Clarifai Release 6.0 marks the official unveiling of our powerful gRPC-based APIs, plus a variety of new features that make it easy to collaborate and innovate when designing AI solutions. Now you can duplicate applications and save your search data with the click of a button, so that you can rapidly develop and iterate on custom models. Also, don't miss out on our new apparel detection model, the perfect starting place for many retail applications.
Take a look at some of the highlights from the 6.0 release:
gRPC Clients for Python, Java and Node
Our new gRPC clients represent the cutting edge in API design for AI. They are designed for optimal performance by using a gRPC channel for the network transfer of data. Plus, since the gRPC clients are auto-generated, they will always have the latest available Clarifai API feature-set.
Cloning an existing application can be a great way to start a new project, or branch and existing one. We’ve made cloning easy with a simple interface in Portal. Just click “Create a copy” in the bottom-right corner of your app on the app management page.
Apparel detection
The ‘Apparel Detection’ model recognizes over 200 fashion-related concepts. Use this model for automatic tagging to quickly identify clothing and accessories to reduce the time to website workflow. This model is great for anyone building a fashion-related app such as an e-commerce platform or a fashion curation site.
Saved Searches
Make the results of your model tests reproducible. With saved searches you can capture your search results at a given point in time, and record the inputs, annotations, search parameters and models that you are running through the platform. Saved searches are extremely helpful when testing out multiple versions of a model, or collaborating with a team. Just save your search, and refer back to it any time. Saved searches are also the basis for task management in upcoming Labeler product.
