Official Python SDK for HumanRail — route tasks to vetted human workers when AI hits its limits.
Project description
HumanRail Python SDK
Official Python client library for the HumanRail API.
Route tasks to vetted human workers when your AI hits its limits. Verified results. Instant payouts. One API call.
Installation
pip install humanrail
Requires Python 3.12+.
Quick Start
import os
from humanrail import EscalationClient
client = EscalationClient(api_key=os.environ["HUMANRAIL_API_KEY"])
task = client.tasks.create(
idempotency_key="order-12345-refund",
task_type="refund_eligibility",
risk_tier="medium",
sla_seconds=300,
payload={
"orderId": "order-12345",
"reason": "Item arrived damaged",
},
output_schema={
"type": "object",
"required": ["eligible", "reason_code"],
"properties": {
"eligible": {"type": "boolean"},
"reason_code": {"type": "string", "enum": ["approved", "denied_policy", "needs_review"]},
},
},
payout={"currency": "USD", "max_amount": 0.50},
)
result = client.tasks.wait_for_completion(task.id, timeout=600)
print(result.output)
# {"eligible": True, "reason_code": "approved"}
Async Usage
from humanrail import AsyncEscalationClient
async_client = AsyncEscalationClient(api_key=os.environ["HUMANRAIL_API_KEY"])
task = await async_client.tasks.acreate(...)
result = await async_client.tasks.await_for_completion(task.id)
Features
- Synchronous and async clients
- Automatic retries with exponential backoff
- Webhook signature verification (HMAC-SHA256)
- Idempotency support
- Typed responses with Pydantic models
- OpenTelemetry tracing
Documentation
License
MIT - see LICENSE
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
humanrail-0.1.0.tar.gz
(14.0 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
humanrail-0.1.0-py3-none-any.whl
(14.6 kB
view details)
File details
Details for the file humanrail-0.1.0.tar.gz.
File metadata
- Download URL: humanrail-0.1.0.tar.gz
- Upload date:
- Size: 14.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
99f08fe7fb579339f6b53214f01ce1ad3d050aadf1d8d6e737fa7429cd519fe9
|
|
| MD5 |
bea17941ccbb2c711c062dae4f5e94f2
|
|
| BLAKE2b-256 |
b34699fa40300a1e91e301543d5acd8b64a783a6936a76e9ea44afaad88daf2d
|
File details
Details for the file humanrail-0.1.0-py3-none-any.whl.
File metadata
- Download URL: humanrail-0.1.0-py3-none-any.whl
- Upload date:
- Size: 14.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
15a969744554181f36bc8d1a855c224cb2952b43d62205cb6e863177bd67c8a2
|
|
| MD5 |
80614443a5d4ea1f13d1930af574aec9
|
|
| BLAKE2b-256 |
85924a193ddf9953e2af1a2bc832e179812942a279bed0085e247ae7347ef9d7
|