GenAI Showcase App

Content Type: Starter App
Categories: Starter Apps,AWS,Artificial Intelligence

Overview

GenAI Showcase App

Showcase application that shows how to use the Mendix Cloud GenAI Connector, OpenAI Connector, Amazon Bedrock Connector, MCP Server, PgVector Knowledge Base, GenAI Commons and Conversational UI which can be used to integrate generative AI - the technology powering ChatGPT - into a Mendix app.

This project contains a variety of example use cases:

  • Multi-agent patterns
  • Exposing tools via MCP
  • Interactive chatbot with history
  • Product description generation
  • Text complexity reduction
  • Text to JSON transformation
  • Demo data creation
  • Postcard (image) generation
  • Embedding vector generation
  • Retrieval Augmented Generation in a chatbot scenario
  • Clustering of unstructured text data
  • Semantic search (books, single-column)
  • Semantic search (tickets, single-column, multi-column and multi-language)
  • Function calling with chat completions
  • Vision with chat completions
  • Document chat
  • RAG with Amazon Bedrock knowledge bases
  • Computer use with Amazon Bedrock

Most examples are supported by the Mendix Cloud GenAI, (Azure) OpenAI and Amazon Bedrock connector.

How to get started

  1. Open the app in Studio Pro
  2. (Amazon Bedrock only): configure the credential constants in Studio Pro (AccessKey and SecretAccessKey from AWS Authentication module)
  3. Run the app & view it
  4. Log in
  5. Configure access to the model providers with API credentials from the Mendix Portal, an OpenAI account*, Azure account or AWS.
  6. Try out the example use cases!

 

You can find technical documentation about the MxGenAI Connector,  OpenAI Connector, Amazon Bedrock Connector, MCP Server, PgVector Knowledge Base, GenAI Commons and Conversational UI on MxDocs.

 

* If you have signed up for an OpenAI account and are using free trial credits, note that these are only valid for three months after the account has been created (not after the API key has been created). For more details, see the OpenAI API reference.

 

Contact Us

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

Documentation

Use this app as an example of what you can do with GenAI in your own project.

 

The majority of the showcase examples in this app follow the principles from the GenAI Commons module. This means that these example use cases are automatically compatible with other GenAI connectors that follow these principles. In this app you can see how you can build vendor-agnostic GenAI use cases that integrate with operations from (for example) the MxGenAI Connector, OpenAI Connector as well as the Amazon Bedrock Connector at the same time.

 

You can find technical documentation about the MxGenAI Connector, OpenAI Connector, Amazon Bedrock Connector, MCP Server, PgVector Knowledge Base, GenAI Commons and Conversational UI on MxDocs.

Releases

Version: 8.4.0
Framework Version: 10.21.0
Release Notes: We have added a new showcase demonstrating computer use with Amazon Bedrock.
Version: 8.3.0
Framework Version: 10.21.0
Release Notes: *We have updated the GenAI marketplace modules to the latest versions. *The “Generate Product Description (Agents)” example was refactored to use Agent Commons instead of Prompt Management (deprecated from the Conversational UI module). The example works the same as before. *We added support for PgVector Knowledge Bases in the Conversational UI chats with advanced settings, so that knowledge bases from the PgVectorKnowledgeBase module can be used in a conversation. The knowledge bases can only be selected if in the configuration an embeddings model was selected and if the knowledge base object was created within the same app environment, for example by inserting chunks into it using one of the RAG examples or by using the PgVectorKnowledgeBase_GetOrCreate microflow.
Version: 8.2.0
Framework Version: 10.21.0
Release Notes: We updated the MCP Server module to the latest version. Additionally, the MCP example now demonstrates how to use an authentication microflow to authorize users via basic auth (username + password) as well as how to expose reusable prompts to Claude Desktop.
Version: 8.1.0
Framework Version: 10.21.0
Release Notes: We have updated the following marketplace modules: *Agent Commons 1.3.0 *Amazon Bedrock Connector 8.1.0 *GenAI Commons 4.1.0 *PgVector Knowledge Base 4.1.0 *Mendix Cloud GenAI Connector 4.1.0
Version: 8.0.0
Framework Version: 10.21.0
Release Notes: - Updated all GenAI marketplace modules to the latest versions and migrated showcases accordingly. - Document chat showcase is no longer specific for Bedrock and now supports all three main providers.
Version: 7.3.0
Framework Version: 10.21.0
Release Notes: We added a new example to demonstrate the value of the MCP Server module and Mendix. In this example, microflows are exposed as tools via the Model Context Protocol and we explain how external applications (such as Claude Desktop) can connect to the MCP Server and thus use the tools.
Version: 7.2.0
Framework Version: 10.21.0
Release Notes: We updated all GenAI marketplace modules to the latest versions.
Version: 7.1.0
Framework Version: 10.21.0
Release Notes: - We have added a multi-LLM showcase example that demonstrates a routing pattern. - Furthermore, example microflows have been added to support the new how-to document about building an agent.
Version: 7.0.0
Framework Version: 10.21.0
Release Notes: App has been updated to Mendix Studio Pro 10.21.0
Version: 6.3.0
Framework Version: 9.24.2
Release Notes: *We have added a new section on the home page for multi-agent patterns. Three examples are currently available: a three-step deterministic flow, a three-step deterministic flow with gatekeeper, and an example displaying the Evaluator-Optimizer pattern. *We added the EchoConnector module which can be a starting point to create your own GenAI connector. The EchoConnector only supports ChatCompletions and returns the same input that the user has given. We added an example microflow for Prompt Management that is used in the new how-to documentation. Lastly, all marketplace modules were updated to the latest version.