# Case Study: A Support Knowledge-Base Assistant — Retrieval-Augmented Generation (RAG)

Source: https://www.geekswithgeeks.com/en/rag/z-case

> Design a RAG assistant for customer-support articles, with permissions and citations.

## The design

Goal: support agents ask questions and get answers with links to help-centre articles. **Ingestion**: nightly crawl and a webhook on edits; extract clean text, keep headings, split by section into 300-token chunks with the article title prepended; metadata for product, language, audience (public or internal), article version and URL. **Retrieval**: hybrid BM25 + embeddings merged with RRF, filtered by product and audience, top 30 reranked to 5. **Generation**: instructions to answer only from numbered excerpts, cite as [n], reply "not found" otherwise, JSON output. **Safeguards**: code verifies citation IDs, a groundedness check flags weak answers, injection-resistant wording, and internal articles never reach external users. **Evaluation**: 150-question golden set including 20 unanswerable questions, tracking recall@5, faithfulness, refusal accuracy, latency and cost on every change. **Operations**: incremental re-indexing, deletion handling, feedback buttons and a weekly review of failed questions.

## A measured, trustworthy assistant

Combine ingestion, hybrid retrieval, grounded generation and evaluation into one dependable system.

![Four habits: clean data, hybrid search, grounded answers, constant measurement.](assets/figures/rag/section-8-map.svg) — Figure 8.1 — Clean data, hybrid search, grounded answers and measurement.

## The design on one page

Each line maps to a section of this course.

```text
Ingest      clean text, section chunks (300 tok), title prefix, metadata   (Sec 2)
Retrieve    BM25 + embeddings -> RRF -> filter -> rerank 30->5              (Sec 3, 4)
Generate    numbered excerpts, cite [n], "not found" allowed, JSON          (Sec 5)
Guard       citation-ID check, groundedness flag, injection wording, ACLs   (Sec 5, 7)
Evaluate    150-question golden set incl. unanswerable; recall@5, faithful  (Sec 6)
Operate     incremental index, deletes, feedback, weekly failure review     (Sec 7)
```

**Quiz:** Why are internal articles filtered out in the retrieval query?

- [x] So external users can never receive internal content
- [ ] To speed up the font
- [ ] To enlarge chunks
- [ ] Because embeddings dislike them

*Answer:* So external users can never receive internal content. Permissions must be enforced before text reaches the model.