From c1cc2fe987df3de8e516cb7d5ddc218d45505f6b Mon Sep 17 00:00:00 2001 From: linaaaf <90840263+linaaaf@users.noreply.github.com> Date: Thu, 28 Aug 2025 15:15:12 +0200 Subject: [PATCH 01/12] Update mendix-cloud-grp.md - added small section around required connector versions --- .../marketplace/genai/mendix-cloud-genai/mendix-cloud-grp.md | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/content/en/docs/marketplace/genai/mendix-cloud-genai/mendix-cloud-grp.md b/content/en/docs/marketplace/genai/mendix-cloud-genai/mendix-cloud-grp.md index 2f459ef1173..fdbe2167d48 100644 --- a/content/en/docs/marketplace/genai/mendix-cloud-genai/mendix-cloud-grp.md +++ b/content/en/docs/marketplace/genai/mendix-cloud-genai/mendix-cloud-grp.md @@ -75,7 +75,10 @@ The Mendix Portal allows easy access to manage the resources, through the GenAI ## Mendix Cloud GenAI Connector -The [Mendix Cloud GenAI connector](/appstore/modules/genai/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. +The [Mendix Cloud GenAI connector](/appstore/modules/genai/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. Please make sure to use no older versions of this connector as +* contained in GenAI for Mendix bundle v2.4.1 (Mendix 9) or +* Mendix Cloud GenAI connector v3.1.1 (no DeployedKnowledgeBase support) or +* Mendix Cloud GenAI connector v4.4.0 (DeployedKnowledgeBase support). ## Regional Availability From c70fcf5cde0c18e9f620aedfcc4fa5ab2d6f9480 Mon Sep 17 00:00:00 2001 From: linaaaf <90840263+linaaaf@users.noreply.github.com> Date: Fri, 29 Aug 2025 11:16:37 +0200 Subject: [PATCH 02/12] Update navigate_mxgenai.md added section about using metadata instead of one collection per topic --- .../marketplace/genai/mendix-cloud-genai/navigate_mxgenai.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/content/en/docs/marketplace/genai/mendix-cloud-genai/navigate_mxgenai.md b/content/en/docs/marketplace/genai/mendix-cloud-genai/navigate_mxgenai.md index 723a058cc07..1ee79dbc347 100644 --- a/content/en/docs/marketplace/genai/mendix-cloud-genai/navigate_mxgenai.md +++ b/content/en/docs/marketplace/genai/mendix-cloud-genai/navigate_mxgenai.md @@ -77,7 +77,7 @@ On the **Content** page, you can find information on adding knowledge to your Kn Currently, you have the following options for adding data to a Knowledge Base: * Add files (for example, TXT or PDF) -* Add data from a Mendix application +* Add data from a Mendix application. #### Add Files @@ -85,6 +85,8 @@ When you select the **Add Files Like .TXT or .PDF** option, you can upload docum {{% alert color="info" %}} Only TXT and PDF files are supported. {{% /alert %}} +You can decide for yourself, whether to upload data to a new, the default or a different existing collection inside of the resource. Since collections correspond to GenIICommons.DeployedKnowledgebases, they provide separation inside of the same knowledge base resource into several objects. However, it is not a best practice to create many collections inside of the same resource and usually not required. Instead, metadata can also be used to 'label' data and provide a more performant way to separate data inside of the same collection. + ##### Metadata {#metadata} Metadata is additional information that can be attached to data in a GenAI knowledge base. Unlike the actual content, metadata provides structured details that help in organizing, searching, and filtering information more efficiently. It helps manage large datasets by allowing to retrieve of relevant data based on specific attributes rather than relying solely on similarity-based searches. From 93544b74a932d1dc9e232b85c507a49177835a99 Mon Sep 17 00:00:00 2001 From: linaaaf <90840263+linaaaf@users.noreply.github.com> Date: Fri, 29 Aug 2025 14:42:13 +0200 Subject: [PATCH 03/12] Update Mx GenAI Connector.md added section #architecture for collection info --- .../genai/mendix-cloud-genai/Mx GenAI Connector.md | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/content/en/docs/marketplace/genai/mendix-cloud-genai/Mx GenAI Connector.md b/content/en/docs/marketplace/genai/mendix-cloud-genai/Mx GenAI Connector.md index 022dcf05b25..0f698a4f6a8 100644 --- a/content/en/docs/marketplace/genai/mendix-cloud-genai/Mx GenAI Connector.md +++ b/content/en/docs/marketplace/genai/mendix-cloud-genai/Mx GenAI Connector.md @@ -41,7 +41,10 @@ Knowledge bases are often used for: 1. [Retrieval Augmented Generation (RAG)](/appstore/modules/genai/rag/) retrieves relevant knowledge from the knowledge base, incorporates it into a prompt, and sends it to the model to generate a response. 2. Semantic search enables advanced search capabilities by considering the semantic meaning of the text, going beyond exact and approximate matching. It allows the knowledge base to be searched for similar chunks effectively. -If you are looking for a step-by-step guide on how to get your application data into a Mendix Cloud Knowledge Base, refer [Grounding Your Large Language Model in Data – Mendix Cloud GenAI](/appstore/modules/genai/how-to/howto-groundllm/). Note that the Mendix Portal also provides options for importing data into your knowledge base, such as file uploads. For more information, see [Navigate through the Mendix Cloud GenAI Portal](/appstore/modules/genai/mx-cloud-genai/Navigate-MxGenAI/). This documentation focuses solely on adding data from an application using the connector. +If you are looking for a step-by-step guide on how to get your application data into a Mendix Cloud Knowledge Base, refer [Grounding Your Large Language Model in Data – Mendix Cloud GenAI](/appstore/modules/genai/how-to/howto-groundllm/). Note that the Mendix Portal also provides options for importing data into your knowledge base, such as file uploads. For more information, see [Navigate through the Mendix Cloud GenAI Portal](/appstore/modules/genai/mx-cloud-genai/Navigate-MxGenAI/). This documentation focuses solely on adding data from an application using the connector. + +##### Architecture +Each Knowledge Base resource may exist out of several collections where each collection corresponds to a `GenAICommons.DeployedKnowledgebase`. This offers a way of data separation into different objects, one object per collection. However, adding a large number of collections to the same knowledge base resource is not a best practice. Separation can also be achieved in a more performant and practical way through the addition of metadata. You can read more about this below, in the section about [Retrieve and Generate](/appstore/modules/genai/MxGenAI/#retrieve-and-generate). #### Embeddings From e3a582e6913470326ae67cabe6055ceb5d5c0fd5 Mon Sep 17 00:00:00 2001 From: linaaaf <90840263+linaaaf@users.noreply.github.com> Date: Fri, 29 Aug 2025 14:49:34 +0200 Subject: [PATCH 04/12] Update Mx GenAI Connector.md added link to DeployedKnowledgeBase entity --- .../marketplace/genai/mendix-cloud-genai/Mx GenAI Connector.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/content/en/docs/marketplace/genai/mendix-cloud-genai/Mx GenAI Connector.md b/content/en/docs/marketplace/genai/mendix-cloud-genai/Mx GenAI Connector.md index 0f698a4f6a8..0022340a0cb 100644 --- a/content/en/docs/marketplace/genai/mendix-cloud-genai/Mx GenAI Connector.md +++ b/content/en/docs/marketplace/genai/mendix-cloud-genai/Mx GenAI Connector.md @@ -44,7 +44,7 @@ Knowledge bases are often used for: If you are looking for a step-by-step guide on how to get your application data into a Mendix Cloud Knowledge Base, refer [Grounding Your Large Language Model in Data – Mendix Cloud GenAI](/appstore/modules/genai/how-to/howto-groundllm/). Note that the Mendix Portal also provides options for importing data into your knowledge base, such as file uploads. For more information, see [Navigate through the Mendix Cloud GenAI Portal](/appstore/modules/genai/mx-cloud-genai/Navigate-MxGenAI/). This documentation focuses solely on adding data from an application using the connector. ##### Architecture -Each Knowledge Base resource may exist out of several collections where each collection corresponds to a `GenAICommons.DeployedKnowledgebase`. This offers a way of data separation into different objects, one object per collection. However, adding a large number of collections to the same knowledge base resource is not a best practice. Separation can also be achieved in a more performant and practical way through the addition of metadata. You can read more about this below, in the section about [Retrieve and Generate](/appstore/modules/genai/MxGenAI/#retrieve-and-generate). +Each Knowledge Base resource may exist out of several collections where each collection corresponds to a [GenAICommons.DeployedKnowledgebase](/appstore/modules/genai-commons/#deployed-knowledge-base). This offers a way of data separation into different objects, one object per collection. However, adding a large number of collections to the same knowledge base resource is not a best practice. Separation can also be achieved in a more performant and practical way through the addition of metadata. You can read more about this below, in the section about [Retrieve and Generate](/appstore/modules/genai/MxGenAI/#retrieve-and-generate). #### Embeddings From e14a474156534f3b9f684b5dbd7aa3bbc16b78fc Mon Sep 17 00:00:00 2001 From: linaaaf <90840263+linaaaf@users.noreply.github.com> Date: Fri, 29 Aug 2025 14:50:37 +0200 Subject: [PATCH 05/12] Update navigate_mxgenai.md added Link to DeployedKnowledgeBase entity --- .../marketplace/genai/mendix-cloud-genai/navigate_mxgenai.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/content/en/docs/marketplace/genai/mendix-cloud-genai/navigate_mxgenai.md b/content/en/docs/marketplace/genai/mendix-cloud-genai/navigate_mxgenai.md index 1ee79dbc347..9483d765210 100644 --- a/content/en/docs/marketplace/genai/mendix-cloud-genai/navigate_mxgenai.md +++ b/content/en/docs/marketplace/genai/mendix-cloud-genai/navigate_mxgenai.md @@ -85,7 +85,7 @@ When you select the **Add Files Like .TXT or .PDF** option, you can upload docum {{% alert color="info" %}} Only TXT and PDF files are supported. {{% /alert %}} -You can decide for yourself, whether to upload data to a new, the default or a different existing collection inside of the resource. Since collections correspond to GenIICommons.DeployedKnowledgebases, they provide separation inside of the same knowledge base resource into several objects. However, it is not a best practice to create many collections inside of the same resource and usually not required. Instead, metadata can also be used to 'label' data and provide a more performant way to separate data inside of the same collection. +You can decide for yourself, whether to upload data to a new, the default or a different existing collection inside of the resource. Since collections correspond to [GenAICommons.DeployedKnowledgebases](/appstore/modules/genai-commons/#deployed-knowledge-base), they provide separation inside of the same knowledge base resource into several objects. However, it is not a best practice to create many collections inside of the same resource and usually not required. Instead, metadata can also be used to 'label' data and provide a more performant way to separate data inside of the same collection. ##### Metadata {#metadata} From c175926ce7277d5f5bbd2c201df3a8335ba300a2 Mon Sep 17 00:00:00 2001 From: linaaaf <90840263+linaaaf@users.noreply.github.com> Date: Fri, 29 Aug 2025 16:59:07 +0200 Subject: [PATCH 06/12] Update navigate_mxgenai.md edited section about best practices for collections in content --- .../marketplace/genai/mendix-cloud-genai/navigate_mxgenai.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/content/en/docs/marketplace/genai/mendix-cloud-genai/navigate_mxgenai.md b/content/en/docs/marketplace/genai/mendix-cloud-genai/navigate_mxgenai.md index 9483d765210..6e677149557 100644 --- a/content/en/docs/marketplace/genai/mendix-cloud-genai/navigate_mxgenai.md +++ b/content/en/docs/marketplace/genai/mendix-cloud-genai/navigate_mxgenai.md @@ -85,7 +85,7 @@ When you select the **Add Files Like .TXT or .PDF** option, you can upload docum {{% alert color="info" %}} Only TXT and PDF files are supported. {{% /alert %}} -You can decide for yourself, whether to upload data to a new, the default or a different existing collection inside of the resource. Since collections correspond to [GenAICommons.DeployedKnowledgebases](/appstore/modules/genai-commons/#deployed-knowledge-base), they provide separation inside of the same knowledge base resource into several objects. However, it is not a best practice to create many collections inside of the same resource and usually not required. Instead, metadata can also be used to 'label' data and provide a more performant way to separate data inside of the same collection. +Before the upload, you can decide for yourself, whether to upload data to a new, the default or a different existing collection inside of the resource. A Knowledge Base resource can comprise several collections. Each collection is specifically designed to hold numerous documents, serving as a logical grouping for related information based on their shared domain, purpose, or thematic focus. While collections provide a mechanism for data separation—with each corresponding to a [GenAICommons.DeployedKnowledgebases](/appstore/modules/genai-commons/#deployed-knowledge-base) — it is not best practice to create a large number of collections within a single Knowledge Base resource. A more performant and practical approach for achieving fine-grained data separation is through the strategic use of metadata. ##### Metadata {#metadata} From ef07750f6ad9fcf8e80bbb8dc9b543f6e50e8742 Mon Sep 17 00:00:00 2001 From: linaaaf <90840263+linaaaf@users.noreply.github.com> Date: Fri, 29 Aug 2025 16:59:53 +0200 Subject: [PATCH 07/12] Update navigate_mxgenai.md removed unnecessary plural --- .../marketplace/genai/mendix-cloud-genai/navigate_mxgenai.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/content/en/docs/marketplace/genai/mendix-cloud-genai/navigate_mxgenai.md b/content/en/docs/marketplace/genai/mendix-cloud-genai/navigate_mxgenai.md index 6e677149557..f45b4bfbeca 100644 --- a/content/en/docs/marketplace/genai/mendix-cloud-genai/navigate_mxgenai.md +++ b/content/en/docs/marketplace/genai/mendix-cloud-genai/navigate_mxgenai.md @@ -85,7 +85,7 @@ When you select the **Add Files Like .TXT or .PDF** option, you can upload docum {{% alert color="info" %}} Only TXT and PDF files are supported. {{% /alert %}} -Before the upload, you can decide for yourself, whether to upload data to a new, the default or a different existing collection inside of the resource. A Knowledge Base resource can comprise several collections. Each collection is specifically designed to hold numerous documents, serving as a logical grouping for related information based on their shared domain, purpose, or thematic focus. While collections provide a mechanism for data separation—with each corresponding to a [GenAICommons.DeployedKnowledgebases](/appstore/modules/genai-commons/#deployed-knowledge-base) — it is not best practice to create a large number of collections within a single Knowledge Base resource. A more performant and practical approach for achieving fine-grained data separation is through the strategic use of metadata. +Before the upload, you can decide for yourself, whether to upload data to a new, the default or a different existing collection inside of the resource. A Knowledge Base resource can comprise several collections. Each collection is specifically designed to hold numerous documents, serving as a logical grouping for related information based on their shared domain, purpose, or thematic focus. While collections provide a mechanism for data separation—with each corresponding to a [GenAICommons.DeployedKnowledgebase](/appstore/modules/genai-commons/#deployed-knowledge-base) — it is not best practice to create a large number of collections within a single Knowledge Base resource. A more performant and practical approach for achieving fine-grained data separation is through the strategic use of metadata. ##### Metadata {#metadata} From 2961e140c34e1553322790de4207a8a60b5d0c0d Mon Sep 17 00:00:00 2001 From: linaaaf <90840263+linaaaf@users.noreply.github.com> Date: Fri, 29 Aug 2025 17:02:59 +0200 Subject: [PATCH 08/12] Update Mx GenAI Connector.md edited section about architecture of knowledge base resources --- .../marketplace/genai/mendix-cloud-genai/Mx GenAI Connector.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/content/en/docs/marketplace/genai/mendix-cloud-genai/Mx GenAI Connector.md b/content/en/docs/marketplace/genai/mendix-cloud-genai/Mx GenAI Connector.md index 0022340a0cb..c03cddf62f7 100644 --- a/content/en/docs/marketplace/genai/mendix-cloud-genai/Mx GenAI Connector.md +++ b/content/en/docs/marketplace/genai/mendix-cloud-genai/Mx GenAI Connector.md @@ -44,7 +44,7 @@ Knowledge bases are often used for: If you are looking for a step-by-step guide on how to get your application data into a Mendix Cloud Knowledge Base, refer [Grounding Your Large Language Model in Data – Mendix Cloud GenAI](/appstore/modules/genai/how-to/howto-groundllm/). Note that the Mendix Portal also provides options for importing data into your knowledge base, such as file uploads. For more information, see [Navigate through the Mendix Cloud GenAI Portal](/appstore/modules/genai/mx-cloud-genai/Navigate-MxGenAI/). This documentation focuses solely on adding data from an application using the connector. ##### Architecture -Each Knowledge Base resource may exist out of several collections where each collection corresponds to a [GenAICommons.DeployedKnowledgebase](/appstore/modules/genai-commons/#deployed-knowledge-base). This offers a way of data separation into different objects, one object per collection. However, adding a large number of collections to the same knowledge base resource is not a best practice. Separation can also be achieved in a more performant and practical way through the addition of metadata. You can read more about this below, in the section about [Retrieve and Generate](/appstore/modules/genai/MxGenAI/#retrieve-and-generate). +A Knowledge Base resource can comprise several collections. Each collection is specifically designed to hold numerous documents, serving as a logical grouping for related information based on their shared domain, purpose, or thematic focus. While collections provide a mechanism for data separation—with each corresponding to a [GenAICommons.DeployedKnowledgebase](/appstore/modules/genai-commons/#deployed-knowledge-base) — it is not best practice to create a large number of collections within a single Knowledge Base resource. A more performant and practical approach for achieving fine-grained data separation is through the strategic use of metadata. You can learn about this in [Retrieve and Generate](/appstore/modules/genai/MxGenAI/#retrieve-and-generate). #### Embeddings From 47ede0df444c2449a69563f2923d915ff6b416d8 Mon Sep 17 00:00:00 2001 From: linaaaf <90840263+linaaaf@users.noreply.github.com> Date: Wed, 3 Sep 2025 13:13:11 +0200 Subject: [PATCH 09/12] Update mendix-cloud-grp.md - added Claude Sonnet 3.7 model --- .../genai/mendix-cloud-genai/mendix-cloud-grp.md | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/content/en/docs/marketplace/genai/mendix-cloud-genai/mendix-cloud-grp.md b/content/en/docs/marketplace/genai/mendix-cloud-genai/mendix-cloud-grp.md index fdbe2167d48..c69c9f3d87b 100644 --- a/content/en/docs/marketplace/genai/mendix-cloud-genai/mendix-cloud-grp.md +++ b/content/en/docs/marketplace/genai/mendix-cloud-genai/mendix-cloud-grp.md @@ -28,7 +28,8 @@ Mendix Cloud Model Resource Packs provide customers with a monthly quota of inpu The Mendix Cloud GenAI Resource Packs provide access to the following models: -* Anthropic Claude v3.5 Sonnet v1 +* Anthropic Claude 3.5 Sonnet v1 +* Anthropic Claude 3.7 Sonnet (Cross-Region Inference Profile) * Cohere Embed v3 (English & multilingual options) The models are available through the Mendix Cloud, leveraging AWS's highly secure Amazon Bedrock multi-tenant architecture. This architecture employs advanced logical isolation techniques to effectively segregate customer data, requests, and responses, ensuring a level of data protection that aligns with global security compliance requirements. Customer prompts, requests, and responses are neither stored nor used for model training. Your data remains your data. @@ -39,8 +40,8 @@ Customers looking to leverage other models in addition to the above can also tak | GenAI Model Resource Pack Plan | S | M | L | | ------------------------------------------ | ----------------- | ----------------- | ----------------- | -| Anthropic Claude V3.5 (Tokens in/month) | 2.5 million in | 5 million | 10 million | -| Anthropic Claude V3.5 (Tokens out/month) | 1.25 million out | 2.5 million | 5 million | +| Anthropic Claude (any version) (Tokens in/month) | 2.5 million in | 5 million | 10 million | +| Anthropic Claude (any version) (Tokens out/month) | 1.25 million out | 2.5 million | 5 million | | Cohere Embed V3 (Tokens in/month) | 5 million in | 10 million | 20 million | ## Knowledge Bases From a70b6cdd237d34d69fdf53b64a3709fedbeb991a Mon Sep 17 00:00:00 2001 From: linaaaf <90840263+linaaaf@users.noreply.github.com> Date: Thu, 4 Sep 2025 08:35:07 +0200 Subject: [PATCH 10/12] Update Mx GenAI Connector.md applied feedback --- .../mendix-cloud-genai/Mx GenAI Connector.md | 42 ++++++++++--------- 1 file changed, 23 insertions(+), 19 deletions(-) diff --git a/content/en/docs/marketplace/genai/mendix-cloud-genai/Mx GenAI Connector.md b/content/en/docs/marketplace/genai/mendix-cloud-genai/Mx GenAI Connector.md index c03cddf62f7..8135f10d5f6 100644 --- a/content/en/docs/marketplace/genai/mendix-cloud-genai/Mx GenAI Connector.md +++ b/content/en/docs/marketplace/genai/mendix-cloud-genai/Mx GenAI Connector.md @@ -10,11 +10,11 @@ aliases: ## Introduction -The [Mendix Cloud GenAI connector](https://marketplace.mendix.com/link/component/239449) 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. Feel free to contact [genai-resource-packs@mendix.com](mailto:genai-resource-packs@mendix.com) to learn more. +The [Mendix Cloud GenAI connector](https://marketplace.mendix.com/link/component/239449) 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. ### Typical Use Cases -The Mendix Cloud GenAI Connector is commonly used for text generation, embeddings, and knowledge bases. These use cases are described in more detail below: +The Mendix Cloud GenAI Connector is commonly used for text generation, embeddings generation, and knowledge bases. These use cases are described in more detail below: #### Text Generation @@ -31,22 +31,8 @@ The Mendix Cloud GenAI Connector is commonly used for text generation, embedding * Translate languages * Simulate characters for games * Image to text - -#### Knowledge Base - -The module enables tailoring generated responses to specific contexts by grounding them in data inside of a collection belonging to a Mendix Cloud GenAI knowledge base resource. This allows for the secure use of private company data or other non-public information when interacting with GenAI models within the Mendix app. It provides a low-code solution to store discrete data (commonly called chunks) in the knowledge base and retrieves relevant information for end-user actions or application processes. - -Knowledge bases are often used for: - -1. [Retrieval Augmented Generation (RAG)](/appstore/modules/genai/rag/) retrieves relevant knowledge from the knowledge base, incorporates it into a prompt, and sends it to the model to generate a response. -2. Semantic search enables advanced search capabilities by considering the semantic meaning of the text, going beyond exact and approximate matching. It allows the knowledge base to be searched for similar chunks effectively. - -If you are looking for a step-by-step guide on how to get your application data into a Mendix Cloud Knowledge Base, refer [Grounding Your Large Language Model in Data – Mendix Cloud GenAI](/appstore/modules/genai/how-to/howto-groundllm/). Note that the Mendix Portal also provides options for importing data into your knowledge base, such as file uploads. For more information, see [Navigate through the Mendix Cloud GenAI Portal](/appstore/modules/genai/mx-cloud-genai/Navigate-MxGenAI/). This documentation focuses solely on adding data from an application using the connector. - -##### Architecture -A Knowledge Base resource can comprise several collections. Each collection is specifically designed to hold numerous documents, serving as a logical grouping for related information based on their shared domain, purpose, or thematic focus. While collections provide a mechanism for data separation—with each corresponding to a [GenAICommons.DeployedKnowledgebase](/appstore/modules/genai-commons/#deployed-knowledge-base) — it is not best practice to create a large number of collections within a single Knowledge Base resource. A more performant and practical approach for achieving fine-grained data separation is through the strategic use of metadata. You can learn about this in [Retrieve and Generate](/appstore/modules/genai/MxGenAI/#retrieve-and-generate). - -#### Embeddings + +#### Embeddings generation Convert strings into vector embeddings for various purposes based on the relatedness of texts. @@ -62,9 +48,27 @@ Embeddings are commonly used for the following: You can combine embeddings with text generation capabilities and leverage specific sources of information to create a smart chat functionality tailored to your knowledge base. {{% alert color="info" %}} -The Mendix Cloud GenAI Connector module generates embeddings internally when interacting with the knowledge base. Pure embedding operations are only required if additional processes, such as using the generated vectors instead of text, are needed. For example, a similar search algorithm could use vector distances to calculate relatedness. +The Mendix Cloud GenAI Connector module generates embeddings internally when interacting with a knowledge base. Pure embedding operations are only required if additional processes, such as using the generated vectors instead of text, are needed. For example, a similar search algorithm could use vector distances to calculate relatedness. {{% /alert %}} + + +#### Knowledge Base + +The module enables tailoring generated responses to specific contexts by grounding them in data inside of a collection belonging to a Mendix Cloud GenAI knowledge base resource. This allows for the secure use of private company data or other non-public information when interacting with GenAI models within the Mendix app. It provides a low-code solution to store discrete data (commonly called chunks) in the knowledge base and retrieves relevant information for end-user actions or application processes. + +Knowledge bases are often used for: + +1. [Retrieval Augmented Generation (RAG)](/appstore/modules/genai/rag/) retrieves relevant knowledge from the knowledge base, incorporates it into a prompt, and sends it to the model to generate a response. +2. Semantic search enables advanced search capabilities by considering the semantic meaning of the text, going beyond exact and approximate matching. It allows the knowledge base to be searched for similar chunks effectively. + +If you are looking for a step-by-step guide on how to get your application data into a Mendix Cloud Knowledge Base, refer [Grounding Your Large Language Model in Data – Mendix Cloud GenAI](/appstore/modules/genai/how-to/howto-groundllm/). Note that the Mendix Portal also provides options for importing data into your knowledge base, such as file uploads. For more information, see [Navigate through the Mendix Cloud GenAI Portal](/appstore/modules/genai/mx-cloud-genai/Navigate-MxGenAI/). This documentation focuses solely on adding data from an application using the connector. + +##### Architecture +A Knowledge Base resource can comprise several collections. Each collection is specifically designed to hold numerous documents, serving as a logical grouping for related information based on their shared domain, purpose, or thematic focus. While collections provide a mechanism for data separation—with each corresponding to a [GenAICommons.DeployedKnowledgebase](/appstore/modules/genai-commons/#deployed-knowledge-base) — it is not best practice to create a large number of collections within a single Knowledge Base resource. A more performant and practical approach for achieving fine-grained data separation is through the strategic use of metadata. You can learn about this in [Retrieve and Generate](/appstore/modules/genai/MxGenAI/#retrieve-and-generate). + + + ### Features In the current version, Mendix supports text generation (including function/tool calling, chat with images, and chat with documents), vector embedding generation, knowledge base storage, and retrieval of knowledge base chunks. From a111bacded9aaced8d2579a260e7ee7c454ef41a Mon Sep 17 00:00:00 2001 From: linaaaf <90840263+linaaaf@users.noreply.github.com> Date: Thu, 4 Sep 2025 08:37:25 +0200 Subject: [PATCH 11/12] Update mendix-cloud-grp.md - applied feedback --- .../marketplace/genai/mendix-cloud-genai/mendix-cloud-grp.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/content/en/docs/marketplace/genai/mendix-cloud-genai/mendix-cloud-grp.md b/content/en/docs/marketplace/genai/mendix-cloud-genai/mendix-cloud-grp.md index c69c9f3d87b..50954f4523a 100644 --- a/content/en/docs/marketplace/genai/mendix-cloud-genai/mendix-cloud-grp.md +++ b/content/en/docs/marketplace/genai/mendix-cloud-genai/mendix-cloud-grp.md @@ -76,8 +76,8 @@ The Mendix Portal allows easy access to manage the resources, through the GenAI ## Mendix Cloud GenAI Connector -The [Mendix Cloud GenAI connector](/appstore/modules/genai/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. Please make sure to use no older versions of this connector as -* contained in GenAI for Mendix bundle v2.4.1 (Mendix 9) or +The [Mendix Cloud GenAI connector](/appstore/modules/genai/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. Please note that versions older than the ones listed below do no longer work: +* 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 * Mendix Cloud GenAI connector v4.4.0 (DeployedKnowledgeBase support). From 2d5df5ca56681ee2db9d751e950ad04d8e238081 Mon Sep 17 00:00:00 2001 From: Karuna-Mendix Date: Fri, 5 Sep 2025 11:12:38 +0530 Subject: [PATCH 12/12] TW Review --- .../genai/mendix-cloud-genai/Mx GenAI Connector.md | 7 ++----- .../genai/mendix-cloud-genai/mendix-cloud-grp.md | 13 +++++++------ .../genai/mendix-cloud-genai/navigate_mxgenai.md | 2 +- 3 files changed, 10 insertions(+), 12 deletions(-) diff --git a/content/en/docs/marketplace/genai/mendix-cloud-genai/Mx GenAI Connector.md b/content/en/docs/marketplace/genai/mendix-cloud-genai/Mx GenAI Connector.md index 8135f10d5f6..9a96888fc3b 100644 --- a/content/en/docs/marketplace/genai/mendix-cloud-genai/Mx GenAI Connector.md +++ b/content/en/docs/marketplace/genai/mendix-cloud-genai/Mx GenAI Connector.md @@ -32,7 +32,7 @@ The Mendix Cloud GenAI Connector is commonly used for text generation, embedding * Simulate characters for games * Image to text -#### Embeddings generation +#### Embeddings Generation Convert strings into vector embeddings for various purposes based on the relatedness of texts. @@ -51,8 +51,6 @@ You can combine embeddings with text generation capabilities and leverage specif The Mendix Cloud GenAI Connector module generates embeddings internally when interacting with a knowledge base. Pure embedding operations are only required if additional processes, such as using the generated vectors instead of text, are needed. For example, a similar search algorithm could use vector distances to calculate relatedness. {{% /alert %}} - - #### Knowledge Base The module enables tailoring generated responses to specific contexts by grounding them in data inside of a collection belonging to a Mendix Cloud GenAI knowledge base resource. This allows for the secure use of private company data or other non-public information when interacting with GenAI models within the Mendix app. It provides a low-code solution to store discrete data (commonly called chunks) in the knowledge base and retrieves relevant information for end-user actions or application processes. @@ -65,9 +63,8 @@ Knowledge bases are often used for: If you are looking for a step-by-step guide on how to get your application data into a Mendix Cloud Knowledge Base, refer [Grounding Your Large Language Model in Data – Mendix Cloud GenAI](/appstore/modules/genai/how-to/howto-groundllm/). Note that the Mendix Portal also provides options for importing data into your knowledge base, such as file uploads. For more information, see [Navigate through the Mendix Cloud GenAI Portal](/appstore/modules/genai/mx-cloud-genai/Navigate-MxGenAI/). This documentation focuses solely on adding data from an application using the connector. ##### Architecture -A Knowledge Base resource can comprise several collections. Each collection is specifically designed to hold numerous documents, serving as a logical grouping for related information based on their shared domain, purpose, or thematic focus. While collections provide a mechanism for data separation—with each corresponding to a [GenAICommons.DeployedKnowledgebase](/appstore/modules/genai-commons/#deployed-knowledge-base) — it is not best practice to create a large number of collections within a single Knowledge Base resource. A more performant and practical approach for achieving fine-grained data separation is through the strategic use of metadata. You can learn about this in [Retrieve and Generate](/appstore/modules/genai/MxGenAI/#retrieve-and-generate). - +A Knowledge Base resource can comprise several collections. Each collection is specifically designed to hold numerous documents, serving as a logical grouping for related information based on its shared domain, purpose, or thematic focus. While collections provide a mechanism for data separation, with each corresponding to a [DeployedKnowledgebase](/appstore/modules/genai/genai-for-mx/commons/#deployed-knowledge-base), it is not best practice to create a large number of collections within a single Knowledge Base resource. A more performant and practical approach for achieving fine-grained data separation is through the strategic use of metadata. To learn more, see [Retrieve and Generate](/appstore/modules/genai/mx-cloud-genai/MxGenAI-connector/#retrieve-and-generate). ### Features diff --git a/content/en/docs/marketplace/genai/mendix-cloud-genai/mendix-cloud-grp.md b/content/en/docs/marketplace/genai/mendix-cloud-genai/mendix-cloud-grp.md index 50954f4523a..d0c74985ba6 100644 --- a/content/en/docs/marketplace/genai/mendix-cloud-genai/mendix-cloud-grp.md +++ b/content/en/docs/marketplace/genai/mendix-cloud-genai/mendix-cloud-grp.md @@ -24,13 +24,13 @@ Mendix Cloud GenAI Resource Packs is a premium Mendix product that requires an a 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. -### Supported models +### Supported Models The Mendix Cloud GenAI Resource Packs provide access to the following models: * Anthropic Claude 3.5 Sonnet v1 -* Anthropic Claude 3.7 Sonnet (Cross-Region Inference Profile) -* Cohere Embed v3 (English & multilingual options) +* Anthropic Claude 3.7 Sonnet (Cross-region inference profile) +* Cohere Embed v3 (English and multilingual options) The models are available through the Mendix Cloud, leveraging AWS's highly secure Amazon Bedrock multi-tenant architecture. This architecture employs advanced logical isolation techniques to effectively segregate customer data, requests, and responses, ensuring a level of data protection that aligns with global security compliance requirements. Customer prompts, requests, and responses are neither stored nor used for model training. Your data remains your data. @@ -76,10 +76,11 @@ The Mendix Portal allows easy access to manage the resources, through the GenAI ## Mendix Cloud GenAI Connector -The [Mendix Cloud GenAI connector](/appstore/modules/genai/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. Please note that versions older than the ones listed below do no longer work: +The [Mendix Cloud GenAI connector](/appstore/modules/genai/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: + * 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 -* Mendix Cloud GenAI connector v4.4.0 (DeployedKnowledgeBase support). +* Mendix Cloud GenAI connector v3.1.1 (no `DeployedKnowledgeBase` support) or +* Mendix Cloud GenAI connector v4.4.0 (`DeployedKnowledgeBase` support). ## Regional Availability diff --git a/content/en/docs/marketplace/genai/mendix-cloud-genai/navigate_mxgenai.md b/content/en/docs/marketplace/genai/mendix-cloud-genai/navigate_mxgenai.md index f45b4bfbeca..da7c5ca3c27 100644 --- a/content/en/docs/marketplace/genai/mendix-cloud-genai/navigate_mxgenai.md +++ b/content/en/docs/marketplace/genai/mendix-cloud-genai/navigate_mxgenai.md @@ -85,7 +85,7 @@ When you select the **Add Files Like .TXT or .PDF** option, you can upload docum {{% alert color="info" %}} Only TXT and PDF files are supported. {{% /alert %}} -Before the upload, you can decide for yourself, whether to upload data to a new, the default or a different existing collection inside of the resource. A Knowledge Base resource can comprise several collections. Each collection is specifically designed to hold numerous documents, serving as a logical grouping for related information based on their shared domain, purpose, or thematic focus. While collections provide a mechanism for data separation—with each corresponding to a [GenAICommons.DeployedKnowledgebase](/appstore/modules/genai-commons/#deployed-knowledge-base) — it is not best practice to create a large number of collections within a single Knowledge Base resource. A more performant and practical approach for achieving fine-grained data separation is through the strategic use of metadata. +Before uploading, you can choose to upload the data to a new collection, the default collection, or another existing collection within the resource. A Knowledge Base resource can comprise several collections. Each collection is specifically designed to hold numerous documents, serving as a logical grouping for related information based on its shared domain, purpose, or thematic focus. While collections provide a mechanism for data separation, with each corresponding to a [DeployedKnowledgebase](/appstore/modules/genai/genai-for-mx/commons/#deployed-knowledge-base), it is not best practice to create a large number of collections within a single Knowledge Base resource. A more performant and practical approach for achieving fine-grained data separation is through the strategic use of metadata. ##### Metadata {#metadata}