onedevatlasBeta
Browse the atlas
AllCAPBTPUI5ABAP
SampleSampletypeA worked example you read or clone. Evidence: it demonstrates, it never provides.See every one →What this type is →by SAPby SAPoriginPublished by SAP itself. A visible facet, never an input to a reading — a dormant official plugin reads exactly like a dormant independent one.See every one →Reference

SAP BTP AI Best Practice Demo - Vector Embedding (RAG) - CAP

A CAP backend-sample and fullstack-sample that parse an uploaded CSV of science data, embed each row through SAP AI Core and store the vectors in SAP HANA Cloud's vector store.

uploadScienceData parses an uploaded CSV of science data and creates the embeddings through SAP AI Core's Generative AI Hub, in the logic srv/services/ai-sdk.ts holds; the vectors go into the schema.cds entity the sample deploys to an HDI container in SAP HANA Cloud, and scienceData reads the stored rows back. The fullstack-sample adds a UI5 app, manage-science-data, together with a launchpad configuration and an approuter for local testing, on top of the same service. Building that container is a step of its own before a run, npm run build:db, beside the cds bind for the SAP AI Core instance.

GitHub68 ★

Facts

Last pushLicenceApache-2.0

Where it sits

Lives in
CAP
Demonstrates
Retrieval-augmented generationCAPBTPRetrieval-augmented generationcapabilityGrounding a model's answer in data retrieved at question time: text split into chunks, each chunk embedded as a vector, and the chunks nearest to the question placed into the prompt. Semantic search is the same retrieval with a person reading the matches, and fine-tuning changes the model's weights, not its input.
Serves
BTP/BAIP
Flavors
Node.js
Requires
SAP AI CoreSAP AI CoreartifactThe service instance the samples bind to at runtime to create the embeddings for each uploaded row.SAP HANA CloudSAP HANA CloudartifactWhere the embeddings are stored: the sample's schema is built into an HDI container by its own build:db step before the service can read or write vectors.

Who is behind it

SAP SamplesSAP SamplesOrganisationMaintains this
In the atlas: maintains 222@SAP-samplesmaintainerLuís MarquesPersonContributes to this
In the atlas: contributes to 8@luismarques-io1 contributor

Before choosing this

Conditions

PracticalFunctional boundary

Every CDS service in both samples is marked @requires: 'any' and left publicly accessible, which the README says simplifies the testing and deployment process, and it asks for proper authentication mechanisms to be applied in their place.

What it declares

Every artifact

Type
Sample
Origin
By SAP
Use as
A reference
Runtime
Node.js

As a sample

Form
A reference application

Connections5

Download
SAP BTP AI Best Practice Demo - Vector Embedding (RAG) - CAP connectionsSAP BTP AI Best PracticeDemo - Vector Embedding(RAG) - CAPPROVIDES→ demonstrates1demonstrates authoredRetrieval-augmented generationNEEDS→ connects to2connects to stated Each uploaded row, sent to an embeddings model, and the vector that comes back. SAP-samples/sap-btp-ai-best-practices — vector-rag-embedding/cap/backend-sample README, configuration: https://raw.githubusercontent.com/SAP-samples/sap-btp-ai-best-practices/main/best-practices/generative-ai/vector-rag-embedding/cap/backend-sample/README.md SAP-samples/sap-btp-ai-best-practices — vector-rag-embedding/cap/backend-sample README: https://raw.githubusercontent.com/SAP-samples/sap-btp-ai-best-practices/main/best-practices/generative-ai/vector-rag-embedding/cap/backend-sample/README.mdSAP AI Coreconnects to stated The embeddings the service writes to the vector store, and the stored rows `scienceData` reads back. SAP-samples/sap-btp-ai-best-practices — vector-rag-embedding/cap/backend-sample README: https://raw.githubusercontent.com/SAP-samples/sap-btp-ai-best-practices/main/best-practices/generative-ai/vector-rag-embedding/cap/backend-sample/README.md SAP-samples/sap-btp-ai-best-practices — vector-rag-embedding/cap/backend-sample README, project structure: https://raw.githubusercontent.com/SAP-samples/sap-btp-ai-best-practices/main/best-practices/generative-ai/vector-rag-embedding/cap/backend-sample/README.mdSAP HANA Cloud→ needs2needs stated The service instance the samples bind to at runtime to create the embeddings for each uploaded row. SAP-samples/sap-btp-ai-best-practices — vector-rag-embedding/cap/backend-sample README: https://raw.githubusercontent.com/SAP-samples/sap-btp-ai-best-practices/main/best-practices/generative-ai/vector-rag-embedding/cap/backend-sample/README.mdSAP AI Coreneeds stated Where the embeddings are stored: the sample's schema is built into an HDI container by its own `build:db` step before the service can read or write vectors. SAP-samples/sap-btp-ai-best-practices — vector-rag-embedding/cap/backend-sample README, local deployment: https://raw.githubusercontent.com/SAP-samples/sap-btp-ai-best-practices/main/best-practices/generative-ai/vector-rag-embedding/cap/backend-sample/README.mdSAP HANA Cloud

README

quoted from SAP-samples/sap-btp-ai-best-practices under Apache-2.0, read
SAP-samples/sap-btp-ai-best-practices/best-practices/generative-ai/vector-rag-embedding/cap/README.mdOn GitHub

CAP Implementations for Generative AI Access

This directory contains Cloud Application Programming (CAP) model implementations that demonstrate best practices for accessing Embeddings models using the SAP GenAI Hub and storing them in SAP HANA Vector Store. It provides examples of different ways to create and store embeddings in the vector store.

Available Samples

Overview

These samples showcase how to:

  • Connect to generative AI services from CAP applications
  • Structure service layers for AI orchestration
  • Implement proper error handling
  • Deploy applications to SAP BTP

Getting Started

Each subdirectory contains a comprehensive README.md with detailed setup instructions, deployment guides, and usage examples.

Apache-2.0, read

Details

Sources3
Added by handdiscovered herechecked
github.com/SAP-samples/sap-btp-ai-best-practices/tree/main/best-practices/generative-ai/vector-rag-embedding/captree, pushes, contributors, CIchecked
best-practices/generative-ai/vector-rag-embedding/cap/README.mdquoted, and what the entry declareschecked

Sources are graph entities: the same page may back several entries, and an unreachable source flags every row that rests on it.

Compatibility and provenance
runtimesnode
discovered viaAdded by hand
first seen in the atlas
ecosystem and domaincap, ai-and-agents
Flavors1
Contributors1
Luís Marques

From the repository’s contributor list, .

History in the atlas1
  1. First seen.
For your agent
Ref
artifact:sap-samples-btp-ai-bp-vector-rag-embedding-cap
JSON
/artifacts/sap-samples-btp-ai-bp-vector-rag-embedding-cap.json
MCP
Connecting an agent