Enrich Your Mendix App with GenAI Capabilities
Last modified: February 11, 2025
Introduction
With the Mendix GenAI capabilities, you can create engaging, intelligent experiences with a variety of AI models and your own data.
These pages cover modules that integrate with generative AI tools. For running pre-trained Machine Learning (ML) models using the Mendix Runtime, please see the Machine Learning Kit.
Typical Use Cases
Mendix supports a variety of generative AI tasks by integrating with tools such as Amazon Bedrock or Azure OpenAI. Typical use cases include the following:
- Create conversational UIs for AI-powered chatbots and integrate those UIs into your Mendix applications.
- Connect any model through our GenAI connectors, or by integrating your connector into our GenAI commons interface.
- Connect your data to ground GenAI systems with data from inside your application and the rest of your IT landscape.
Getting Started
To familiarize yourself with the GenAI capabilities of Mendix, explore the sections below based on your experience level:
Familiar with GenAI
If you are already familiar with GenAI and want to start building, refer to How to Build Smarter Apps Using GenAI guide to start building your first GenAI-powered application and access further supportive resources.
New to GenAI
If you are new to GenAI, follow the steps below:
- Familiarize yourself with the concepts such as prompt engineering, Retrieval Augmented Generation (RAG), and function calling (ReAct).
- Select the right architecture to support your use case. For a full list of possibilities, see the Architecture and Components section below.
- Obtain the required credentials for your selected architecture.
Architecture and Components
To help you get started, the following sections list the available GenAI components and models.
Mendix Components
| Asset | Description | Type | Studio Pro Version |
|---|---|---|---|
| AI Bot Starter App | Lets you kick-start the development of enterprise-grade AI chatbot experiences. For example, you can use it to create your own private enterprise-ready ChatGPT-like app. | Starter App | 10.12 |
| Blank GenAI App | Start from scratch to create a new application with GenAI capabilities and without any dependencies. | Starter App | 10.12 |
| GenAI Showcase App | Understand what you can build with generative AI. Understand how to implement the Mendix Cloud GenAI, OpenAI, and Amazon Bedrock connectors and how to integrate them with the Conversational UI module. | Showcase App | 9.24.2 |
| RFP Assistant Starter App / Questionnaire Assistant Starter App | The RFP Assistant Starter App and the Questionnaire Assistant Starter App leverage historical RFPs (or question-answer pairs) and a continuously updated knowledge base to generate and assist in editing responses to RFPs, offering a time-saving alternative to manually finding similar responses and enhancing the knowledge management process. | Starter App | 9.24.2 |
| Support Assistant Starter App | Learn how to combine common GenAI patterns, such as function calling and RAG to build your support assistant. Connect it to a model like Anthropic Claude via Mendix Cloud GenAI or Amazon Bedrock or use an (Azure) OpenAI subscription. | Starter App | 10.12 |
| GenAI For Mendix | GenAI Commons: Common capabilities that allow all GenAI connectors to be integrated with the other modules. You can also implement your own connector based on this. | Common Module | 9.24.2 |
| Conversational UI: Create a Conversational UI for a new or existing app. | UI Module | 9.24.2 | |
| Mendix Cloud GenAI Connector: Connect to Mendix Cloud and utilize Mendix Cloud GenAI resource packs directly within your Mendix application. | Connector Module | 9.24.2 | |
| OpenAI Connector | Connect to (Azure) OpenAI. | Connector Module | 9.24.2 |
| Amazon Bedrock Connector | Connect to Amazon Bedrock. Use Retrieve and Generate or Bedrock agents. | Connector Module | 9.24.2 |
| PgVector Knowledge Base | Manage and interact with a PostgreSQL pgvector Knowledge Base. | Connector Module | 9.24.2 |
| Snowflake Showcase App | Learn how to implement the Cortex functionalities in your app. | Showcase App | 10.12 |
Available Models
Mendix connectors offer direct support for the following models:
| Architecture | Models | Category | Input | Output | Additional capabilities |
|---|---|---|---|---|---|
| Mendix Cloud GenAI | Anthropic Claude 3.5 Sonnet | Chat Completions | text, image, document | text | Function calling |
| Cohere Embed English, Cohere Embed Multilingual | Embeddings | text | embeddings | ||
| Azure / OpenAI | gpt-3.5-turbo | Chat completions | text | text | Function calling |
| gpt-4, gpt-4-turbo, gpt-4o, gpt-4o mini | Chat completions | text, image | text | Function calling | |
| DALL·E 2, DALL·E 3 | Image generation | text | image | ||
| text-embedding-ada-002, text-embedding-3-small, text-embedding-3-large | Embeddings | text | embeddings | ||
| Amazon Bedrock | Amazon Titan Text G1 - Express, Amazon Titan Text G1 - Lite, Amazon Titan Text G1 - Premier | Chat Completions | text, document (except Titan Premier) | text | |
| AI21 Jamba-Instruct | Chat Completions | text | text | ||
| AI21 Labs Jurassic-2 (Text) | Chat Completions | text | text | ||
| Amazon Nova Pro, Amazon Nova Lite | Chat Completion | text, image, document | text | Function calling | |
| Amazon Titan Image Generator G1 | Image generation | text | image | ||
| Amazon Titan Embeddings Text v2 | Embeddings | text | embeddings | ||
| Anthropic Claude 2.0, Anthropic Claude 2.1 | Chat Completions | text, document | text | ||
| Anthropic Claude 3 Sonnet, Anthropic Claude 3.5 Sonnet, Anthropic Claude 3.5 Sonnet v2, Anthropic Claude 3 Haiku, Anthropic Claude 3 Opus | Chat Completions | text, image, document | text | Function calling | |
| Cohere Command | Chat Completions | text, document | text | ||
| Cohere Command Light | Chat Completions | text | text | ||
| Cohere Command R, Cohere Command R+ | Chat Completions | text, document | text | Function calling | |
| Cohere Embed English, Cohere Embed Multilingual | Embeddings | text | embeddings | ||
| Meta Llama 2, MetaLlama 3 | Chat Completions | text, document | text | ||
| Meta Llama 3.1 | Chat Completions | text, document | text | Function calling | |
| Mistral AI Instruct | Chat Completions | text. document | text | ||
| Mistral Large, Mistral Large 2 | Chat Completions | text, document | text | Function calling | |
| Mistral Small | Chat Completions | text | text | Function calling |
For more details on limitations and supported model capabilities for the Bedrock Converse API used in the ChatCompletions operations, see Supported models and model features in the AWS documentation.
The available showcase applications offer implementation inspiration for many of the listed models.
Connecting to Other Models
In addition to the models listed above, you can also connect to other models by implementing one of the following options:
- To connect to other foundation models and implement them in your app, use the Amazon Bedrock connector.
- To connect to Snowflake Cortex LLM functions, configure the Snowflake REST SQL connector for Snowflake Cortex Analyst.
- To implement your connector compatible with the other components, use the GenAI Commons interface.