backend-ai-rag skillA
backend-ai-rag is agent-read markdown (skill) from bekaku/java-spring-boot-starter: Optional module. Use only when the task changes Spring AI, Ollama, Qdrant vector stores, document ingestion, SSE chat streaming, AI tools, chat memory, prompts, or face recognition in this Spring Boot backend. Never load for ordinary CRUD, auth, file, or messaging work..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Backend AI / RAG — Playbook (optional module) > **Role:** HOW to change the AI path safely. Binding facts + evidence: `skills/backend/AI_RAG.md` (read it too). > **Requires:** `backend-core`. Add `backend-api` / `backend-data` / `backend-files` / `backend-security` only for the boundaries the change crosses. Finish with `backend-testing`. > **Do not load for ordinary CRUD/auth/file/messaging work.** ## Know this first - SSE runs on Spring MVC with Reactor `Flux` — not WebFlux. Reactor threads have no logged-in user: pass `userId`. - Qdrant beans exist only when `spring.ai.vectorstore.qdrant.enabled=true`. `app.rag.qdrant-enabled` does nothing. - Collection names (`rag_documents`, `table_schemas`) are hard-coded in `QdrantVectorStoreConfig`. - `chunk-overlap` / `max-num-chunks` are not used by the splitter. ## Pick your path | Change | Start at | |---|---| | Chat/SSE behavior, events | `AiChatController#streamChat` → `AiRagChatServiceImpl#streamAnswer` | | Ingestion / deletion | `AiDocumentMetaController` → `AiDocumentIngestionServiceImpl` | | Extraction by file type | `extraction/DocumentExtractorFactory` + extractors | …
Read the whole file at its exact version.
How to install
mdr add bekaku/java-spring-boot-starter/backend-ai-rag@git:20260924.15dc64amdr add bekaku/java-spring-boot-starter/backend-ai-rag@sha256:033cf7f7eb51331dPin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_zgaurblwtglirpgf)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260924.15dc64a latest | 2026-09-24 | 15dc64a | 4,245 B | A | view · diff |
| git:20260923.b5acb6d | 2026-09-23 | b5acb6d | 2,415 B | A | view · diff |
| git:20260921.de5eb9f | 2026-09-21 | de5eb9f | 1,600 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4245 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
bekaku/java-spring-boot-starter · 31 stars · license none · pushed 2026-09-24 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_zgaurblwtglirpgf GET https://markdownregistry.com/api/v1/resolve?ref=bekaku/java-spring-boot-starter/backend-ai-rag GET https://markdownregistry.com/api/v1/blob/033cf7f7eb51331deed7fa3ea8885eec878547eb9c3cb35d4328a9758de7338c
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.