Overview

Use this template to accelerate the development of a new AI-augmented app. It is preloaded with all the modules you need for a variety of models, such as the Mendix Cloud GenAI Connector, OpenAI connector, Amazon Bedrock connector and Mistral connector.

Ground the application in your own data by linking it to your data sources in a Retrieval-Augmented-Generation setup, or query live data with function calling through the ReAct pattern, it is all possible.

Trace back how the LLM arrived at their generated response (e.g. using tools and knowledge sources) and monitor token consumption.

Contact Us

For support and questions, feel free to reach out via email genai-components-feedback@mendix.com or Community Slack.

Documentation

Configuration

In order to use one (or both) of the platform-supported GenAI connectors, you only need to configure the access to the providers.

• • For Mendix Cloud GenAI resources, the admin can import the keys for GenAI resources obtained in the Mendix Portal. For more information, see Mendix Cloud GenAI Configuration.
  • For OpenAI, the admin can configure the connection to OpenAI at runtime (see navigation). Make sure that the Encryption module is set up correctly. For more information, see OpenAI Configuration.
  • For Amazon Bedrock, there are multiple ways to configure the access which is specific to your use case. See the official documentation to decide what fits best for you, see AWS Authentication. At runtime, the AWS region can be selected (see navigation).
  • For Mistral resources, API keys need to be created here and then be added to the application as described for Mistral Configuration.

Read more

If you plan to create your own Chat-GPT-like app, check out the AI Bot Starter App.

If you seek more Mendix + GenAI examples, the GenAI Showcase apps cover many use cases and patterns to implement GenAI successfully.