Single-image object detection; classification, segmentation and video need separate adapters.
Run it in your own environment
Create a Python environment, install inference-sdk, and record its exact installed version. Set ROBOFLOW_API_KEY, ROBOFLOW_MODEL_ID (project/version), and IMAGE_PATH in your local environment. Save the code as roboflow_smoke.py and run python roboflow_smoke.py. The SDK call has no explicit total deadline in this starter: use a supervised process timeout for the pilot.
Keep credentials in your local or server-side credential provider. Running this sample sends an image to provider cloud and may consume account usage.
View runnable Python starter · roboflow_smoke.py
"""Smart Tools starter: one Roboflow object-detection image. Not production-certified."""
import json
import math
import os
import sys
from datetime import datetime, timezone
from importlib.metadata import version
from pathlib import Path
from time import monotonic
def normalize(raw):
if not isinstance(raw, dict) or not isinstance(raw.get('predictions'), list):
raise ValueError('unexpected_schema')
items = []
for item in raw['predictions']:
if not isinstance(item, dict) or not isinstance(item.get('class'), str):
raise ValueError('unexpected_schema')
score = item.get('confidence')
if type(score) not in (int, float) or not math.isfinite(score) or not 0 <= score <= 1:
raise ValueError('unexpected_schema')
box = {key: item.get(key) for key in ('x', 'y', 'width', 'height')}
if any(type(n) not in (int, float) or not math.isfinite(n) for n in box.values()):
raise ValueError('unexpected_schema')
if box['width'] < 0 or box['height'] < 0:
raise ValueError('unexpected_schema')
items.append({'label': item['class'], 'score': score, 'box_center_pixels': box})
return items
def run():
start = monotonic()
result = {'schema_version': '1.0.0', 'provider': 'Roboflow', 'status': 'error',
'model_version': None, 'data': None, 'error': None,
'captured_at': datetime.now(timezone.utc).isoformat()}
try:
key, model = os.environ['ROBOFLOW_API_KEY'], os.environ['ROBOFLOW_MODEL_ID']
filename = Path(os.environ['IMAGE_PATH'])
if not key or '/' not in model or not filename.is_file():
raise ValueError('configuration')
from inference_sdk import InferenceHTTPClient, InferenceConfiguration
result['sdk_version'] = version('inference-sdk')
result['model_version'] = model
# Hosted endpoint only; image leaves this machine. Header auth needs server >=1.5.
client = InferenceHTTPClient(api_url='https://serverless.roboflow.com', api_key=key)
client.configure(InferenceConfiguration(api_key_transport='header'))
result['data'] = normalize(client.infer(str(filename), model_id=model))
result['status'] = 'ok'
except (KeyError, FileNotFoundError):
result['error'] = 'configuration'
except ValueError:
result['error'] = 'configuration_or_schema'
except ImportError:
result['error'] = 'dependency_missing'
except Exception:
# Provider exceptions may contain request URLs or credentials: never echo them.
result['error'] = 'provider_or_transport_failure'
result['elapsed_ms'] = round((monotonic() - start) * 1000)
return result
if __name__ == '__main__':
output = run()
print(json.dumps(output, ensure_ascii=False, allow_nan=False))
sys.exit(0 if output['status'] == 'ok' else 1)