Skip to main content

Integrations Overview

Integrations: AI Observatory is the Glue of the MLOps Ecosystem#

AI Observatory is built on the idea that the strength of a monitoring tool is in its ability to bring together information from many sources and to send actionable insights to many workflows. With this idea, there are many types of integrations that are supported:

  • Data pipeline integrations: integrations with various data and ml pipelines such as Spark, Ray, Kafka, etc.
  • Model framework integrations: integrations with frameworks such as scikit-learn, tensorflow, PyTorch, etc.
  • Model lifecycle integrations: integrations with model lifecycle tools such as MLflow, Metaflow, Flyte, etc.
  • Notification workflow integrations: integrations with common team workflows, such as Slack, PagerDuty, etc.
  • Pipeline trigger integrations: integrations with model deployment infrastructure to enable retraining triggers

Data Pipeline Integrations:#

IntegrationFeaturesResources
SparkCapture profiles in an Apache Spark environmenthttps://github.com/whylabs/whylogs-examples/blob/mainline/scala/src/main/scala/WhyLogsDemo.scala
PandasLog and monitor any pandas dataframehttps://github.com/whylabs/whylogs-examples/blob/mainline/python/logging_example.ipynb
KafkaLog and monitor Kafka topicshttps://whylabs.ai/blog/posts/integrating-whylogs-into-your-kafka-ml-pipeline

Model Lifecycle Integrations#

IntegrationFeaturesResources
MLflowEnhance MLflow metrics with WhyLabshttps://github.com/whylabs/whylogs-examples/blob/mainline/python/MLFlow%20Integration%20Example.ipynb
Prefooter Illustration Mobile
Run AI With Certainty
Get started for free
Prefooter Illustration