Skip to main content

Python SDK

View as Markdown

Python SDK

Build, run, and manage AI pipelines from Python. The rocketride package is async-first — built on asyncio and websockets — and speaks the engine's native WebSocket protocol: you author a .pipe (visually or by hand) and run it against the engine from your own application.

Install​

pip install rocketride

Python 3.10+. The rocketride CLI is installed with the package.

Quickstart​

import asyncio
from rocketride import RocketRideClient


async def main():
    async with RocketRideClient(uri='https://api.rocketride.ai', auth='my-key') as client:
        result = await client.use(filepath='pipeline.pipe')
        token = result['token']
        out = await client.send(token, 'Hello, pipeline!', objinfo={'name': 'input.txt'}, mimetype='text/plain')
        print(out)
        await client.terminate(token)


asyncio.run(main())

send() / send_files() target pipelines whose source is webhook or dropper; if your pipeline source is chat, use client.chat(). No pipeline yet? The IDE walkthrough builds one in minutes.

Explore the SDK​

ConfigurationConstructor options, environment variables, timeouts, and reconnection.ConnectionThe attach/login layers, context manager, persist mode, and lifecycle callbacks.Running PipelinesStart with use(), watch progress, validate, and terminate.DeploymentsPublish immutable versions, point team environments at them, and schedule runs.Sending DataOne-shot sends, concurrent file uploads with progress, and chunked streaming.File StorageRead, write, and manage your server-side store; signed URLs for direct access.ChatBuild a Question, stream the response, parse it with Answer.Run LogsThe log continuum and the DVR session: live monitoring and replay with one API.Error HandlingWhat the SDK raises, when, and how to catch it.API ReferenceEvery public class and method, in one place.ExamplesSeven complete programs, from hello-pipeline to custom DAP requests.AnalyticsReport client-side analytics events through the SDK.
Last updated on