Build, run, and manage AI pipelines from Python.
Full documentation: docs.rocketride.org/clients/python — guides, the complete API reference, and worked examples.
pip install rocketrideimport 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() are for pipelines whose source is webhook or dropper;
if your pipeline source is chat, use client.chat() instead. Don't have a pipeline
yet? Build one visually with the RocketRide IDE extension.
The SDK is async-first (built on asyncio and websockets), includes the
rocketride CLI, and covers the full
engine surface: pipeline execution, streaming data, chat, deployments with cron
schedules, server-side file storage, and run-log replay.
RocketRide is an open-source, developer-native AI pipeline
platform: build, debug, and deploy production AI workflows without leaving your IDE,
on a visual canvas or code-first. 140+ ready-to-use nodes (15+ LLM providers, 10+
vector stores, OCR, NER, PII anonymization) run on a high-performance C++ engine,
deployable anywhere, MIT licensed. You build your .pipe — and run it against the
fastest AI runtime available.
| Variable | Description |
|---|---|
ROCKETRIDE_URI |
Server URI (e.g. wss://api.rocketride.ai or ws://localhost:5565) |
ROCKETRIDE_APIKEY |
API key for authentication |
All constructor options, timeouts, and reconnection behavior: Configuration.
- Overview & quickstart
- Running pipelines · Sending data · Chat
- Deployments · File storage · Run logs
- Error handling · API reference · Examples
MIT - see LICENSE.