Skip to main content

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:

  • WhyLabs integration with the WhyLabs Observability Platform for ad-hoc debugging, monitoring, and notification workflows
  • Data pipelines integrations with various data and ml pipelines such as Spark, Ray, Kafka, etc.
  • Model frameworks integrations with frameworks such as scikit-learn, tensorflow, PyTorch, etc.
  • Model lifecycle integrations with model lifecycle tools such as MLflow, Airflow, Flyte, etc.
  • Notification integrations with common team workflows, such as Slack, PagerDuty, ServiceNow, etc.

Our complete list of integrations can be found on the following sections:

WhyLabs

You can monitor your whylogs profiles continuously with the WhyLabs Observability Platform. The platform is built to work with whylogs profiles and it enables observability into data projects and ML models, with easy-to-set-up workflows that can be triggered when anomalies are detected.

IntegrationDescription
Writing profilesSend profiles to your WhyLabs Dashboard
Reference ProfileSend profiles as Reference (Static) Profiles to WhyLabs
Regression MetricsMonitor Regression Model Performance Metrics with whylogs and WhyLabs
Classification MetricsMonitor Classification Model Performance Metrics with whylogs and WhyLabs

For more information on the WhyLabs Observability Platform start here.

Data Pipelines

IntegrationDescription
Apache SparkProfile data in an Apache Spark environment
BigQueryProfile data queried from a Google BigQuery table
DaskProfile data in parallel with Dask
DatabricksLearn how to configure and run whylogs on a Databricks cluster
FugueUse Fugue to unify parallel whylogs profiling tasks
KafkaLearn how to create a Kafka integration to profile streaming data from an existing Kafka topic, or attach a container to a topic to automatically generate profiles.
RayProfile Big Data in parallel with the Ray integration

Storage

IntegrationDescription
s3See how to write your whylogs profiles to AWS S3 object storage
GCSSee how to write your whylogs profiles to the Google Cloud Storage
BigQuerySetup automatic jobs to profile data from BigQuery tables using our no-code templates.

Model lifecycle and deployment

IntegrationDescription
Apache AirflowUse Airflow Operators to create drift reports and run constraint validations on your data
FastAPIMonitor your FastAPI models with WhyLabs
FeastLearn how to log features from your Feature Store with Feast and whylogs
FlaskSee how you can create a Flask app with this whylogs + WhyLabs integration
FlyteLearn how to use whylogs' DatasetProfileView type natively on your Flyte workflows
Github ActionsMonitor your ML datasets as part of your GitOps CI/CD pipeline
MLflowLog your whylogs profiles to an MLflow experiment
SagemakerMonitor your Amazon Sagemaker models with WhyLabs
ZenMLCombine different MLOps tools together with ZenML and whylogs

AI

IntegrationDescription
LangChainUse LangKit to hook into LangChain and monitor your LLM applications
OpenAIUse LangKit to log the prompts and responses from OpenAI's python api

Others

IntegrationDescription
whylogs ContainerA low code solution to profile your data with a Docker container deployed to your environment
JavaProfile data with whylogs with Java

Get in touch

Missing an important integration tool for your tech stack? Contact us at anytime!

Prefooter Illustration Mobile
Run AI With Certainty
Get started for free
Prefooter Illustration