composio-togetherai 0.7.6

Use Composio to get an array of tools with your Together AI Function Call.

🚀🔗 Leveraging Together AI with Composio

Facilitate the integration of Together AI with Composio to empower open source models to directly interact with external applications, broadening their capabilities and application scope.

Objective

• Automate starring a GitHub repository using conversational instructions via Together AI Function Calls.

Installation and Setup

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

# Install Composio LangChain package
pip install composio-togetherai

# Connect your GitHub account
composio add github

# View available applications you can connect with
composio apps

### Usage Steps

#### 1. Import Base Packages

Prepare your environment by initializing necessary imports from OpenAI and setting up your client.

```python
from together import Together

# Initialize OpenAI client
client = Together(api_key="<together-ai-api-key>")

Step 2: Integrating GitHub Tools with Composio

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

from composio_togetherai import Action, ComposioToolSet, App


toolset = ComposioToolSet()
actions = toolset.get_tools(apps=[App.GITHUB])

Step 3: Agent Execution

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

my_task = "Star a repo composiohq/composio on GitHub"

# Create a chat completion request to decide on the action
response = client.chat.completions.create(model="gpt-4o",
    tools=actions, # Passing actions we fetched earlier.
    messages=[
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": my_task}
        ]
    )

print(response)

Step 4: Validate Execution Response

Execute the following code to validate the response, ensuring that the intended task has been successfully completed.

result = toolset.handle_tool_calls(response)
pprint(result)