Takes a request, makes a request
Go to file
2022-01-31 23:05:34 +01:00
k8s initial commit 2021-11-23 00:19:29 +01:00
svm_prefilter_service Fixed model not downloading 2021-12-18 03:58:28 +01:00
.dockerignore initial commit 2021-11-23 00:19:29 +01:00
.drone.yml upload to docker hub 2022-01-31 23:01:36 +01:00
.gitignore initial commit 2021-11-23 00:19:29 +01:00
Dockerfile use public base image 2022-01-31 23:01:13 +01:00
README.md Added readme 2022-01-31 23:05:34 +01:00
requirements-dev.txt initial commit 2021-11-23 00:19:29 +01:00
requirements.txt Added reporter 2021-12-03 00:31:30 +01:00
uwsgi.ini Finally fixed 2021-11-23 21:33:06 +01:00

SVM Prefilter Service

The purpose of this service is to bring the SVM Ai from the Birbox to the Edge.

This service has the same interface as the input service. Upon receiving a request it enqueues it, runst the Ai prediction, if a bird chirp sound is predicted then this service forwards the request to the original input service in the cloud.

This service needs to communicate with the input service and the model service. And optionally it can report its queue length to birb-latency-collector.

Configuration:

This service can be configured trough envvars:

  • SECRET_KEY: Flask secret key. See https://flask.palletsprojects.com/en/2.0.x/config/#SECRET_KEY
  • SENTRY_DSN: Sentry DSN. See https://docs.sentry.io/product/sentry-basics/dsn-explainer/
  • RELEASE_ID: Release ID for Sentry.
  • RELEASEMODE: Release mode for sentry.
  • MODEL_INFO_URL: URL of the model service endpoint when the information about the used SVM model can be fetched (e.g.: https://birb.k8s.kmlabz.com/model/svm/$default)
  • INPUT_SERVICE_URL: URL of the real input service (e.g.: https://birb.k8s.kmlabz.com/input)
  • REPORT_URL: URL of the birb-latency-collector service to report queue length to (e.g.: http://192.168.110.100:30420/report/site)
  • REPORT_INTERVAL: Seconds between reporting queue length to birb-latency-collector.