BentoML-0.4.5

• Improved BentoML module import time by around 3-4x
• List deployments command now shows "age" column denoting how long the deployment has been created
• Fixed a bug where serverless deployment failed to install required plugins

Docs:

• Updated documentation site https://bentoml.readthedocs.io/

BentoML-0.4.4

New Features:

• Support for both Keras and tensorflow.keras module in KerasModelArtifact
• New serialization option for KerasModelArtifact that stores model in json and weights files (by @ghunkins )
• bentoml list deployments provides clean table outputs now
• Support for AWS S3 based BentoML repository (Beta)

Bug fixes:

• Fixed error with old click version #335
• Fixed REST API Server issue on Windows platform #333

BentoML-0.4.3

• Enhancement to Serverless deployment and SageMaker deployment
• Updated default version string format for user-defined BentoService
• Added the versioneer interface on BentoService for users to define a customized versioning format
• Added '--force' option to bentoml deployment delete command
• Updated clipper base image to 0.4.1

For BentoML developers:

• BentoML now packages local BentoML dev branch when bundling a BentoService for deployment

BentoML-0.4.2

• Introduced SklearnModelArtifact, adding more scikit-learn specific optimizations over previous general PickleArtifact
• Fixed a number of issues with AWS Lambda Serverless deployment
• Improved error message and CLI outputs of AWS SageMaker deployment

BentoML-0.4.1

• Fixed an issue with initializing BentoML logging and repository file direcotry

BentoML-0.4.0 Beta

• Redesigned deployment component available now, take a look at the deploy command:bentoml deployment --help

• Multiple image support in ImageHandler

• Yatai Service Beta Release - a new component in BentoML providing a model registry and deployment manager for your BentoService. It's a stateful service that can run in your local machine for a personal project, or hosted on a server and shared by a machine learning team.

BentoML-0.3.4

• Add pip_dependencies option to @bentoml.env decorator, and making it the recommended approach for adding PyPI dependencies
• Fixed an issue related OpenAPI doc spec with ImageHandler

BentoML Developer Notes

• DEV: added versioneer.py for version management, now using git tags to manage releases
• DEV: Yatai service protobufs and generated interfaces are in the REPO now

BentoML-0.3.1

This is a minor release with mostly bug fixes:

• Added bentoml config cli command for configuring local BentoML preferences and configs
• Fixed an issue when serving Keras model with API server in docker
• Fixed an issue when dependency missing in docker environment when using ImageHandler

BentoML-0.3.0

• Fast.ai support, find example notebooks here: https://github.com/bentoml/gallery/tree/master/fast-ai

• PyTorch support - fixed a number of issues related to PyTorch model serialization and updated example notebook here: https://github.com/bentoml/BentoML/blob/master/examples/pytorch-fashion-mnist/pytorch-fashion-mnist.ipynb

• Keras Support - fixed a number of issues related to serving Keras model as API server

• Clipper deployment support - easily deploy BentoML service to Clipper cluster, read more about it here: https://github.com/bentoml/BentoML/blob/master/examples/deploy-with-clipper/deploy-iris-classifier-to-clipper.ipynb

• ImageHandler improvements - API server's web UI now support posting images to API server for testing API endpoint:
  

BentoML-0.2.2 Beta

• Fast.ai support is in beta now, check out the example notebook here: https://colab.research.google.com/github/bentoml/gallery/blob/master/fast-ai/pet-classification/notebook.ipynb

• Improved OpenAPI docs endpoint:

• DataframeHandler allows specifying input types now - users can also generate API Client library that respects the expected input format for each BentoML API service user defined, e.g.:

class MyClassifier(BentoService):

    @api(DataframeHandler, input_types=['int8', 'int8', 'float', 'str', 'bool'])
    def predict(self, df):
        ...

    # or specifying both column name & type:
    @api(DataframeHandler, input_types={'id': 'string', 'age': 'int' })
    def predict(self, df):
        ...

• API server index page now provides web UI for testing API endpoints and shows instructions for how to generate Client API library: