2 tools = composio_toolset.get_tools(
3     actions=[Action.GITHUB_ACTIVITY_STAR_REPO_FOR_AUTHENTICATED_USER]
4 )

IBM Agent Setup

This step involves configuring and executing the agent to carry out actions, such as starring a GitHub repository.

IBM Agent Setup

1 parameters = {
2 "decoding_method": "sample",
3 "max_new_tokens": 100,
4 "min_new_tokens": 1,
5 "temperature": 0.5,
6 "top_k": 50,
7 "top_p": 1,
8 }
9 url = input('Add your IBM Cloud URL here: ')
10 project_id = input('Add your IBM Project ID here: ')
11 watsonx_llm = ChatWatsonx(
12 model_id = 'ibm/granite-3-8b-instruct',
13 url = url, 
14 project_id = project_id,
15 )   
16 
17 if not url or not project_id:
18     raise ValueError("IBM Cloud URL and Project ID must be provided")
19 
20 llm_with_tools = watsonx_llm.bind_tools(tools)

Execute with your prompt/task.

Execute the following code to execute the agent, ensuring that the intended task has been successfully completed.

Agent Execution

1 response = llm_with_tools.invoke("Star the composiohq/composio repository")
2 print(response)

$	pip install composio-langchain
>	pip install langchain-ibm
>
>	# Connect your GitHub so agents can use it.
>	composio add github
>	# Check all different apps which you can connect with
>	composio apps

1	from composio_langchain import ComposioToolSet, Action
2	from langchain_ibm import ChatWatsonx
3	import os
4
5	os.environ['WATSONX_API_KEY'] = '<ibm_api_key>' #add your ibm api key here
6	if not os.environ.get('WATSONX_API_KEY'):
7	raise ValueError("WATSONX_API_KEY environment variable is not set")

1	composio_toolset = ComposioToolSet()
2	tools = composio_toolset.get_tools(
3	actions=[Action.GITHUB_ACTIVITY_STAR_REPO_FOR_AUTHENTICATED_USER]
4	)

1	parameters = {
2	"decoding_method": "sample",
3	"max_new_tokens": 100,
4	"min_new_tokens": 1,
5	"temperature": 0.5,
6	"top_k": 50,
7	"top_p": 1,
8	}
9	url = input('Add your IBM Cloud URL here: ')
10	project_id = input('Add your IBM Project ID here: ')
11	watsonx_llm = ChatWatsonx(
12	model_id = 'ibm/granite-3-8b-instruct',
13	url = url,
14	project_id = project_id,
15	)
16
17	if not url or not project_id:
18	raise ValueError("IBM Cloud URL and Project ID must be provided")
19
20	llm_with_tools = watsonx_llm.bind_tools(tools)

1	response = llm_with_tools.invoke("Star the composiohq/composio repository")
2	print(response)