Process (inference api)

Edgeflow Inference API

The Gateway supports an Inference API which returns detections from all models in a pipeline.

POST /1/process/{subject_uid}
HOST: http://<gateway ip address or hostname>:8000

The Edgeflow listens for HTTP POST requests on port 8000. The URL must include the input subject_uid of the first application in which inference is to begin. These subjects are configured as output subjects of an HTTP Input application (see the previous section on configuring this application).

Additional arguments can be provided as part of the form-data.
All responses are returned along with the HTTP status response.

Responses

API usage example

import requests
from time import time
import simplejson as json

API_VERSION = 1
EDGEFLOW_IP="10.1.20.100"
URL_PREFIX = 'http://%s:8000/%d/' % (EDGEFLOW_IP, API_VERSION)
TIMEOUT_SECS = 20
SUBJECT_UID = "drone_images_6op"
filename = "testimg.jpg"
files = {'file': open(filename, 'rb')}
data = {"media_timestamp": time(),
        "external_media_id":"abcde-tag", 
        'uploaded_by_user': 'foouser@cogniac.co', 
        'domain_unit': 'test_domain_1',
        'custom_data': json.dumps({'test': "123test", 'tick': time()})}

resp = requests.post(URL_PREFIX + 'process/%s' % SUBJECT_UID, data=data, files=files, timeout=TIMEOUT_SECS)

if resp.status_code == 200:
    detections = resp.json()

curl -X POST -F 'cat.jpg=@path/to/local/file/cat.jpg' \ http:10.1.20.100:8000/1/process/drone_images_6op \
-H "Content-Type: application/json" \
-d '{
    "media_timestamp": 1589833.02
 }'

Below is an example JSON-formatted response for a pipeline composed of box detection and classification apps. The primary key is 'detections,' whose value is a list of all detections for the pipeline associated with an input subject_uid.
Each detection entry contains the application_id reporting the detection, the model used, output subject_id, probability, and specific application data associated with the application. For example, a box detection app will report app_data_type as 'box_set' and a list of boxes in the app_data dictionary.

{u'detections': [{u'app_data': [{u'box': {u'x0': 1474,
                                          u'x1': 1554,
                                          u'y0': 1449,
                                          u'y1': 1487},
                                 u'probability': 0.8900902271270752},
                                {u'box': {u'x0': 705,
                                          u'x1': 781,
                                          u'y0': 988,
                                          u'y1': 1028},
                                 u'probability': 0.8875505924224854},
                                {u'box': {u'x0': 1979,
                                          u'x1': 2038,
                                          u'y0': 2417,
                                          u'y1': 2482},
                                          u'app_data_type': u'box_set',
                  u'app_id': u'z2PNlsAs',
                  u'assertion_prefix': u'spabepadrjic',
                  u'created_at': 1545864284.67,
                  u'detection_id': u'spabepadrjic:0',
                  u'focus': None,
                  u'model_id': u'Hpo-d-8e49-DmDT9hhuJOW_mtsv1_INT_10000.tgz',
                  u'subject_uid': u'vehicles_carbox_3gu',
                  u'uncal_prob': 0.8900902271270752,
                  u'user_id': u'foobar@cogniac.co'},
                 {u'app_data': None,
                  u'app_data_type': None,
                  u'app_id': u'8H88vm4v',
                  u'assertion_prefix': u'spabepadrjic.ankz',
                  u'created_at': 1545864284.67,
                  u'detection_id': u'spabepadrjic.ankz:0',
                  u'focus': {u'box': {u'x0': 3977,
                                      u'x1': 3997,
                                      u'y0': 1670,
                                      u'y1': 1713}},
                  u'inference_focus': {u'box': {u'x0': 3773,
                                                u'x1': 4000,
                                                u'y0': 1578,
                                                u'y1': 1805}},                 
                  u'model_id': u'InitialModel_8H88vm4v_gKS6Vz.tgz',
                  u'subject_uid': u'vehiclestestoutput_6jo',
                  u'uncal_prob': 1.0,
                  u'user_id': u'foobar@cogniac.co'}]}