Skip to main content

Use Composio to get an array of tools with your Lyzr workflow.

Project description

Using Composio With Lyzr

Integrate Composio with Lyzr agents to allow them to interact seamlessly with external apps, enhancing their functionality and reach.

Goal

  • Star a repository on GitHub using natural language commands through a LangChain 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 LangChain package
pip install composio-lyzr

# Connect your GitHub account
composio-cli add github

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

Usage

from  lyzr_automata  import  Task, Agent
from lyzr_automata.ai_models.openai import OpenAIModel
from lyzr_automata.tasks.task_literals import InputType, OutputType
from lyzr_automata.pipelines.linear_sync_pipeline import LinearSyncPipeline

import os
import dotenv
dotenv.load_dotenv()
from composio_lyzr import ComposioToolSet, App, Action

open_ai_text_completion_model = OpenAIModel(
    api_key=os.environ["OPENAI_API_KEY"],
    parameters={
        "model": "gpt-4-turbo-preview",
        "temperature": 0.2,
        "max_tokens": 1500,
    },
)


lyzr_agent = Agent(
        role="Github Agent",
        prompt_persona="You are AI agent that is responsible for taking actions on Github on users behalf. You need to take action on Github using Github APIs"
    )

composio_toolset = ComposioToolSet()
composio_tool = composio_toolset.get_lyzr_tool(Action.GITHUB_STAR_REPO)

task = Task(
        name="Github Starring",
        agent=lyzr_agent,
        tool=composio_tool,
        output_type=OutputType.TEXT,
        input_type=InputType.TEXT,
        model=open_ai_text_completion_model,
        instructions="Star a repo composiohq/composio on GitHub",
        log_output=True,
        enhance_prompt=False,
)

lyzr_output = LinearSyncPipeline(
    name="Composio Lyzr",
		# completion message after pipeline completes
    completion_message="Task completed",
    tasks=[
				# tasks are instance of Task class
        task,
    ],
).run()

print(lyzr_output)

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_lyzr-0.5.48rc1.tar.gz (3.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

composio_lyzr-0.5.48rc1-py3-none-any.whl (3.9 kB view details)

Uploaded Python 3

File details

Details for the file composio_lyzr-0.5.48rc1.tar.gz.

File metadata

  • Download URL: composio_lyzr-0.5.48rc1.tar.gz
  • Upload date:
  • Size: 3.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.7

File hashes

Hashes for composio_lyzr-0.5.48rc1.tar.gz
Algorithm Hash digest
SHA256 e8f5894191a718cb6b2d8a07d4da79a2c0bac4abb90c0359c7867d6462772d33
MD5 bf8e270fa88da3c99881fdd5d1ef2ea6
BLAKE2b-256 3da1046e0366784dcf6f97f6ea23ec34c9d6ba9c09ead7af1ad363432187ebf8

See more details on using hashes here.

File details

Details for the file composio_lyzr-0.5.48rc1-py3-none-any.whl.

File metadata

File hashes

Hashes for composio_lyzr-0.5.48rc1-py3-none-any.whl
Algorithm Hash digest
SHA256 21ec57c1c666eb9093a711e948df26a4d9703597b0f1acf142815813f287f40e
MD5 becb2831506348775b1a81548f0b0a4d
BLAKE2b-256 f69798f1937275b8a0161a85380c795a317a2f54a671158e71e60291b773eaf9

See more details on using hashes here.

Supported by

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