v0.11.0-rc1

• Batching & caching Feast retrieval from standard transformer
• Enable retry for polling get batch job right after create batch job
• User define function(UDF) for standard transformer (geohash, nested json, s2id)
• Support UDF syntax in UI
• Model version labelling and filtering

Release v0.10.1

Improvements:

• Standard transformer optimization
• Retry if create prediction job failed

Release v0.10.0

New features:

• Add Request & Response Logging feature
• Add Standard Transformer (Feast Enrichment) feature

Fixes:

• Fixes the pyspark app's dependencies

Release v0.10.0-rc2

Add Standard Transformer (Feast Enrichment) feature.

Release v0.10.0-rc1

Add Request & Response Logging feature and bug fixes on the pyspark app python dependencies

UI Hotfix & Pagination Support

Support API Pagination On Model Version API (#40)

* Support pagination for model versions API

* Update golang client and python client

* Fix code that use merlin api client

* Fixing type check

* Address PR Review:
1. Generalized pagination implementation
2. Remove unnecessary code

* Support pagination on version list page

* Fix warning on ui

* Reformat generated enum named from swagger

* Fix yarn.lock

* Remove unncessary code

* Add comment to exported method OkWithHeaders

* Support search based on environment name

* Load current state after user deploy or serve model

Merlin release v0.9.1

Bump python sdk version (#43)

Merlin release v0.9.0

Merlin sdk 0.9.0.dev0 (#38)

* Publish merlin-sdk 0.9.0.dev0

Merlin release v0.8.0-alpha

Enable users to deploy a custom transformer for pre/post-processing alongside their models.

Merlin release v0.7.0

This is the first public release of Merlin, a platform for managing, deploying, and serving machine learning models.

Features:

• Deployment of standard models (Tensorflow, XGBoost, SKLearn, PyTorch), user-defined models (PyFunc), and batch prediction job
• Multi-environment deployment
• Traffic routing to the running model version using Istio
• UI for model and batch prediction job management and deployment
• Python SDK library to interacting with Merlin API
• CLI to provides a way to deploy and undeploy Merlin model
• Authentication using Google OAuth and authorization across resources using Keto
• Model logging in the Merlin UI
• ML model performance metrics monitoring with Grafana
• Alerting for a model endpoint using Prometheus
• Resources configuration including the number of minimum and maximum replicas, CPU, and memory