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, Mistral Connector, MCP Server, MCP Client, 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 and consuming 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, Amazon Bedrock and Mistral 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. Set the EncryptionKey constant
  4. Run the app & view it
  5. Log in
  6. Configure access to the model providers with API credentials from the Mendix Portal, an OpenAI account*, Azure account, AWS or Mistral.
  7. Try out the example use cases!

 

You can find technical documentation about all single components 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, the Amazon Bedrock Connector as well as the Mistral Connector at the same time.

You can find technical documentation about all connectors to GenAI providers, MCP Server, MCP Client, PgVector Knowledge Base, GenAI Commons and Conversational UI on MxDocs.

 

Releases

Version: 9.5.0
Framework Version: 10.24.0
Release Notes:

- Support of Mistral deployed models has been added and examples which are supported by Mistral are now labelled as such. The Clustering example now processes generation of many embedding vectors with Mistral in batches.

- React Client is now enabled per default.

Version: 9.4.0
Framework Version: 10.24.0
Release Notes:

- GenAI modules have been upgraded to their latest versions.

- Encryption has been upgraded.

Version: 9.3.0
Framework Version: 10.24.0
Release Notes: Modules have been upgraded to their latest versions: - MCPClient 2.1.0 - Mendix Cloud GenAI Connector 5.2.0 - AgentCommons 2.2.0 - GenAICommons 5.3.0 - Conversational UI 5.1.0
Version: 9.2.0
Framework Version: 10.24.0
Release Notes: We added new example implementations of multi-agent patterns, highlighting capabilities from the Agent Commons module. The MCP Client showcase was refactored for compatibility with the latest MCP Client module (v2.0.0). Additionally the following modules were updated: - Administration 4.3.2 - Agent Commons 2.1.0 - Amazon Bedrock Connector 9.2.0 - Amazon S3 Connector 5.0.0 - AWS Authentication 4.1.1 - Community Commons 11.3.0 - Database Connector 7.0.1 - Data Widgets 3.3.0 - Encryption 11.0.2 - GenAI Commons 5.2.0 - MCP Client 2.0.0 (NEW) - OpenAI Connector 7.2.0
Version: 9.1.0
Framework Version: 10.24.0
Release Notes: * A new showcase example was added to demonstrate the MCP Client capabilities. You can connect to external MCP servers, discover prompts and tools and finally use them in a chat interface powered by GenAI Commons and Conversational UI. If you don't have access to an external MCP server, you can also just make use of the MCP Server showcase example within the same app and connect locally. * In the MCP Server example, we now describe how to connect from a Mendix app and from VS Code with Github Copilot (as alternatives to Claude Desktop).
Version: 9.0.0
Framework Version: 10.24.0
Release Notes: App has been upgraded to Mendix Studio Pro version 10.24
Version: 8.5.0
Framework Version: 10.21.0
Release Notes: * We updated all GenAI modules to the latest version. * We redesigned the landing (home) page and navigation of the app to make it even easier to get started with GenAI in Mendix. * The function calling example now demonstrate how to use more advanced and multiple input parameters for tool microflows (such as DateTime, Enumeration etc.). * We removed the AfterStartup microflow which checked for an Encryption key and sync all Amazon Bedrock resources. The encryption key is now validated in individual connectors if needed. * For the MCP Server example more complex tool microflows were added demonstrating how to use multiple input parameters of various types.
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.