AI-Infused Apps

What Is an AI-Infused or Smart Mendix App?

An AI-infused or smart Mendix application is an app that uses an Artificial Intelligence (AI)/Machine Learning (ML) model or service, often as a part of its logic. The AI models make use of patterns in the data to make predictions instead of programming the predictions explicitly. This can create a better user experience, automate processes & workflows, and deliver personalized services. Hence, it increases workplace efficiency, reduces costs and risks, and enhances customer satisfaction.

How Does Mendix Support Building Apps with AI/ML Models?

Mendix supports multiple ways of integrating and deploying AI/ML models into a Mendix app in a low-code way. Firstly, Mendix enables integrating any third-party AI services or ML models with Mendix apps using REST APIs in a low-code way. This is a viable approach especially for third-party AI services. Secondly, a Mendix Platform capability, the Mendix ML Kit, allows customers to integrate an ML model—built using a common ML framework and language—into the Mendix Studio Pro runtime in a low-code way. This approach provides various benefits, such as superior performance, privacy, and cost reduction.

The Mendix ML Kit and Java actions combined with the Mendix Platform enable various state-of-the-art ML implementation patterns, such as Ensembles, Cascaded inference, Machine learning model as a service, and Batch inference.

How Can I Integrate AI/ML Models Built In-House to a Mendix App?

The Mendix ML Toolkit allows developers to integrate a ML model—built using a common ML framework and language—into the Mendix Studio Pro runtime in a low-code way. In this way, the ML model will be part of the Mendix app and deployed on the same node.

The ML Kit is based on the Open Neural Network Exchange (ONNX), an open-source framework co-developed to enable framework interoperability. Mendix customers can train a ML model in your favorite ML framework, such as TensorFlow or PyTorch, then convert it into ONNX format and consume it in a different framework like Mendix.

The Mendix ML Kit provides various advantages:

• Faster time-to-market by decreasing the time to ML deployment from weeks to days/hours.
• Easier integration by bridging the two worlds—AI Platforms and LCAPs—and enabling teams to integrate ML models built using third-party AI platforms into apps built with Mendix.
• Superior performance thanks to lower latency (network and model inference latency) by integrating the model into the app runtime and running on JVM.
• Lower effort and cost with no need to acquire, deploy, or maintain other hosting services for the model deployment (vs. microservices integration).

How Can I Integrate AWS AI Services Using Connectors?

AWS has over 250 products, called AWS Services, which you can integrate into your Mendix apps to make them more powerful and intelligent. We are working with AWS and our developer community to provide a rich set of AWS-Mendix connectors and make that integration simple and secure. Read more about our strategy for AWS Connectors in the Mendix Marketplace.

We also want to enable Mendix and AWS developers to use these connectors and build their own if needed. For Mendix developers, we are working on a course about AWS connectors, and for AWS developers, AWS has launched a self-paced AWS Workshop on Mendix.

How Can I Integrate Other Third-Party AI Services and Models into a Mendix App?

Mendix enables integrating any AI services or ML models with Mendix apps using standard REST APIs in a low-code way. For more advanced use cases with specific integration needs, customers can use Java actions to integrate custom third-party AI services.

Does Mendix Provide Free Pre-trained AI/ML Models?

Mendix is the only low-code platform that has native support for ONNX runtime. Thanks to that, customers can pick any ML model from ONNX Model Zoo, customize it with their own data for their use case, and integrate it into their Mendix app using the ML Kit. The ONNX Model Zoo provides a collection of pre-trained, state-of-the-art models in the ONNX format. Below, you can find the list of ONNX models in the ONNX Model Zoo. You can use these pre-trained models to build your business use cases.

Vision

• Image Classification
• Object Detection & Image Segmentation
• Body, Face & Gesture Analysis
• Image Manipulation

Language

• Machine Comprehension
• Machine Translation
• Language Modelling

Other

• Visual Question Answering & Dialog
• Speech & Audio Processing
• Other interesting models

How Does Mendix Facilitate Collaboration between App Development and Data Science Teams?

Thanks to Mendix low-code AI/ML deployment capabilities, Mendix ML Kit and REST APIs, both data science teams and (Mendix) app development teams can seamlessly collaborate to integrate AI/ML models into applications.