Pipecat Cloud

Python module and CLI for interacting with Pipecat Cloud.

Requirements

• Python 3.10+
• Docker and a Docker repository (e.g. Docker Hub)
• Active Pipecat Cloud account

Documentation

Documentation for Pipecat Cloud is available here.

Installation

pip install pipecatcloud

pcc --version
pcc --help

# Note: you can use `pcc` or `pipecatcloud` interchangeably
pcc auth login

! All CLI commands have a --help flag that will display the command usage and options.

Usage

1. Create an account at Pipecat Cloud

2. Login to your account pcc auth login

3. (Optional): Clone the starter agent here

4. Build your agent docker build --platform linux/arm64 -t your-agent-name .

5. Push your Docker image to your repository docker push your-repository/your-agent-name:0.1

6. Deploy your agent pcc deploy starter-agent your-repository/your-agent-name:0.1

Usage in Python scripts

If want to programmatically start an agent within a Python script, you can use the pipecatcloud.session module.

from pipecatcloud.session import Session
from pipecatcloud.exception import AgentStartError
import asyncio

async def main():
    session = Session(
        agent_name="your-agent-name",
        api_key="pk_...",
    )

    try:
        await session.start()
    except AgentStartError as e:
        print(e)
    except Exception as e:
        raise (e)

if __name__ == "__main__":
    asyncio.run(main())