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 MxGenAI Connector, OpenAI Connector, Amazon Bedrock Connector, 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:

  • 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

Most examples are supported by the MxGenAI, 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, 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, PgVector Knowledge Base, GenAI Commons and Conversational UI on MxDocs.

Releases

Version: 6.2.1
Framework Version: 9.24.2
Release Notes: *We added Generate Product Description (Prompt Management) as a new example that demonstrates how the prompt management capabilities of the ConversationalUI module can be implemented into your app. *We added a warning and validations for the knowledge base examples when MxCloud is used as architecture to inform the user about the 60-120 seconds asynchronous data synchronization after changing chunks in the knowledge base. *We fixed a bug which prevented users from selecting an embeddings model for the “RAG on Large Text” example when using “Other” as knowledge base architecture. *We fixed a bug in the RAG Amazon Bedrock Knowledge Bases example to only show knowledge bases of the currently selected region. *We updated all GenAI marketplace modules to the latest versions (that were not part of the 6.2.0 release).
Version: 6.1.0
Framework Version: 9.24.2
Release Notes: All GenAI components have been updated to the latest version. In GenAICommons, function microflows now accept “Tool” and/or “Request” as optional inputs, and there’s a new specialization called “KnowledgeBaseRetrieval” for better integration with knowledge base tools. In MxGenAIConnector, we’ve removed the “retrieve” and “generate” actions and introduced a new action: “Tools: Add Mendix Cloud Knowledge Base” for efficient knowledge base retrieval in chat completions. A new ExampleMicroflows module has been created. It includes the finished example microflows that are developed in the How-to documents on GenAI capabilities of Mendix​.
Version: 6.0.0
Framework Version: 9.24.2
Release Notes: The genai components were updated to the latest version. The showcase app is compatible with the new Deployed Model selection and demonstrates the compatibility of all connectors that are based on GenAI Commons. The MxGenaiConnector was added as provider next to OpenAI and Amazon Bedrock.
Version: 5.2.0
Framework Version: 9.24.2
Release Notes: We made small changes to improve the overall developer experience. This includes pre-filling of configuration dropdowns used in the examples, restructuring of pages, and enhanced prompt engineering. Lastly, we have updated the marketplace modules to the following versions: Amazon Bedrock Connector (5.3.0) AWS Authentication Module (3.2.0) Community Commons (10.0.7) ConversationalUI (1.5.1) GenAI Commons (1.5.0) OpenAI Connector (3.4.1) PgVector Knowledge Base (2.2.0)
Version: 5.1.0
Framework Version: 9.24.2
Release Notes: A page has been added for usage monitoring. You can now see how to use the page, snippets and logic from the Conversational UI module to get insights into how much tokens were used up during successful GenAI operations in the specified time period. Currently, the token monitor is only supported by the OpenAI Connector.
Version: 5.0.0
Framework Version: 9.24.2
Release Notes: The OpenAI Showcase App has been renamed to GenAI Showcase App.
Version: 3.3.0
Framework Version: 9.24.2
Release Notes: We added two Amazon Bedrock-specific examples. The first “RAG with Amazon Bedrock Knowledge Bases” shows how to setup a knowledge base in Amazon Bedrock and interact with it via a Mendix app. In the second example “Document Chat”, users can upload up to five documents and chat about them using the interface from Conversational UI. Lastly, we have updated the GenAI-related marketplace modules to the following versions: - AWS Authentication Connector 3.1.2 - AWS Bedrock Connector 5.2.0 - Conversational UI 1.3.0 - GenAI Commons 1.2.0 - OpenAI Connector 3.2.0 - PgVector Knowledge base 2.1.0
Version: 3.2.0
Framework Version: 9.24.2
Release Notes: We improved the UX in the Vision and Function Calling examples and updated the Amazon Bedrock Connector, OpenAI Connector and Conversational UI to the latest version.
Version: 3.1.0
Framework Version: 9.24.2
Release Notes: We have updated the genAI-related marketplace modules to the following versions - GenAI Commons 1.1.0 - OpenAI Connector 3.1.0 - AWS Authentication Connector 3.1.1 - AWS Bedrock Connector 4.0.0 - Conversational UI 1.2.0 - PgVector Knowledge base 2.0.0 The embeddings and image generation showcases are now compatible with GenAI Commons. As a result both OpenAI and AWS Bedrock models can be selected for the model interactions.
Version: 3.0.0
Framework Version: 9.24.2
Release Notes: - The OpenAI Connector has been updated to version 3.0.0 so that all chat showcase examples are based on the GenAI Commons module. - The Amazon Bedrock Connector has been imported and all chat completion examples can now be used with Anthropic Claude and Amazon Titan models. - All chat examples are now based on the Conversational UI module. - We have improved the UX of the homepage and some existing examples.