Skip to main content

Python SDK for Neonloops — run AI workflows via API

Project description

neonloops

Python SDK for Neonloops — run AI workflows via API.

Installation

pip install neonloops

Quick Start

Async (recommended)

import asyncio
from neonloops import Runner, RunInput

runner = Runner(
    api_key="nl_sk_...",
    base_url="https://your-app.vercel.app",
)

async def main():
    result = await runner.run(
        workflow_id="wf_abc123",
        input=[RunInput(role="user", content="Hello, run my workflow!")],
    )
    print(result.output)
    print(result.metadata.tokens)

asyncio.run(main())

Sync

from neonloops import Runner, RunInput

runner = Runner(
    api_key="nl_sk_...",
    base_url="https://your-app.vercel.app",
)

result = runner.run_sync(
    workflow_id="wf_abc123",
    input=[RunInput(role="user", content="Hello!")],
)
print(result.output)

Configuration

Parameter Type Default Description
api_key str Required. Your Neonloops API key (nl_sk_...)
base_url str http://localhost:3000 Base URL of your Neonloops instance
project_id str None Default project ID to scope requests
timeout float 120.0 Request timeout in seconds
max_retries int 2 Max retries for 429/5xx errors

Error Handling

from neonloops import Runner, NeonloopsApiError, NeonloopsTimeoutError

try:
    result = await runner.run(
        workflow_id="wf_abc123",
        input=[RunInput(role="user", content="Hello")],
    )
except NeonloopsApiError as e:
    print(f"API error {e.status}: {e}")
except NeonloopsTimeoutError as e:
    print(f"Timeout: {e}")

License

MIT

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

neonloops-0.1.0.tar.gz (5.6 kB view details)

Uploaded Source

Built Distribution

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

neonloops-0.1.0-py3-none-any.whl (7.3 kB view details)

Uploaded Python 3

File details

Details for the file neonloops-0.1.0.tar.gz.

File metadata

  • Download URL: neonloops-0.1.0.tar.gz
  • Upload date:
  • Size: 5.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.1

File hashes

Hashes for neonloops-0.1.0.tar.gz
Algorithm Hash digest
SHA256 46da357dfe3017a907e346596c3bd2009b021db90358cd4d5c9b7188c2772a54
MD5 ddcb7d2181b833d13be2c61fab6566e4
BLAKE2b-256 54721aec8d45ab20ae033ad84431ca35e24735ca4c6823e5ba9118246e51dbb9

See more details on using hashes here.

File details

Details for the file neonloops-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: neonloops-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 7.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.1

File hashes

Hashes for neonloops-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 6614d61229c7f52bb0957ac147dff7a082428ffb49eda9d103ec0a94e5ed325c
MD5 853c598de3801cf1129aa793fff31604
BLAKE2b-256 216a9101ff0618c55d3678a410b56cdec3fbdd73b254ac59b91a194f0b57eb99

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