Skip to main content

Use Composio Tools to enhance your PraisonAI agents capabilities.

Project description

🚀🔗 Leveraging PraisonAI with Composio

Facilitate the integration of PraisonAI with Composio to empower Praison Agents to directly interact with external applications, broadening their capabilities and application scope.

Objective

  • Automate starring a GitHub repository using conversational instructions via PraisonAI Agents.

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-praisonai

# 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 Praison and setting up your client.

import os
import yaml
from praisonai import PraisonAI

Step 2: Write the Praison-supported Composio Tools ins tools.py file.

This step involves fetching and integrating GitHub tools provided by Composio, and writing them in Praison supported Format, returning the name of tools in a format, that should be added to agents.yml file.

from composio_praisonai import Action, ComposioToolSet

composio_toolset = ComposioToolSet()
tools = composio_toolset.get_actions(
    actions=[Action.GITHUB_STAR_A_REPOSITORY_FOR_THE_AUTHENTICATED_USER]
)

tool_section_str = composio_toolset.get_tools_section(tools)
print(tool_section_str)

Step 3: Define the 'agents_yml` either in a separate file, or in your script.

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

agent_yaml = """
framework: "crewai"
topic: "Github Mangement"

roles:
  developer:
    role: "Developer"
    goal: "An expert programmer"
    backstory: "A developer exploring new codebases and have certain tools available to execute different tasks."
    tasks:
      star_github:
        description: "Star a repo composiohq/composio on GitHub"
        expected_output: "Response whether the task was executed."
""" + tool_section_str

print(agent_yaml)

Step 4: Run the Praison Agents to execute the goal/task.

Here you initialize PraisonAI class, and execute.

# Create a PraisonAI instance with the agent_yaml content
praison_ai = PraisonAI(agent_yaml=agent_yaml)

# Run PraisonAI
result = praison_ai.main()

# Print the result
print(result)

Project details


Download files

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

Source Distribution

composio_praisonai-0.5.12.tar.gz (4.5 kB view details)

Uploaded Source

Built Distribution

composio_praisonai-0.5.12-py3-none-any.whl (4.8 kB view details)

Uploaded Python 3

File details

Details for the file composio_praisonai-0.5.12.tar.gz.

File metadata

  • Download URL: composio_praisonai-0.5.12.tar.gz
  • Upload date:
  • Size: 4.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.5

File hashes

Hashes for composio_praisonai-0.5.12.tar.gz
Algorithm Hash digest
SHA256 d00306b8720657d409db8cc0a8df0268ac29cb36eeb939312e54ec691a7b7b64
MD5 fa08c7c9bf6ae612ffa6d2270d70b513
BLAKE2b-256 944cd05920381765a7c170609f85363998f265bd4598934be82b4b94874a0d0b

See more details on using hashes here.

File details

Details for the file composio_praisonai-0.5.12-py3-none-any.whl.

File metadata

File hashes

Hashes for composio_praisonai-0.5.12-py3-none-any.whl
Algorithm Hash digest
SHA256 579a30c4205a01a6618ee96ff5b5e9264202e834c6d1d7685c3e83603e270805
MD5 20e4526f9b915afd046e36d0c328f84d
BLAKE2b-256 cb75984c4e2786bd81d41283151a87b9e2f153c7d904c3086722aa29c9014ed8

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