{"ref":"content:ac-generative-ai-on-sap-btp","page":"/content/ac-generative-ai-on-sap-btp","json":"/content/ac-generative-ai-on-sap-btp.json","generated":"2026-10-26","drafted_with_ai":true,"entity":{"id":"ac-generative-ai-on-sap-btp","title":"Generative AI on SAP BTP","url":"https://architecture.learning.sap.com/docs/ref-arch/39eb58","content_type":"reference-architecture","explains":[{"ref":"capability:llm-integration","applies_to":{"ecosystems":["btp","cap"]}},{"ref":"capability:retrieval-augmented-generation","applies_to":{"ecosystems":["btp","cap"]}}],"parts":[{"actor":"User","key":"user","role":"interacts with the application through the user interface and submits prompts","sources":[{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/1-basics/readme.md","title":"RA0005 1-basics/readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"In this architecture, the Cloud Application Programming (CAP) model serves as the central point for managing application logic and sending prompts, either through well-designed, integrated prompt templates within the application itself or via a user interface like SAPUI5 for end-user interaction."},{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/3-retrieval-augmented-generation/readme.md","title":"RA0005 3-retrieval-augmented-generation/readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"The user submits a question or prompt, which is transformed into a dense vector (embedding) by an embedding model."}]},{"ref":"artifact:sap-cds","key":"cap","role":"central hub for application and domain logic","area":"btp","sources":[{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"In the provided Reference Architecture, CAP serves as the central hub for application and domain logic, interacting with SAP solutions (Cloud or On-Premise), 3rd party applications, and managing data sources such as SAP HANA Cloud."},{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/1-basics/readme.md","title":"RA0005 1-basics/readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"In this architecture, the Cloud Application Programming (CAP) model serves as the central point for managing application logic and sending prompts, either through well-designed, integrated prompt templates within the application itself or via a user interface like SAPUI5 for end-user interaction."},{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/2-semantic-search/readme.md","title":"RA0005 2-semantic-search/readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"CAP natively supports embeddings as part of its data schema, allowing for seamless integration of vector representations."}]},{"ref":"artifact:btp-hana-cloud","key":"hana","role":"stores data and embeddings for similarity search through its Vector Engine","area":"btp","sources":[{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"At its core, this reference architecture features a [CAP](#sap-cloud-application-programming-model)-based backend to manage application logic, SAP HANA Cloud for storing data, including embeddings to facilitate similarity search with the power of its [Vector Engine](#vector-engine), and the [Generative AI Hub](#generative-ai-hub) as the central access point to Foundation Models and Large Language Models (LLMs)."},{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/2-semantic-search/readme.md","title":"RA0005 2-semantic-search/readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"These vectors are then stored and indexed within SAP HANA Cloud's [Vector Engine](../readme.md#vector-engine), enabling fast similarity searches through methods like cosine similarity."}]},{"ref":"artifact:btp-ai-core","key":"aicore","role":"Generative AI Hub: central access point to foundation models, with orchestration and grounding","area":"btp","sources":[{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"At its core, this reference architecture features a [CAP](#sap-cloud-application-programming-model)-based backend to manage application logic, SAP HANA Cloud for storing data, including embeddings to facilitate similarity search with the power of its [Vector Engine](#vector-engine), and the [Generative AI Hub](#generative-ai-hub) as the central access point to Foundation Models and Large Language Models (LLMs)."},{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"The [Generative AI Hub](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/generative-ai-hub-in-sap-ai-core) incorporates Generative AI into your AI activities in [SAP AI Core](https://discovery-center.cloud.sap/serviceCatalog/sap-ai-core?region=all) and [SAP AI Launchpad](https://discovery-center.cloud.sap/serviceCatalog/sap-ai-launchpad?region=all)."},{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"An important feature of the Generative AI Hub is [Orchestration](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/orchestration), which combines content generation via an [Harmonized API](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/harmonized-api) with essential functions often required in business AI scenarios."},{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/3-retrieval-augmented-generation/readme.md","title":"RA0005 3-retrieval-augmented-generation/readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"[SAP’s Orchestration Workflow](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/orchestration-workflow) contains a [Grounding module](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/grounding) which provides specialized data retrieval through vector databases."}]},{"ref":"artifact:btp-ai-launchpad","key":"launchpad","role":"manages AI use cases across AI runtimes","area":"btp","sources":[{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"The [Generative AI Hub](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/generative-ai-hub-in-sap-ai-core) incorporates Generative AI into your AI activities in [SAP AI Core](https://discovery-center.cloud.sap/serviceCatalog/sap-ai-core?region=all) and [SAP AI Launchpad](https://discovery-center.cloud.sap/serviceCatalog/sap-ai-launchpad?region=all)."},{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"Customers and partners can use SAP AI Launchpad to manage AI use cases (scenarios) across multiple instances of AI runtimes (such as SAP AI Core)."}]},{"ref":"artifact:cap-llm-plugin","key":"cap-llm-plugin","role":"plugin within the application logic for Generative AI solutions","area":"btp","sources":[{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"Within the application logic, various plugins (e.g., [CAP LLM Plugin](https://www.npmjs.com/package/cap-llm-plugin)) and SDKs like SAP Cloud SDK for AI ([JavaScript/TypeScript](https://github.com/SAP/ai-sdk-js) or [Java](https://github.com/SAP/ai-sdk-java)) can be utilized to support the development of Generative AI solutions - also together with [LangChain](https://www.langchain.com/)."},{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/3-retrieval-augmented-generation/readme.md","title":"RA0005 3-retrieval-augmented-generation/readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"Custom CAP based application can benefit from the CAP LLM Plugin for efficient and faster development."},{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/3-retrieval-augmented-generation/readme.md","title":"RA0005 3-retrieval-augmented-generation/readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"The CAP LLM Plugin also supports anonymization."}]},{"ref":"artifact:sap-ai-sdk-foundation-models","key":"ai-sdk","role":"SDK within the application logic for the Generative AI Hub and the Vector Engine","area":"btp","sources":[{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"Within the application logic, various plugins (e.g., [CAP LLM Plugin](https://www.npmjs.com/package/cap-llm-plugin)) and SDKs like SAP Cloud SDK for AI ([JavaScript/TypeScript](https://github.com/SAP/ai-sdk-js) or [Java](https://github.com/SAP/ai-sdk-java)) can be utilized to support the development of Generative AI solutions - also together with [LangChain](https://www.langchain.com/)."},{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/2-semantic-search/readme.md","title":"RA0005 2-semantic-search/readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"Additionally, various SDKs and plugins, such as the [SAP Cloud SDK (for AI)](https://github.com/SAP/ai-sdk-js), [CAP LLM Plugin](https://github.com/SAP-samples/cap-llm-plugin-samples) and [LangChain](https://www.langchain.com/), enhance the embedding process and streamline integration with both, the Generative AI Hub and the Vector Engine."}]},{"ref":"artifact:sap-ai-sdk-orchestration","key":"ai-sdk-orchestration","role":"SDK client for the orchestration configuration","area":"btp","sources":[{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"However, details for each module can be configured, and optional modules can be omitted by including an orchestration configuration in JSON format with the request body or even easier leveraging the [SAP Cloud SDK for AI](https://sap.github.io/ai-sdk/)."},{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/1-basics/readme.md","title":"RA0005 1-basics/readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"The [Orchestration Service](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/orchestration) provides a harmonized API for content generation (e.g., LLM completions) and includes key functionalities such as prompt templating and content filtering, making it even easier and more efficient to work with these models."}]},{"ref":"artifact:btp-cloud-foundry-runtime","key":"cf","role":"runtime","area":"btp","paths":["cloud-foundry"],"sources":[{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"This architecture accommodates both Cloud Foundry and Kyma runtimes, ensuring adaptability in leveraging GenAI within SAP BTP applications."},{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"[SAP BTP, Cloud Foundry Runtime](https://discovery-center.cloud.sap/serviceCatalog/cloud-foundry-runtime?region=all) lets you develop polyglot cloud-native applications and run them on the SAP BTP Cloud Foundry environment."}]},{"ref":"artifact:btp-kyma-runtime","key":"kyma","role":"runtime","area":"btp","paths":["kyma"],"sources":[{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"This architecture accommodates both Cloud Foundry and Kyma runtimes, ensuring adaptability in leveraging GenAI within SAP BTP applications."},{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"[SAP BTP, Kyma runtime](https://discovery-center.cloud.sap/serviceCatalog/kyma-runtime/?region=all) is a fully managed Kubernetes runtime based on the open-source project \"Kyma\"."}]},{"ref":"artifact:sap-approuter","key":"approuter","role":"consuming application that accesses the HTML5 static content","area":"btp","sources":[{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"In runtime, the service enables the consuming application, typically the application router, to access HTML5 application static content in a secure and efficient manner."}]},{"ref":"artifact:btp-html5-application-repository","key":"html5-repo","role":"central storage of HTML5 applications","area":"btp","sources":[{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"[SAP HTML5 Application Repository Service for SAP BTP](https://discovery-center.cloud.sap/serviceCatalog/html5-application-repository-service?region=all) enables central storage of HTML5 applications on SAP BTP."},{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"In runtime, the service enables the consuming application, typically the application router, to access HTML5 application static content in a secure and efficient manner."}]},{"ref":"artifact:btp-destination","key":"destination","role":"backend destination details","area":"btp","sources":[{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"[SAP Destination service](https://discovery-center.cloud.sap/serviceCatalog/destination?service_plan=lite&region=all&commercialModel=cloud) lets you retrieve the backend destination details you need to configure applications in the Cloud Foundry environment."}]},{"ref":"artifact:btp-authorization-and-trust-management","key":"xsuaa","role":"user authorizations and trust to identity providers","area":"btp","sources":[{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"[SAP Authorization and Trust Management Service](https://discovery-center.cloud.sap/serviceCatalog/authorization-and-trust-management-service?region=all) lets you manage user authorizations and trust to identity providers."}]},{"ref":"artifact:btp-cloud-identity-services","key":"cids","role":"identity provider","sources":[{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"Identity providers are the user base for applications. We recommend that you use the SAP Identity Authentication Service (IAS), an SAP on-premise system, or a custom corporate identity provider."}]},{"ref":"artifact:btp-business-application-studio","key":"bas","role":"development environment","area":"btp","sources":[{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"[SAP Business Application Studio](https://discovery-center.cloud.sap/serviceCatalog/business-application-studio?region=all) (the next generation of SAP Web IDE) is a powerful and modern development environment, tailored for efficient development of business applications for the Intelligent Enterprise."}]},{"ref":"artifact:btp-continuous-integration-and-delivery","key":"cicd","role":"CI/CD pipelines","area":"btp","sources":[{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"[SAP Continuous Integration and Delivery service](https://discovery-center.cloud.sap/serviceCatalog/continuous-integration--delivery?region=all) lets you configure and run predefined continuous integration and delivery (CI/CD) pipelines that automatically build, test, and deploy your code changes to speed up your development and delivery cycles."}]}],"paths":[{"key":"cloud-foundry","name":"On the Cloud Foundry runtime","sources":[{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"This architecture accommodates both Cloud Foundry and Kyma runtimes, ensuring adaptability in leveraging GenAI within SAP BTP applications."},{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"[SAP BTP, Cloud Foundry Runtime](https://discovery-center.cloud.sap/serviceCatalog/cloud-foundry-runtime?region=all) lets you develop polyglot cloud-native applications and run them on the SAP BTP Cloud Foundry environment."}]},{"key":"kyma","name":"On the Kyma runtime","sources":[{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"This architecture accommodates both Cloud Foundry and Kyma runtimes, ensuring adaptability in leveraging GenAI within SAP BTP applications."},{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"[SAP BTP, Kyma runtime](https://discovery-center.cloud.sap/serviceCatalog/kyma-runtime/?region=all) is a fully managed Kubernetes runtime based on the open-source project \"Kyma\"."}]}],"areas":[{"key":"btp","kind":"sap-cloud","label":"SAP BTP","sources":[{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"For applications on SAP Business Technology Platform (SAP BTP) aiming to harness the power of Generative AI, this Reference Architecture provides a comprehensive framework."},{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"This architecture accommodates both Cloud Foundry and Kyma runtimes, ensuring adaptability in leveraging GenAI within SAP BTP applications."}]}],"edges":[{"from":"user","to":"cap","kind":"data","for":"submits a question or prompt through the user interface","sources":[{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/1-basics/readme.md","title":"RA0005 1-basics/readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"In this architecture, the Cloud Application Programming (CAP) model serves as the central point for managing application logic and sending prompts, either through well-designed, integrated prompt templates within the application itself or via a user interface like SAPUI5 for end-user interaction."},{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/3-retrieval-augmented-generation/readme.md","title":"RA0005 3-retrieval-augmented-generation/readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"The user submits a question or prompt, which is transformed into a dense vector (embedding) by an embedding model."}]},{"from":"cap","to":"aicore","kind":"data","for":"sends prompts to the Generative AI Hub via SAP AI Core and its AI API, and converts user inputs into embeddings through it","sources":[{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/1-basics/readme.md","title":"RA0005 1-basics/readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"CAP is connected to the Generative AI Hub via SAP AI Core and its [AI API](https://api.sap.com/api/AI_CORE_API/overview), enabling seamless communication with Foundation Models and Large Language Models (LLMs)."},{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/2-semantic-search/readme.md","title":"RA0005 2-semantic-search/readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"When user inputs are processed, they are converted into embeddings using Embedding Models via the [Generative AI Hub](../readme.md#generative-ai-hub)."}]},{"from":"cap","to":"hana","kind":"data","for":"stores and indexes embeddings in the Vector Engine and retrieves results by similarity search","sources":[{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/2-semantic-search/readme.md","title":"RA0005 2-semantic-search/readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"These vectors are then stored and indexed within SAP HANA Cloud's [Vector Engine](../readme.md#vector-engine), enabling fast similarity searches through methods like cosine similarity."},{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/2-semantic-search/readme.md","title":"RA0005 2-semantic-search/readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"Upon initiating a search, the CAP model communicates with the Vector Engine to retrieve results based on the semantic meaning of the inputs, leading to contextually relevant responses."}]}],"roles":[{"key":"llm-access","name":"Plugins and SDKs within the application logic","capability":"capability:llm-integration","parts":["cap-llm-plugin","ai-sdk","ai-sdk-orchestration"],"sources":[{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"Within the application logic, various plugins (e.g., [CAP LLM Plugin](https://www.npmjs.com/package/cap-llm-plugin)) and SDKs like SAP Cloud SDK for AI ([JavaScript/TypeScript](https://github.com/SAP/ai-sdk-js) or [Java](https://github.com/SAP/ai-sdk-java)) can be utilized to support the development of Generative AI solutions - also together with [LangChain](https://www.langchain.com/)."},{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/1-basics/readme.md","title":"RA0005 1-basics/readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"Furthermore, various SDKs, frameworks, and plugins, such as [SAP Cloud SDK (for AI)](https://github.com/SAP/ai-sdk-js), [LangChain](https://www.langchain.com/), and [CAP LLM Plugin](https://github.com/SAP-samples/cap-llm-plugin-samples), can be leveraged within CAP to not only streamline interactions with the Generative AI Hub but also simplify implementation and enhance robustness by using features like [Output Parsing](https://js.langchain.com/docs/concepts/#output-parsers)."}]},{"key":"hub","part":"aicore"},{"key":"rag","name":"Custom-built RAG on SAP BTP","usecase":"usecase:answer-a-question-from-records-in-a-cap-service","parts":["cap-llm-plugin"],"sources":[{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/3-retrieval-augmented-generation/readme.md","title":"RA0005 3-retrieval-augmented-generation/readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"To leverage these underlying RAG principles, users can choose to either make use of SAP's standardized, use case-specific RAG services, or implement custom-built approaches on SAP BTP."},{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/3-retrieval-augmented-generation/readme.md","title":"RA0005 3-retrieval-augmented-generation/readme.md in SAP/architecture-center","checked":"2026-10-09","quote":"Custom CAP based application can benefit from the CAP LLM Plugin for efficient and faster development."}]}],"summary":"The reference shape for a generative AI application on BTP: a [CAP](artifact:sap-cds) backend, [SAP HANA Cloud](artifact:btp-hana-cloud) holding data and embeddings for similarity search through its vector engine, and the Generative AI Hub in SAP AI Core as the single access point to foundation models. It shows retrieval-augmented generation on that stack and names the CAP plugins and SDKs that connect the pieces, for both Cloud Foundry and Kyma.","short":"Generative AI app on BTP with CAP, HANA Cloud vectors and AI Core","authors":["actor:sap-architecture-center"],"published":"2025-09-02","sources":[{"url":"https://raw.githubusercontent.com/SAP/architecture-center/main/docs/ref-arch/RA0005/readme.md","title":"RA0005 readme.md in SAP/architecture-center — title, contributors and last_update","checked":"2026-09-06"}],"provenance":{"discovered_via":[{"source":"source:architecture-center"}],"first_seen":"2026-09-06"},"drafted_with_ai":true,"history":[{"date":"2026-09-14","field":"capability","from":"capability:retrieval-augmented-generation","to":"capability:retrieval-augmented-generation","reason":"The capability moved to a neutral id when it opened to HANA, BTP and ABAP; the concern and this entry's edge to it are unchanged."},{"date":"2026-10-09","field":"parts","from":null,"to":"17 parts, 3 edges, 1 area","reason":"Filled from SAP's own readmes at the maintainer's request; the AI-native door reads these designs. Every part names what the graph holds; what it lacks is listed as candidates in the curation note."},{"date":"2026-10-09","field":"roles, paths","from":"no roles, no paths","to":"the plugins and SDKs within the application logic typed by LLM integration with the three the source names, the hub fixed, custom-built RAG typed by the CAP use case with the plugin the source names; two ways, one per runtime the readme accommodates","reason":"The readme names the place for plugins and SDKs by example and leaves it open, and the RAG page names SAP's standardized services or a custom-built approach as the choice (docs/concepts/design-roles-and-interfaces.md §3). The three scenario pages are overlapping flows over the same parts, so they are not ways; the two runtimes are."},{"date":"2026-10-17","field":"explains","from":null,"to":"applies_to on capability:llm-integration (cap, btp); capability:retrieval-augmented-generation (cap, btp)","reason":"Door scope proposed from the title and summary, so a door page lists the piece only where it holds (docs/concepts/content-on-doors.md)."}],"published_on":"source:architecture-center"},"readings":{"liveness":[{"label":"Checked against the source","tier":"unknown","evidence":"nobody has checked it"},{"label":"Source reachable","tier":"good","evidence":"up as of 2026-10-26"},{"label":"Source updated","tier":"fair","evidence":"2025-09-02 by the publisher"}],"compatibility":[{"label":"Version","tier":"unknown","evidence":"no version declared"},{"label":"Moved since?","tier":"poor","evidence":"@cap-js/ai 1.0.0, 2026-04 and 1 more"},{"label":"Findings","tier":"good","evidence":"none flagged"}],"reach":[{"value":null,"unit":"views"},{"value":null,"unit":"comments"},{"value":null,"unit":"likes"}]},"signals":{"crawled_at":"2026-10-26","reachable":true,"source_updated":"2025-09-02"},"series":null,"edges":{"authors":[{"ref":"actor:sap-architecture-center","name":"SAP Architecture Center","json":"/actors/sap-architecture-center.json"}]}}