Skip to main content

Use Composio to get an array of tools with your LlamaIndex agent.

Project description

🦙 Using Composio With LlamaIndex

Integrate Composio with llamaindex agents to allow them to interact seamlessly with external apps & data sources, enhancing their functionality and reach.

Goal

  • Star a repository on GitHub using natural language commands through a llamaindex Agent.

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 llamaindex package
pip install composio-llamaindex

# Connect your GitHub account
composio-cli add github

# View available applications you can connect with
composio-cli show-apps

Usage Steps

1. Import Base Packages

Prepare your environment by initializing necessary imports from llamaindex and setting up your agent.

from llama_index.llms.openai import OpenAI
from llama_index.core.llms import ChatMessage
from llama_index.core.agent import FunctionCallingAgentWorker

import dotenv
from llama_index.core.tools import FunctionTool

# Load environment variables from .env
dotenv.load_dotenv()

llm = OpenAI(model="gpt-4-turbo")

2. Fetch GitHub llamaindex Tools via Composio

Access GitHub tools provided by Composio for llamaindex.

from composio_llamaindex import App, Action, ComposioToolSet

# Get All the tools
composio_toolset = ComposioToolSet()
tools = composio_toolset.get_actions(
    actions=[Action.GITHUB_STAR_A_REPOSITORY_FOR_THE_AUTHENTICATED_USER]
)
print(tools)

3. Prepare the Agent

Configure the agent to perform tasks such as starring a repository on GitHub.

prefix_messages = [
    ChatMessage(
        role="system",
        content=(
            "You are now a integration agent, and what  ever you are requested, you will try to execute utilizing your toools."
        ),
    )
]

agent = FunctionCallingAgentWorker(
    tools=tools,
    llm=llm,
    prefix_messages=prefix_messages,
    max_function_calls=10,
    allow_parallel_tool_calls=False,
    verbose=True,
).as_agent()

4. Check Response

Validate the execution and response from the agent to ensure the task was completed successfully.

response = agent.chat("Hello! I would like to star a repo composiohq/composio on GitHub")
print("Response:", response)

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

composio_llamaindex-0.5.42.tar.gz (4.0 kB view details)

Uploaded Source

Built Distribution

composio_llamaindex-0.5.42-py3-none-any.whl (4.4 kB view details)

Uploaded Python 3

File details

Details for the file composio_llamaindex-0.5.42.tar.gz.

File metadata

  • Download URL: composio_llamaindex-0.5.42.tar.gz
  • Upload date:
  • Size: 4.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.7

File hashes

Hashes for composio_llamaindex-0.5.42.tar.gz
Algorithm Hash digest
SHA256 71dc7ee70604e65d714bacfe97cfeb52cb73332a69705ad9628a4b6ffb12e32c
MD5 3c248190a7e4b9b015a23e016e84aef6
BLAKE2b-256 ee70c7778d3c261dafc87dc3a7136d8fe624c0d3d136aa230596ecb60338ffc5

See more details on using hashes here.

File details

Details for the file composio_llamaindex-0.5.42-py3-none-any.whl.

File metadata

File hashes

Hashes for composio_llamaindex-0.5.42-py3-none-any.whl
Algorithm Hash digest
SHA256 2cb4e34e67b21919074115afabf9ab856dcab2676a80c1bea1da1b074480683c
MD5 9de92a8b482b5d83eae0f69a8ba6e6ed
BLAKE2b-256 45e302b583fba0d9e10b3fcd0382259d109a148840ef513eaaef57815d4fcdfa

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page