onedevatlasBeta
Browse the atlas
AllCAPUI5ABAPBTP
SampleSampletypeA worked example you read or clone. Evidence: it demonstrates, it never provides.See every one →What this type is →independently maintainedindependently maintainedoriginPublished by one person or a small company outside SAP. Says nothing about quality; the readings say that.See every one →Reference

cap-bp-rag

An event-driven RAG application: Cloud Integration embeds a Business Partner event taken off a broker, and the CAP service stores the vector in SAP HANA Cloud and answers questions from it.

Written as a submission to the May 2026 Developer Challenge, so the README carries an architecture diagram and the two flows and no setup steps. Ingestion is split across two systems: Cloud Integration takes the event off Solace PubSub+, calls OpenAI for an embedding of the text, and posts it to the CAP service's insert API, so the application itself neither subscribes to the broker nor embeds on write. The CDS entity carries textEmbedding: Vector(1536) beside the business partner's fullData and text, and the service exposes BusinessPartners as insert-only and BusinessPartnerViewer as read-only, both without the embedding column. Retrieval sits in two actions on that service: similaritySearch sorts rows by cosine_similarity against to_real_vector of the query embedding, and ask hands the ten nearest to a gpt-4o-mini completion. The integration flow itself ships as an exported zip under cpi/, so what it does is not readable in the repository.

GitHub0 ★

Facts

Last push

Where it sits

Lives in
CAP
Demonstrates
Retrieval-augmented generationCAPRetrieval-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.Event MeshCAPEvent MeshcapabilityEmitting and consuming business events across systems through brokers, including subscriptions and mapping application events to broker topics. Work that must survive a request, including deferred processing and retries, belongs to [async processing](capability:async-processing).
Flavors
Node.jsfrom its runtime
Runs
Cloud Foundry
Requires
SAP HANA CloudSAP HANA Cloudartifactthe vector store: the 1536-dimension embedding column sits there and the similarity search runs there, and the production profile binds the hana database kind

Who is behind it

Mio YasutakeMio YasutakePersonMaintains this
In the atlas: maintains 47, contributes to 47, wrote 10@miyasutamaintainer

Before choosing this

Signals

LicenceNo licenseNeither the package manifest nor the repository tree declares a licence

Without a licence the default is all rights reserved. Ask the maintainer, or check for terms stated elsewhere, before depending on it.

What it declares

Every artifact

Type
Sample
Origin
Independently maintained
Use as
A reference
Runtime
Node.js
Runs on
Cloud Foundry

As a sample

Form
A reference application

Connections5

Download
cap-bp-rag connectionscap-bp-ragPROVIDES→ demonstrates2demonstrates authoredEvent Meshdemonstrates authoredRetrieval-augmented generationNEEDS→ connects to2connects to stated the ingestion side calls in: Cloud Integration posts the Business Partner record with the embedding it created for it miyasuta/cap-bp-rag — README, ingestion flow: https://github.com/miyasuta/cap-bp-ragCloud Integrationconnects to stated writes the embedding of a Business Partner record and reads the nearest rows back for a question miyasuta/cap-bp-rag — README, ingestion flow: https://github.com/miyasuta/cap-bp-rag miyasuta/cap-bp-rag — README, query flow: https://github.com/miyasuta/cap-bp-ragSAP HANA Cloud→ needs1needs declared the vector store: the 1536-dimension embedding column sits there and the similarity search runs there, and the production profile binds the hana database kind miyasuta/cap-bp-rag — README: https://github.com/miyasuta/cap-bp-rag miyasuta/cap-bp-rag — package.json: https://raw.githubusercontent.com/miyasuta/cap-bp-rag/main/package.jsonSAP HANA Cloud

README

quoted from miyasuta/cap-bp-rag, read
miyasuta/cap-bp-rag/readme.mdOn GitHub

cap-bp-rag

This repository is my submission for the May 2026 Developer Challenge — From Events to Intelligence: Building an Event-Driven RAG Application.

It implements an event-driven Retrieval-Augmented Generation (RAG) application built with the SAP Cloud Application Programming Model (CAP), using SAP HANA Cloud's Vector Engine as the vector store and OpenAI for embeddings and answer generation.

excerpt, no licence read, read the rest, on GitHub

Details

Sources3
GitHub organisations and accountsdiscovered here, miyasutachecked
github.com/miyasuta/cap-bp-ragtree, pushes, contributors, CIchecked
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
deploymentCloud Foundry
discovered viaGitHub organisations and accounts · miyasuta
first seen in the atlas
ecosystem and domaincap, ai-and-agents
History in the atlas1
  1. First seen.
For your agent
Ref
artifact:miyasuta-cap-bp-rag
JSON
/artifacts/miyasuta-cap-bp-rag.json
MCP
Connecting an agent