diff --git a/content/en/docs/control-center/entitlements/cloud-tokens.md b/content/en/docs/control-center/entitlements/cloud-tokens.md index d7194d2bd61..1203fa207b5 100644 --- a/content/en/docs/control-center/entitlements/cloud-tokens.md +++ b/content/en/docs/control-center/entitlements/cloud-tokens.md @@ -98,19 +98,7 @@ These tables show how many Mendix Cloud Tokens each CRP requires: ## GenAI Resource Packs {#grps} -GenAI Resource Packs provide turn-key access to Generative AI technology, delivered through Mendix Cloud. For the technical details of each GenAI Resource Pack (GRP), refer to [GenAI Resource Packs](/agents/mx-cloud-genai/resource-packs/). - -| GenAI Model Resource Pack – Anthropic Claude Sonnet | Mendix Cloud Tokens | -| --- | --: | -| S | 30 | -| M | 60 | -| L | 120 | - -| GenAI Model Resource Pack – Cohere Embed | Mendix Cloud Tokens | -| --- | --: | -| S | 6 | -| M | 12 | -| L | 24 | +GenAI Resource Packs provide turn-key access to Generative AI technology, delivered through Mendix Cloud. For text generation and embeddings resources, 1 Mendix Cloud Token equals 100 GenAI Units. You choose any Cloud Token amount when provisioning a resource. There are no fixed plan sizes. For technical details, GenAI Unit exchange rates, and model pricing, see [Mendix Cloud GenAI Resource Packs](/agents/mx-cloud-genai/resource-packs/). | GenAI Knowledge Base Resource Packs | Mendix Cloud Tokens | | --- | --: | diff --git a/content/en/docs/control-center/genai-resources-self-service.md b/content/en/docs/control-center/genai-resources-self-service.md index 7be62785aef..5476d2962da 100644 --- a/content/en/docs/control-center/genai-resources-self-service.md +++ b/content/en/docs/control-center/genai-resources-self-service.md @@ -7,16 +7,16 @@ weight: 20 ## Introduction -The **GenAI Resources** section provides a detailed overview of all Mendix GenAI resources available within your company, allowing Mendix Admins to seamlessly provision and deprovision GenAI resources as needed. With this feature, Mendix Admins can efficiently manage all GenAI resources directly within the [Control Center](https://controlcenter.mendix.com/index.html) through a self-service capability, ensuring streamlined operations and improved governance. For more information, refer to [Accessing GenAI Resources](/agents/mx-cloud-genai/resource-packs/#accessing-genai-resources). +The **GenAI Resources** section provides a detailed overview of all Mendix GenAI resources available within your company, allowing Company Admins to seamlessly provision and deprovision GenAI resources as needed. With this feature, Company Admins can efficiently manage all GenAI resources directly within the [Control Center](https://controlcenter.mendix.com/index.html) through a self-service capability, ensuring streamlined operations and improved governance. For more information, see [Accessing GenAI Resources](/agents/mx-cloud-genai/resource-packs/#accessing-genai-resources). ## Prerequisites -Self-service provisioning of GenAI resources using Mendix Cloud Tokens is available only if the users meet the following conditions: +Self-service provisioning of GenAI resources using Mendix Cloud Tokens is available only if you meet the following conditions: -1. Sufficient token entitlements – The user should have an adequate number of available Mendix Cloud Tokens to allocate for GenAI resource provisioning. -2. Valid subscription plan – The user's Mendix subscription must be based on the FY21 price list or newer. Older subscription plans are not eligible for provisioning. -3. Single account ownership – The user should have a single account. Owning multiple accounts is not supported for self-service GenAI provisioning. -4. Enterprise platform subscription – The user should have a single active enterprise platform subscription. If no active subscription is found, the system will display a warning message with this text: "We couldn't retrieve your correct platform account, which is required to access available tokens and create resources. Please contact Mendix Support for assistance." +1. Sufficient token entitlements – You must have an adequate number of available Mendix Cloud Tokens to allocate for GenAI resource provisioning. +2. Valid subscription plan – Your Mendix subscription must be based on the FY21 price list or newer. Older subscription plans are not eligible for provisioning. +3. Single account ownership – You must have a single account. Owning multiple accounts is not supported for self-service GenAI provisioning. +4. Enterprise platform subscription – You must have a single active enterprise platform subscription. If no active subscription is found, the system displays the following warning: "We couldn't retrieve your correct platform account, which is required to access available tokens and create resources. Please contact Mendix Support for assistance." ## Overview of Deployed Resources @@ -24,16 +24,15 @@ The overview page provides a centralized view of all deployed GenAI resources, i * **Status** – The current status of the resource. * **Name** – The name of the resource. -* **Model** – The model that is used, for example, Anthropic Claude Sonnet 4.0. -* **Plan** – The subscription plan used for resources, for example, small, medium, or large. +* **Available Models** – The model versions available on the resource, grouped by family, for example, Claude Sonnet 4.5, 4.6. +* **GenAI Units** – The monthly GenAI Unit allocation for the resource. * **Created For** – For whom it is created. -{{< figure src="/attachments/control-center/genai-resources/overview-genai-resources.png" >}} +{{< figure src="/attachments/control-center/genai-resources/overview-genai-resources.png" alt="" >}} ## Provisioning GenAI Resources -You can provision any GenAI resources directly within the Control Center using the self-service capability. -To do so, select the appropriate resource type and click **Provision Resource**. +You can provision any GenAI resources directly within the Control Center using the self-service capability. To do so, select the appropriate resource type and click **Provision Resource**. {{% alert color="info" %}} Ensure that you are on the correct resource tab before provisioning. For example, to create a new text generation resource, first select the **Text Generation Resources** tab. @@ -43,52 +42,49 @@ When provisioning a new resource, enter the following information: * **Display Name** – The name of the resource. * **Environment** – The environment for which the resource is created, such as Test, Acceptance, or Production. -* **Mendix Cloud Region** – The cloud region where the resource will be hosted. -* **Cross-region inference** – Specifies whether the selected model supports cross-region inference. For more information, refer to the [Settings](/agents/mx-cloud-genai/Navigate-MxGenAI/#settings) section of *Navigate through the Mendix Cloud GenAI Portal*. -* **Available Text Generation Models** – A list of the supported models you can choose from, for example, Anthropic Claude Sonnet V4. -* **Size** – The subscription plan with the tokens used for resources. +* **Mendix Cloud Region** – The cloud region where the resource is hosted. +* **Cross Region Inference** – Select whether to enable cross region inference for this resource. Without cross region inference, the latest model versions may not be available. For more information, see the [Settings](/agents/mx-cloud-genai/Navigate-MxGenAI/#settings) section of *Navigate through the Mendix Cloud GenAI Portal*. +* **Available Models** – The model versions to enable on the resource. For text generation resources, select one or more versions from the available Claude model families (for example, Claude Haiku 4.5, Claude Sonnet 4.5, Claude Sonnet 4.6, Claude Opus 4.6, Claude Opus 4.7, Claude Opus 4.8). For embeddings resources, select a single model from the available options. +* **Default Model** – The model version used when no model is explicitly specified in an API call. Select one of the model versions chosen in **Available Models**. This ensures backward compatibility with existing apps that use older connector versions. +* **Cloud Tokens** – The number of Mendix Cloud Tokens to allocate per month (minimum 1). Each Cloud Token provides 100 GenAI Units. The **Resource Specification** panel shows the resulting monthly GenAI Unit allocation. * **User** – The name of the user for whom the provisioning was initially created. * **Email** – The user's email address. -After filling in the required fields, you can review all the entered details in the **Resource Specification**. To learn more, refer to [Mendix Cloud GenAI Resource Packs](/agents/mx-cloud-genai/resource-packs/). +After filling in the required fields, review all the entered details in the **Resource Specification** panel. If the Cloud Token amount entered exceeds your available balance, the **Cloud Tokens Consumption** widget turns red and the **Provision Resource** button is disabled. To learn more about GenAI Unit allocation, see [Mendix Cloud GenAI Resource Packs](/agents/mx-cloud-genai/resource-packs/). -Click **Provision Resource** to finalize the process. You are taken back to the **GenAI Resources** page, where the newly created resource is displayed in the list. Selecting the newly provisioned resource opens its details directly in the Mendix Cloud GenAI Portal in a new tab. +Click **Provision Resource** to proceed. Before provisioning is finalized, a **Resource Summary** confirmation dialog shows a read-only overview of all entered details. Review the summary and click **Confirm** to complete provisioning. You are taken back to the **GenAI Resources** page, where the newly created resource is displayed in the list. Selecting the newly provisioned resource opens its details directly in the Mendix Cloud GenAI Portal in a new tab. ## Deprovisioning GenAI Resources -If you want to deprovision the resource, click the three-dot icon ({{% icon name="three-dots-menu-horizontal" %}}) next to the selected resource and select **Deprovision Resource**. -A confirmation pop-up appears, displaying a message and the details of the selected resource, as shown in the example below. +To deprovision a resource, click the three-dot icon ({{% icon name="three-dots-menu-horizontal" %}}) next to the selected resource and select **Deprovision Resource**. A confirmation dialog box appears, displaying a message and the details of the selected resource, as shown in the example below. -{{< figure src="/attachments/control-center/genai-resources/deprovisioning.png" >}} +{{< figure src="/attachments/control-center/genai-resources/deprovisioning.png" alt="" >}} -Click **Deprovision** to proceed. After confirmation, the resource status updates on the **GenAI Resource** page to reflect that deprovisioning is scheduled. +Click **Deprovision** to proceed. After confirmation, the resource status updates on the **GenAI Resources** page to reflect that deprovisioning is scheduled. {{% alert color="info" %}} -Your subscription plan operates on a monthly bundle cycle. When you deprovision a resource, the actual deprovisioning will occur at the end of the current subscription month. Until that date, you can still use the resource, and the scheduled deprovisioning date will appear in the resource's **Status**. +When you deprovision a resource, the actual deprovisioning occurs at the end of the current bundle month. Until that date, you can still use the resource, and the scheduled deprovisioning date appears in the resource's **Status**. Knowledge base and embeddings resources can be deprovisioned in the same bundle month. The system handles the dependency automatically. {{% /alert %}} -## Adjusting GenAI Resource Plan Size +## Adjusting Resource GenAI Unit Capacity {#adjusting-resource-genai-unit-capacity} -You can change the plan size of an already provisioned GenAI resource (text or embedding models) to better match your actual token demand. You can adjust the GenAI resource plan size through the self-service capability of the Control Center. +You can change the Cloud Token allocation of an already provisioned GenAI resource (text generation or embeddings) to better match your actual usage. You can adjust the allocation through the self-service capability of the Control Center. -To adjust a resource plan size, do the following: +To adjust the GenAI Unit capacity of a resource, do the following: 1. Log in to the Control Center as a Company Admin. -2. On the **GenAI Resources** page, click the three-dot ({{% icon name="three-dots-menu-horizontal-filled" %}}) icon next to the selected resource and select **Adjust Plan Size**. -3. Choose the desired plan and review the **Resource Specification** on the **Adjust Plan Size GenAI Resource** page. Click **Adjust Plan** to submit the change. +2. On the **GenAI Resources** page, click the three-dot ({{% icon name="three-dots-menu-horizontal-filled" %}}) icon next to the selected resource and select **Adjust Capacity**. +3. Enter the new Cloud Token amount and review the updated **Resource Specification**. Click **Adjust Capacity** to submit the change. -{{< figure src="/attachments/control-center/genai-resources/adjust-plan-size.png" >}} +{{< figure src="/attachments/control-center/genai-resources/adjust-plan-size.png" alt="" >}} -### Upgrading GenAI Resource Plan Size +### Increasing GenAI Unit Capacity -To upgrade, select a larger plan that matches your expected demand. Upgrades take effect immediately. Your account must have sufficient unutilized cloud tokens to cover the additional tokens required by the new plan. For example, upgrading from a 30-token (Small) plan to a 60-token (Medium) plan requires at least 30 unutilized cloud tokens in your account. If your account lacks the required tokens, you will receive an error message and the upgrade will be prevented. +Increases take effect immediately. The additional GenAI Units are added to the current bundle month and apply to all future months. Your account must have sufficient available Cloud Tokens to cover the increase. -### Downgrading GenAI Resource Plan Size +### Decreasing GenAI Unit Capacity -To downgrade, select a smaller plan. Downgrades are not immediate. The current plan remains active until the end of the current subscription month, and the downgrade takes effect at the start of the next subscription month. For example, if a Medium plan started on 12 February and you schedule a downgrade on 20 February to Small, the actual downgrade will occur on 12 March. The cloud tokens returned to your account as a result of the downgrade become available only after the scheduled downgrade takes effect. +The behavior depends on how much of the current month's allocation has already been consumed: -#### Cancelling a Scheduled Downgrade - -You can cancel a scheduled downgrade at any time before it takes effect. When a downgrade is scheduled, the resource status changes to **PLAN DOWNGRADE SCHEDULED**. To cancel it, click the three-dot ({{% icon name="three-dots-menu-horizontal-filled" %}}) icon next to the selected resource and select **Cancel Plan Downgrade**. The action takes effect immediately and cancels the scheduled downgrade. - -{{< figure src="/attachments/control-center/genai-resources/cancel-plan-downgrade.png" >}} +* **Immediate decrease** – If the GenAI Units consumed so far in the current bundle month are less than the new allocation, the decrease takes effect immediately and Cloud Tokens are released immediately. +* **Deferred decrease** – If the GenAI Units consumed so far in the current bundle month exceed the new allocation, the current month continues at the existing allocation. The decrease takes effect at the start of the next bundle month, and Cloud Tokens are released at that point. diff --git a/content/en/docs/genai/mendix-cloud-genai/mendix-cloud-grp.md b/content/en/docs/genai/mendix-cloud-genai/mendix-cloud-grp.md index 063f49e16e2..2989ec2a10a 100644 --- a/content/en/docs/genai/mendix-cloud-genai/mendix-cloud-grp.md +++ b/content/en/docs/genai/mendix-cloud-genai/mendix-cloud-grp.md @@ -12,21 +12,21 @@ aliases: Mendix Cloud GenAI Resource Packs provide turn-key access to Generative AI technology, delivered through Mendix Cloud. -* Model Resource Packs offer customers access to large language model capacity. Each resource pack includes an allocation of input/output tokens for Anthropic's Claude and Cohere's Embed. Support for additional models will be introduced in the future. +* Model Resource Packs offer access to large language model capacity. You choose a monthly Cloud Token amount, which is converted to GenAI Units at a rate of 100 GenAI Units per Cloud Token. GenAI Units are consumed against a model-specific exchange rate, so you can use any supported Anthropic Claude model — Haiku, Sonnet, or Opus — from a single resource. New model versions are automatically available on your existing resource as Mendix adds them — no resource changes or key updates are required. * Knowledge Base Resource Packs provide an OpenSearch-based vector database to support Retrieval-Augmented Generation (RAG), Semantic Search, and other Generative AI use cases. -Developers can use the Mendix Portal to manage their Mendix Cloud GenAI resources and seamlessly integrate model and knowledge base capabilities into their Mendix applications using the [Mendix Cloud GenAI Connector](/agents/mx-cloud-genai/mxgenai-connector/). Optimized for high performance and low latency, Mendix Cloud GenAI Resource Packs provide the easiest and fastest way to deliver end-to-end Generative AI solutions with Mendix. +Developers can use the Mendix Portal to manage their Mendix Cloud GenAI resources and seamlessly integrate model and knowledge base capabilities into their Mendix apps using the [Mendix Cloud GenAI Connector](/agents/mx-cloud-genai/mxgenai-connector/). Optimized for high performance and low latency, Mendix Cloud GenAI Resource Packs provide the easiest and fastest way to deliver end-to-end Generative AI solutions with Mendix. ### General Availability -Mendix Cloud GenAI Resource Packs is a premium Mendix product that requires an additional purchase. To start using GenAI Resource Packs or inquire about pricing, contact your Customer Success Manager (CSM). For more information, you can also reach out to [genai-resource-packs@mendix.com](mailto:genai-resource-packs@mendix.com). +Mendix Cloud GenAI Resource Packs is a premium Mendix product that requires an additional purchase. To start using GenAI Resource Packs or inquire about pricing, contact your Customer Success Manager (CSM). For more information, you can also contact [genai-resource-packs@mendix.com](mailto:genai-resource-packs@mendix.com). -GenAI Resource Packs can be purchased using Mendix Cloud Tokens. For details around costs, refer to [Cloud Tokens](/control-center/cloud-tokens/). +GenAI Resource Packs can be purchased using Mendix Cloud Tokens. For details around costs, see [Cloud Tokens](/control-center/cloud-tokens/). ## Models -Mendix Cloud Model Resource Packs provide customers with a monthly quota of input and output tokens for Anthropic's Claude and Cohere's Embed models. This allows customers to implement typical Generative AI use cases using text generation, embeddings, and knowledge bases. +Mendix Cloud GenAI Resource Packs give you access to Anthropic's Claude model families and Cohere's Embed models. A single text generation resource supports multiple Claude model families — Haiku, Sonnet, and Opus — so you can use the most appropriate model for each use case without managing separate resources. ### Supported Models @@ -34,9 +34,13 @@ The Mendix Cloud GenAI Resource Packs provide access to the following models: | Model | Model Type | Region(s) | Available Only via Cross-Region Inference (CRI) | AWS Inference Regions | | ----- | ---------- | --------- | ----------------------------------------------- | --------------------------- | -| Anthropic Claude 4.6 Sonnet | Text | Mendix Cloud EU (Frankfurt, Germany) | YES | eu-north-1,
Europe (Paris),
eu-south-1,
eu-south-2,
Europe (Ireland),
Europe (Frankfurt) | -| Anthropic Claude 4.5 Sonnet | Text | Mendix Cloud EU (Frankfurt, Germany) | YES | eu-north-1,
Europe (Paris),
eu-south-1,
eu-south-2,
Europe (Ireland),
Europe (Frankfurt) | -| Anthropic Claude 3 Sonnet | Text | Mendix Cloud Canada (Montreal) | NO | ca-central-1 | +| Anthropic Claude Haiku 4.5 | Text | Mendix Cloud EU (Frankfurt, Germany) | YES | eu-north-1,
Europe (Paris),
eu-south-1,
eu-south-2,
Europe (Ireland),
Europe (Frankfurt) | +| Anthropic Claude Sonnet 4.5 | Text | Mendix Cloud EU (Frankfurt, Germany) | YES | eu-north-1,
Europe (Paris),
eu-south-1,
eu-south-2,
Europe (Ireland),
Europe (Frankfurt) | +| Anthropic Claude Sonnet 4.6 | Text | Mendix Cloud EU (Frankfurt, Germany) | YES | eu-north-1,
Europe (Paris),
eu-south-1,
eu-south-2,
Europe (Ireland),
Europe (Frankfurt) | +| Anthropic Claude Sonnet 3 | Text | Mendix Cloud Canada (Montreal) | NO | ca-central-1 | +| Anthropic Claude Opus 4.6 | Text | Mendix Cloud EU (Frankfurt, Germany) | YES | eu-north-1,
Europe (Paris),
eu-south-1,
eu-south-2,
Europe (Ireland),
Europe (Frankfurt) | +| Anthropic Claude Opus 4.7 | Text | Mendix Cloud EU (Frankfurt, Germany) | YES | eu-north-1,
Europe (Paris),
eu-south-1,
eu-south-2,
Europe (Ireland),
Europe (Frankfurt) | +| Anthropic Claude Opus 4.8 | Text | Mendix Cloud EU (Frankfurt, Germany) | YES | eu-north-1,
Europe (Paris),
eu-south-1,
eu-south-2,
Europe (Ireland),
Europe (Frankfurt) | | Cohere Embed v4 | Embeddings | Mendix Cloud EU (Frankfurt, Germany) | YES | eu-north-1,
Europe (Paris),
eu-south-1,
eu-south-2,
Europe (Ireland),
Europe (Frankfurt) | | Cohere Embed v3
English and multilingual | Embeddings | Mendix Cloud EU (Frankfurt, Germany)
Mendix Cloud Canada (Montreal) | NO | Europe (Frankfurt),
ca-central-1 | @@ -48,38 +52,45 @@ Customers looking to leverage other models in addition to the above can also tak Additional regions will be available in the future. If you have questions about upcoming regions or want to explore making models available in your specific region, reach out to `genai-resource-packs@mendix.com`. {{% /alert %}} -### Technical Details for Model Resource Packs +### GenAI Units and Model Pricing -| GenAI Model Resource Pack Plan | S | M | L | -| ------------------------------------------------ | ------ | ----- | ---- | -| Anthropic Claude (any version) (Tokens in/month) | 2.5 million | 5 million | 10 million | -| Anthropic Claude (any version) (Tokens out/month) | 1.25 million | 2.5 million | 5 million | -| Cohere Embed (any version) (Tokens in/month) | 5 million | 10 million | 20 million | +Text generation and embeddings resources use a flexible consumption model based on GenAI Units. When you provision a resource, you choose a monthly GenAI Unit capacity in Mendix Cloud Tokens. The system converts your selection to GenAI Units at a fixed rate of 100 GenAI Units per Cloud Token. All consumption is then deducted from this GenAI Units balance at a model-specific exchange rate. -## Accessing GenAI Resources +For example, if you allocate 50 Cloud Tokens per month, your resource receives 5,000 GenAI Units per month. You can use any combination of available models against this balance. The exchange rates are as follows: + +| Model Family | GenAI Units per 1M Input Tokens | GenAI Units per 1M Output Tokens | +| ------------ | ------------------------------- | -------------------------------- | +| Claude Haiku | 35.81 | 179.07 | +| Claude Sonnet | 107.44 | 537.21 | +| Claude Opus | 179.07 | 895.35 | +| Cohere Embed | 30.23 | — | + +There are no fixed capacity tiers. You choose any Cloud Token amount that matches your expected usage and adjust it at any time. For more information, see the [Adjusting Resource GenAI Unit Capacity](/control-center/genai-resources-self-service/#adjusting-resource-genai-unit-capacity) section of *GenAI Resources*. -Developers can easily obtain access to GenAI resources through a self-service capability, enabling them to access and manage GenAI resources independently. +{{% alert color="info" %}} +Unused GenAI Units at the end of a bundle month do not carry over. Your balance is refilled at the start of each new bundle month. +{{% /alert %}} -Developers with the required prerequisites can use the self-service capability to provision, deprovision, and manage GenAI resources directly from the Control Center. This enables faster provisioning and reduces manual dependency. +## Accessing GenAI Resources -For developers who do not have self-service capabilities, GenAI resources can still be provisioned or deprovisioned by contacting sales representatives or a Customer Success Manager (CSM) to order an existing stock keeping unit (SKU). +Company Admins can obtain access to GenAI resources through a self-service capability, enabling them to provision, deprovision, and manage resources independently from the Control Center. This enables faster provisioning and reduces manual dependency. -Both approaches allow users to scale GenAI resources efficiently and explore more generative AI solutions with Mendix. +For Company Admins who do not meet the self-service prerequisites, GenAI resources can still be provisioned or deprovisioned by contacting a sales representative or Customer Success Manager (CSM) to order the existing stock keeping unit (SKU) associated with your Mendix subscription. ### Provisioning GenAI Resources Using the Self-Service Capability -When using the self-service capability, Mendix Admins can manage the provisioning and deprovisioning of GenAI resources directly through the [Control Center](https://controlcenter.mendix.com/index.html). They can provision the new resource, review it, and open it in a new tab of the [Mendix Cloud GenAI portal](https://genai.home.mendix.com/p/homepage). For more information, refer to [GenAI Resources](/control-center/genai-resources-self-service/). +When using the self-service capability, Company Admins can manage the provisioning and deprovisioning of GenAI resources directly through the [Control Center](https://controlcenter.mendix.com/index.html). They can provision the new resource, review it, and open it in a new tab of the [Mendix Cloud GenAI portal](https://genai.home.mendix.com/p/homepage). For more information, see [GenAI Resources](/control-center/genai-resources-self-service/). To provision GenAI resources successfully using self-service, ensure that you meet the requirements below: -1. Mendix Admins can access the Control Center to provision or deprovision the GenAI resources. -2. You have sufficient free Mendix Cloud Tokens. These tokens are required to allocate GenAI capacity. For more information, refer to [Cloud Tokens](/control-center/cloud-tokens/). +1. You have access to the Control Center as a Company Admin. +2. You have sufficient free Mendix Cloud Tokens. These tokens are required to allocate GenAI Unit capacity. For more information, see [Cloud Tokens](/control-center/cloud-tokens/). -For further details, refer to the [Prerequisites](/control-center/genai-resources-self-service/#prerequisites) section of *GenAI Resources*. +For further details, see the [Prerequisites](/control-center/genai-resources-self-service/#prerequisites) section of *GenAI Resources*. ### Provisioning GenAI Resources Without Using the Self-Service Capability -If the self-service capability is not available in your environment, you can still provision your GenAI resources by ordering the existing SKU associated with your Mendix subscription. To do so, you can contact your sales representative or CSM. +If the self-service capability is not available in your environment, you can still provision your GenAI resources by ordering the existing SKU associated with your Mendix subscription. To do so, contact your sales representative or CSM. ## Knowledge Bases @@ -124,9 +135,9 @@ Compliance with these terms is mandatory to maintain access to the services. ### Mendix Cloud GenAI Portal -The [Mendix Cloud GenAI Portal](https://genai.home.mendix.com/) allows easy access to manage the resources through the GenAI Resources section of the portal. +The [Mendix Cloud GenAI Portal](https://genai.home.mendix.com/) allows easy access to manage your resources. -* Get insight into the consumption of input/output tokens for Text and Embeddings Generation Resources. +* Monitor GenAI Unit consumption and input/output token usage for Text and Embeddings Generation Resources. * Manage content for Knowledge Bases. * Manage team access to all resources. * Create and manage connection keys to connect your apps with all resources. @@ -136,7 +147,7 @@ For more information, see [Navigate Through the Mendix Cloud GenAI Portal](/agen ### Mendix Cloud GenAI Connector -The [Mendix Cloud GenAI connector](/agents/mx-cloud-genai/mxgenai-connector/) lets you utilize Mendix Cloud GenAI resource packs directly within your Mendix application. It allows you to integrate generative AI by dragging and dropping common operations from its toolbox. Note that any versions older than the ones listed below are no longer functional: +The [Mendix Cloud GenAI connector](/agents/mx-cloud-genai/mxgenai-connector/) lets you use Mendix Cloud GenAI Resource Packs directly within your Mendix application. It allows you to integrate generative AI by dragging and dropping common operations from its toolbox. Note that any versions older than the ones listed below are no longer functional: * GenAI for Mendix bundle v2.4.1 (Mendix 9) (contains Mendix Cloud GenAI connector) or * Mendix Cloud GenAI connector v3.1.1 (no `DeployedKnowledgeBase` support) or diff --git a/content/en/docs/genai/mendix-cloud-genai/navigate_mxgenai.md b/content/en/docs/genai/mendix-cloud-genai/navigate_mxgenai.md index 66419c0a2dd..f93acbff3e7 100644 --- a/content/en/docs/genai/mendix-cloud-genai/navigate_mxgenai.md +++ b/content/en/docs/genai/mendix-cloud-genai/navigate_mxgenai.md @@ -14,7 +14,7 @@ The [Mendix Cloud GenAI portal](https://genai.home.mendix.com/) is the part of t ## Resource Details -After clicking a specific resource, you land on its details page, offering a shortcut to consumption insights, key generation, team management, and helpful documentation. +After clicking a specific resource, you land on its details page, which provides shortcuts to consumption insights, key generation, team management, and helpful documentation. {{< figure src="/attachments/genai/navigate_mxgenai/GenAIResource_Details.png" alt="" >}} @@ -22,41 +22,26 @@ After clicking a specific resource, you land on its details page, offering a sho The **Settings** tab contains the details of a GenAI resource. It shows the following: -* **Display Name**: indicates the name of the resource. -* **ID**: indicates the resource ID. -* **Region(s)**: the region where the resource is hosted. -* **Cross Region Inference (CRI)**: shows if the model supports cross-region inference ¹. -* **Cloud Provider**: indicates the cloud provider, for example, AWS. -* **Type**: this is the type of resource, for example, Text Generation, Embedding, Knowledge Base, etc. -* **Model**: indicates which model is used, for example, Anthropic Claude Sonnet 3.5. For more information, see the [Upgrading the Text Model Version](#upgrade-model) section below. -* **Plan**: indicates the subscription plan used for compute resources (for example, embedding or text generation resources). -* **Environment**: shows which environment is used, for example, test, acceptance, or production. +* **Display Name** – The name of the resource. +* **ID** – The resource ID. +* **Region(s)** – The region where the resource is hosted. +* **Cross Region Inference (CRI)** – Indicates whether cross region inference is enabled for this resource ¹. +* **Cloud Provider** – The cloud provider, for example, AWS. +* **Type** – The type of resource, for example, Text Generation Model, Embeddings Generation, or Knowledge Base. +* **Available models** – The model versions enabled on the resource. For text generation resources, this lists all Claude model versions available for use (for example, Anthropic Claude Haiku 4.5, Anthropic Claude Sonnet 4.5, Anthropic Claude Sonnet 4.6). For embeddings resources, this lists all available Cohere Embed model versions (for example, Cohere Embed English v3, Cohere Embed multilingual v3, Cohere Embed v4). +* **Default model** – The model version used as a fallback when no model is explicitly specified in an API call. This field only applies to text generation resources and is present for backward compatibility with apps using connector versions below V3.0.0. +* **Tokens** – The monthly GenAI Unit allocation for the resource, for example, 1,000 GenAI Units. +* **Environment** – The environment, for example, Test, Acceptance, or Production. -¹ Cross-region inference (CRI) allows a model to redirect requests to another region, helping to distribute the load across multiple regions within the same area. EU requests always stay within EU regions. Connecting to a cross-region inference profile does not change how the request is sent; the redirection happens on the server side, determining the region to handle the request to get the fastest response. For more information, see [Increase throughput with cross-region inference](https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference.html). If applicable, CRI profiles are selected during provisioning of a model resource. New models are available under the CRI inferencing type by default. +¹ Cross Region Inference (CRI) allows a model to redirect requests to another region, helping to distribute the load across multiple regions within the same area. EU requests always stay within EU regions. Connecting to a cross region inference profile does not change how the request is sent; the redirection happens on the server side, determining the region to handle the request to get the fastest response. For more information, see [Increase throughput with cross-region inference](https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference.html). If applicable, CRI profiles are selected during provisioning of a model resource. New models are available under the CRI inferencing type by default. #### Additional Details for Knowledge Base Resources For knowledge base resources, you can also see details of the associated embeddings resource and vice versa. To learn more about embeddings, see the [Embedding vector](/agents/rag/#embedding-vector) section of *RAG in a Mendix App*. -#### Upgrading the Text Model Version{#upgrade-model} +#### Adjusting the GenAI Unit Capacity of a Resource -Model version upgrades let you migrate your Text Generation Resources to a newer, non-deprecated model within the same model family. For example, GenAI Resources offer the Claude Sonnet family, ranging from Claude Sonnet 3.7 to Claude Sonnet 4.5. Upgrading ensures you gain the latest performance improvements and AI capabilities. In the **Settings** tab of your Text Generation Resource, click **Change Model** to view and select the available model version. - -{{% alert color="warning" %}} -While changing the model version, note the following: - -* Changing a model version in production requires careful evaluation. Even within the same model family, newer versions can behave differently, and may affect how your LLM-driven applications, such as agents, perform. - -* Always validate a new model version in a test environment before using it for your use case, and downgrade to the previous version if required. -{{% /alert %}} - -{{% alert color="info" %}} -Ensure you are using Mendix Cloud GenAI Connector version 5.3.0 and above to support the latest Cohere Embed v4 model. To see the upgraded model version reflected in your GenAI Connector after upgrading, make sure you are using Mendix Cloud GenAI Connector version 5.4.0 and above. -{{% /alert %}} - -#### Adjusting the Plan Size of GenAI Resources (Text and Embedding Models) - -After a resource is provisioned, you can change its plan size, either upgrade or downgrade it to match your actual production token usage. Company admins can change the plan through the GenAI Resources self-service in the Control Center. For more information, see the [Adjusting GenAI Resource Plan Size](/control-center/genai-resources-self-service/#adjusting-genai-resource-plan-size) section of *GenAI Resources*. +After a resource is provisioned, you can change its GenAI Unit capacity to match your actual usage. Company Admins can adjust the capacity through the GenAI Resources self-service in the Control Center. For more information, see the [Adjusting Resource GenAI Unit Capacity](/control-center/genai-resources-self-service/#adjusting-resource-genai-unit-capacity) section of *GenAI Resources*. ### Team @@ -68,9 +53,9 @@ The **Team** page allows you to manage access to the Mendix Cloud GenAI resource You can invite members from outside your organization to access your GenAI resources by entering their email address in **Add Member**. This option is available only if your company admin has enabled external user invitations. -You can track invitations in the **Pending Invites** tab. Invited users will receive an email with a link to accept or decline the invitation. If they do not yet have a Mendix account, the link redirects them to create one. Once the invitation is accepted, the resource will appear in their GenAI portal overview. +You can track invitations in the **Pending Invites** tab. Invited users receive an email with a link to accept or decline the invitation. If they do not yet have a Mendix account, the link redirects them to create one. Once the invitation is accepted, the resource appears in their GenAI portal overview. -Pending invitations can be withdrawn at any time and will automatically expire after two weeks. External members can create and delete keys, export consumption data, manage knowledge base content and collections, and change the model. However, they cannot modify the display name or environment, or manage team membership. +You can withdraw pending invitations at any time. Invitations automatically expire after two weeks. External members can create and delete keys, export consumption data, manage knowledge base content and collections, and change the model. However, they cannot modify the display name or environment, or manage team membership. ### Keys @@ -78,15 +63,15 @@ Pending invitations can be withdrawn at any time and will automatically expire a The **Keys** tab allows you to manage configuration keys for the resources. These keys provide programmatic access to the GenAI resources. From the **Keys** tab, you can create new keys and revoke existing ones. -To create a new key, click **Create Key**, add a description, and save the changes. A pop-up message will display the key. +To create a new key, click **Create Key**, add a description, and save the changes. A dialog box displays the key. {{% alert color="info" %}} -Make sure to store it securely, as it will only be shown once. +Store it securely. The key is shown only once. {{% /alert %}} {{< figure src="/attachments/genai/navigate_mxgenai/GenAIResource_KeyGeneration.png" alt="" >}} -Once created, the key can be used in the Mendix application via the Mendix Cloud GenAI connector. +Once created, the key can be used in the Mendix application via the Mendix Cloud GenAI connector. A single key exposes all model versions currently enabled on the resource. When you import the key into your application, all available models are accessible. No key rotation is required when new model versions are added to the resource. #### Additional Information for Knowledge Base Resource Keys @@ -149,24 +134,32 @@ You can upload data directly from Mendix to the Knowledge Base. To do so, severa {{% alert color="info" %}} The **Consumption** tab is available for Model resources only.{{% /alert %}} -The **Consumption** section provides outcomes of token consumption monitoring for each GenAI resource in a graphical way. Use this overview to see the current usage, insights on the usage per day, and to compare the current month with previous months. Note that months represent bundle months here, which is the period during which token consumption is tracked, beginning on the date of your last GenAI Resource plan entitlement reset and ending on the next reset date. This creates a recurring monthly cycle based on your plan activation date, not the calendar month. +The **Consumption** tab provides an overview of GenAI Unit and token consumption for the resource. Use this overview to see current usage, view daily consumption insights, and compare the current period with previous periods. Note that periods represent bundle months. A bundle month is the period during which consumption is tracked, beginning on the date of your last GenAI Resource entitlement reset and ending on the next reset date. This creates a recurring monthly cycle based on your resource activation date, not the calendar month. {{< figure src="/attachments/genai/navigate_mxgenai/GenAIResource_TokenConsumptionMonitor.png" alt="" >}} -#### What Are Tokens? +The **Current Consumption** panel shows the total GenAI Units consumed against your monthly allocation, displayed as a percentage and a number (for example, 1,521 / 1.6k). The **Plan** panel shows the model family in use and the total GenAI Unit allocation for the bundle month. The bundle refill date is shown at the top of the page. + +Below the summary, the page shows consumption over a selected time range. You can switch between weekly (**W**), bundle month (**BM**), month to date (**MTD**), and six months (**6M**) views. The charts show: + +* **Monthly GenAI Units Consumption** – GenAI Units consumed per day, with a dashed line indicating the monthly allocation limit. +* **Monthly Input Consumption** – Raw input tokens consumed per day. +* **Monthly Output Consumption** – Raw output tokens consumed per day. + +#### What Are Tokens and GenAI Units? -Tokens are what you pay for when consuming large language model services. +Tokens are what you pay for when consuming large language model services. Text input is first "tokenized," meaning it is broken down into smaller pieces where each piece represents a token. A good rule of thumb is that 100 tokens are around 75 English words, though this varies by model and language. Tokens sent to the model are called input tokens; tokens generated by the model are called output tokens. -In order for a large language model to understand text input, the text is first ‘tokenized’: broken down into smaller pieces where each piece represents a token with its unique ID. A good rule of thumb is that 100 tokens are around 75 English words, however there are always differences depending on the model or the language used. After tokenization, each token will be assigned an embeddings vector. The tokens required to feed the input prompt to the model are called ‘input tokens’. The tokens required to transform the model output vectors into, for example, text or images are called ‘output tokens’. +GenAI Units are the unit of measure for consumption across all models on a resource. Each model family has a different exchange rate. The exchange rate is the number of GenAI Units consumed per 1 million input or output tokens. A more capable model costs more GenAI Units per token than a less capable model. -#### When Are Tokens Consumed? +#### When Are Tokens and GenAI Units Consumed? -Text generation resources consume both input and output tokens (text sent to the model and generated by the model). +Text generation resources consume both input and output tokens, which are converted to GenAI Units using the model-specific exchange rate. Embeddings resources only consume input tokens. This is because only the generated embedding vectors are returned and the generated output is not tokenized. -Knowledge base resources do not consume tokens as they only store embedding vectors. Uploading a document to a knowledge base connected to an Embeddings resource will consume tokens in the embeddings resource. +Knowledge base resources do not consume tokens directly. Uploading a document to a knowledge base connected to an embeddings resource consumes tokens in that embeddings resource. -#### Exporting Token Consumption Data +#### Exporting Consumption Data -Click **Export** to export consumption data in CSV format. The export contains basic information about input tokens, output tokens, and dates. Days with no consumption are not exported. +Click **Export** to export consumption data in CSV format. The export contains information about input tokens, output tokens, and dates. Days with no consumption are not exported. diff --git a/content/en/docs/genai/reference-guide/external-platforms/mx-genai-connector.md b/content/en/docs/genai/reference-guide/external-platforms/mx-genai-connector.md index 21eee04084a..c454e298fda 100644 --- a/content/en/docs/genai/reference-guide/external-platforms/mx-genai-connector.md +++ b/content/en/docs/genai/reference-guide/external-platforms/mx-genai-connector.md @@ -21,7 +21,11 @@ Typical use cases for generative AI are described in more detail in the [Typical ### Prerequisites -To use this connector, you need configuration keys to authenticate to the Mendix Cloud GenAI services. You can generate keys in the [Mendix Cloud GenAI Portal](https://genai.home.mendix.com). Alternatively, ask someone with access to generate keys for you or add you to their team so you can generate keys yourself. +To use this connector, you need configuration keys to authenticate to the Mendix Cloud GenAI services. You can generate keys in the [Mendix Cloud GenAI Portal](https://genai.home.mendix.com). Alternatively, ask someone with access to generate keys for you or add you to their team so you can generate keys yourself. + +{{% alert color="info" %}} +The Mendix Cloud GenAI Connector requires at least version 3.0.0. To use multiple models from a single resource, upgrade to version V3.2.1 or later. +{{% /alert %}} {{% alert color="info" %}} The Mendix Cloud GenAI Connector module generates embeddings internally when interacting with a knowledge base. You do not need to create embedding keys yourself when interacting with a Mendix Cloud knowledge base. Direct embedding operations are only required if additional processes are needed, such as using the generated vectors instead of text. For example, a similar search algorithm could use vector distances to calculate relatedness. @@ -48,10 +52,16 @@ To get started, follow these steps: * Add the `Configuration_Overview` page (**USE_ME** > **Configuration**) to your navigation, or add the `Snippet_Configuration` to a page that is already part of your navigation. Alternatively, register your key by using the `Configuration_RegisterByString` microflow. * Complete the runtime setup of the Mendix Cloud GenAI configuration by navigating to the page mentioned above. Import a key generated in the [Mendix Cloud GenAI Portal](https://genai.home.mendix.com) or provided to you and click **Test Key** to validate its functionality. This key establishes a connection between the Mendix Cloud resources and your application and contains all the information required to set up the connection. +A single key exposes all model versions currently enabled on the resource. When you import the key, all available models are accessible. No key rotation is required when new model versions are added to the resource by a Company Admin. + {{% alert color="info" %}} When using an Embeddings Model Resource together with a Knowledge Base Resource, you do not need to import both keys. Importing the Knowledge Base Resource key automatically generates the connection details for the embeddings generation model. {{% /alert %}} +{{% alert color="info" %}} +If you are using connector version V3.2.1 or later, you can select which model to use per agent or microflow from all available models on the resource. If you are using an older version, the connector automatically uses the default model configured on the resource. You do not need to update your app unless you want to use a different model explicitly. +{{% /alert %}} + ## Operations {{< figure src="/attachments/genai/mxgenAI-connector/mxgenaiconnector-configuration.png" alt="" >}} @@ -241,7 +251,7 @@ Use the following toolbox actions to retrieve knowledge data from a collection a ### Embedding Operations -If you are working directly with embedding vectors for specific use cases that do not include knowledge base interaction, such as clustering or classification, the operations below are relevant. For practical examples and guidance, refer to the [GenAI Showcase Application](https://marketplace.mendix.com/link/component/220475) to see how these embedding-only operations can be used. +If you are working directly with embedding vectors for specific use cases that do not include knowledge base interaction, such as clustering or classification, the operations below are relevant. For practical examples and guidance, see the [GenAI Showcase Application](https://marketplace.mendix.com/link/component/220475) to see how these embedding-only operations can be used. To implement embeddings into your Mendix application, use the microflows in the **Knowledge Bases & Embeddings** folder in the GenAICommons module. Both microflows for embeddings are exposed as microflow actions under the **GenAI (Generate)** category in the **Toolbox** in Studio Pro. @@ -329,7 +339,7 @@ To fix this error, try synchronizing all dependencies (**App** > **Synchronize d ## Read More {#readmore} -For Anthropic Claude-specific documentation, refer to: +For Anthropic Claude-specific documentation, see: * [Prompt Engineering Guide](https://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering/overview) * [Tool Use / Function Calling](https://docs.anthropic.com/en/docs/build-with-claude/tool-use)