Release v0.40.1

What's Changed

Other Changes

• fix(ui): Fix negative values shown on the replicas slider when an env is selected during model deployment by @deadlycoconuts in #549

Full Changelog: v0.40.0...v0.40.1

Release v0.40.0

What's Changed

New Features 🎉

• fix(image-builder): Refactor model image naming convention by @deadlycoconuts in #526
• feat: reuse the same bigquery table for multiple model versions for Arize BQ Sink by @khorshuheng in #531
• feat(api): Expose tolerations and node selectors for batch jobs by @deadlycoconuts in #539
• Refactor inference schema by @khorshuheng in #543
• feat: Support HTTP predictor for UPI by @tiopramayudi in #544
• feat(api,ui): Add new max allowed replicas field to env configs and relevant checks by @deadlycoconuts in #546

Other Changes

• fix(api): Change default GPU Request value and prevent null values from being accepted by @deadlycoconuts in #533
• Add documentation for model observability and model schema by @tiopramayudi in #528
• bug: fix json field typo for ranking output by @khorshuheng in #536
• Add MLObs onboarding docs to gitbook by @eric-lidong in #538
• pin mlflow by @leonlnj in #540
• fix: Fix order of pyfunc env vars based on priority by @tiopramayudi in #542
• Revert "fix(image-builder): Refactor model image naming convention (#526) by @deadlycoconuts in #545
• fix: Fix UPI integration test by @tiopramayudi in #548

Full Changelog: v0.39.1...v0.40.0

Release v0.40.0-rc3

What's Changed

Other Changes

• fix: Fix UPI integration test by @tiopramayudi in #548

Full Changelog: v0.40.0-rc2...v0.40.0-rc3

Release v0.40.0-rc2

What's Changed

New Features 🎉

• feat(api,ui): Add new max allowed replicas field to env configs and relevant checks by @deadlycoconuts in #546

Full Changelog: v0.40.0-rc1...v0.40.0-rc2

v0.40.0-rc1

What's Changed

New Features 🎉

• fix(image-builder): Refactor model image naming convention by @deadlycoconuts in #526
• feat: reuse the same bigquery table for multiple model versions for Arize BQ Sink by @khorshuheng in #531
• feat(api): Expose tolerations and node selectors for batch jobs by @deadlycoconuts in #539
• Refactor inference schema by @khorshuheng in #543
• feat: Support HTTP predictor for UPI by @tiopramayudi in #544

Other Changes

• fix(api): Change default GPU Request value and prevent null values from being accepted by @deadlycoconuts in #533
• Add documentation for model observability and model schema by @tiopramayudi in #528
• bug: fix json field typo for ranking output by @khorshuheng in #536
• Add MLObs onboarding docs to gitbook by @eric-lidong in #538
• pin mlflow by @leonlnj in #540
• fix: Fix order of pyfunc env vars based on priority by @tiopramayudi in #542
• Revert "fix(image-builder): Refactor model image naming convention (#526) by @deadlycoconuts in #545

Full Changelog: v0.39.0...v0.40.0-rc1

v0.39.1

What's Changed

New Features 🎉

• feat: reuse the same bigquery table for multiple model versions for Arize BQ Sink by @khorshuheng in #531

Other Changes

• fix(api): Change default GPU Request value and prevent null values from being accepted by @deadlycoconuts in #533
• Add documentation for model observability and model schema by @tiopramayudi in #528
• bug: fix json field typo for ranking output by @khorshuheng in #536
• Add MLObs onboarding docs to gitbook by @eric-lidong in #538
• pin mlflow by @leonlnj in #540
• fix: Fix order of pyfunc env vars based on priority by @tiopramayudi in #542

Full Changelog: v0.39.0...v0.39.1

Release v0.39.1-rc3

What's Changed

New Features 🎉

• feat: reuse the same bigquery table for multiple model versions for Arize BQ Sink by @khorshuheng in #531

Other Changes

• fix(api): Change default GPU Request value and prevent null values from being accepted by @deadlycoconuts in #533
• Add documentation for model observability and model schema by @tiopramayudi in #528
• bug: fix json field typo for ranking output by @khorshuheng in #536
• Add MLObs onboarding docs to gitbook by @eric-lidong in #538
• pin mlflow by @leonlnj in #540
• fix: Fix order of pyfunc env vars based on priority by @tiopramayudi in #542

Full Changelog: v0.39.0...v0.39.1-rc2

v0.39.1-rc2

What's Changed

New Features 🎉

• feat: reuse the same bigquery table for multiple model versions for Arize BQ Sink by @khorshuheng in #531

Other Changes

• fix(api): Change default GPU Request value and prevent null values from being accepted by @deadlycoconuts in #533
• Add documentation for model observability and model schema by @tiopramayudi in #528
• bug: fix json field typo for ranking output by @khorshuheng in #536
• Add MLObs onboarding docs to gitbook by @eric-lidong in #538
• pin mlflow by @leonlnj in #540

Full Changelog: v0.39.0...v0.39.1-rc2

Release v0.39.0

What's Changed

New Features 🎉

• feat: update observation publisher to use newer sdk by @khorshuheng in #509
• feat: Support model observability to pyfunc model by @tiopramayudi in #502
• Add run_pyfunc_model() to build and run pyfunc model locally by @ariefrahmansyah in #514
• feat: Model schemas API and migrate client to OpenAPI 3 by @tiopramayudi in #518
• feat(api): Introduce CPU and memory limit request factors to API server by @deadlycoconuts in #519
• Propagate image building and model deployment errors by @ariefrahmansyah in #524
• feat: Add support for multiple sinks by @khorshuheng in #513

Other Changes

• Miscellaneous Doc updates by @krithika369 in #510
• fix: Set grpc as the container name when raw deployment mode is used by @krithika369 in #511
• Update User and Maintainer Docs by @krithika369 in #512
• Adding back SUMMARY.md file by @eric-lidong in #520
• fix: move git initialization to function body by @khorshuheng in #521
• fix: make sure transformer property on version endpoint is not undefined by @khorshuheng in #523
• fix: Incorrect request body for create and patch version by @tiopramayudi in #522
• fix: Reduce memory usage when publishing prediction log to kafka by @tiopramayudi in #525
• fix(api): Fix failing recovery of deployment attempts interrupted by API server pod termination by @deadlycoconuts in #517
• fix: Retraining model for PyFunc E2E test by @tiopramayudi in #527
• Add troubleshooting deployment errors page by @ariefrahmansyah in #530
• [sdk] Set experiment in model_version run by @leonlnj in #532
• preload pyfunc v2 model to avoid pydantic schema generation error by @khorshuheng in #535
• fix(cicd): Reduce memory footprint of e2e tests by @deadlycoconuts in #534

Full Changelog: v0.38.1...v0.39.0

Release v0.39.0-rc7

What's Changed

New Features 🎉

• feat(api): Introduce CPU and memory limit request factors to API server by @deadlycoconuts in #519
• Propagate image building and model deployment errors by @ariefrahmansyah in #524
• feat: Add support for multiple sinks by @khorshuheng in #513

Other Changes

• fix(api): Fix failing recovery of deployment attempts interrupted by API server pod termination by @deadlycoconuts in #517
• fix: Retraining model for PyFunc E2E test by @tiopramayudi in #527

Full Changelog: v0.39.0-rc6...v0.39.0-rc7