Skip to content

Tracks Drills Topics Technologies Tech stacks Skill areas

Tracks Drills Topics

Loading

Aporeon

Technical interview practice, from one developer to another.

About Editorial standards Support Privacy Terms Refund policy

RAG & Vector Search - AI Engineering | Aporeon

RAG & Vector Search

Chunking, embeddings, retrieval, ranking, grounding, citations, freshness, and access control.

18 drillsPractice one at a timeOrdered pathConcept questionComparison questionArchitecture scenarioDebugging scenario

Recommended start

What RAG adds

Explains RAG as a runtime retrieval boundary that supplies relevant, current, and governed evidence without changing model weights.

Easy~7 minStep 1 of 18

Practice this drill Choose another

Search

18 of 18 shown

1What RAG addsRecommended startExplains RAG as a runtime retrieval boundary that supplies relevant, current, and governed evidence without changing model weights.Concept questionEasy~7 minArtificial IntelligenceGenerative AILarge Language ModelsPractice

Practice order

18 drillsOne at a time

1What RAG addsUp next / Easy / ~7 min
2RAG vs direct data accessMedium / ~10 min
3RAG ingestion pipelineMedium / ~12 min
4

2

RAG vs direct data accessChooses retrieval for ambiguous knowledge search while keeping authoritative structured operations behind deterministic services.Comparison questionMedium~10 minArtificial IntelligenceGenerative AILarge Language Models

Practice

3RAG ingestion pipelineBuilds a repeatable path from governed source documents to parsed, chunked, embedded, traceable, and replaceable index records.Architecture scenarioMedium~12 minArtificial IntelligenceGenerative AILarge Language ModelsPractice

4Choose RAG chunkingBalances retrieval precision, answer completeness, document structure, overlap, metadata, and model input limits.Architecture scenarioMedium~10 minArtificial IntelligenceGenerative AILarge Language ModelsPractice

5Preserve document structureUses hierarchy and adjacency to recover context that flat chunks lose while avoiding indiscriminate document expansion.Concept questionMedium~7 minArtificial IntelligenceGenerative AILarge Language ModelsPractice

6RAG index metadataDesigns index records that support filtering, authorization, freshness, citations, diagnosis, and safe reprocessing.Architecture scenarioMedium~10 minArtificial IntelligenceGenerative AILarge Language ModelsPractice

7Build a retrieval queryTransforms conversational requests into bounded search inputs while preserving user intent, constraints, and traceability.Architecture scenarioMedium~10 minArtificial IntelligenceGenerative AILarge Language ModelsPractice

8Keyword vs vector vs hybridCombines exact lexical matching with semantic recall and explains why hybrid retrieval often needs measured fusion and ranking.Comparison questionMedium~10 minArtificial IntelligenceGenerative AILarge Language ModelsPractice

9Filter vector retrievalUses pre-filtering for authorization and hard constraints while recognizing engine-specific recall and performance behavior.Concept questionMedium~10 minArtificial IntelligenceGenerative AILarge Language ModelsPractice

10Top-k and abstentionTunes evidence quantity and no-answer behavior from measured relevance rather than treating similarity scores as universal confidence.Architecture scenarioHard~12 minArtificial IntelligenceGenerative AILarge Language ModelsPractice

11Rerank RAG resultsUses a more precise second-stage ranker on a bounded candidate set while accounting for latency, cost, and authorization.Concept questionMedium~10 minArtificial IntelligenceGenerative AILarge Language ModelsPractice

12Ground answers and citationsConnects answer claims to retrieved evidence while preventing decorative citations and preserving source-level traceability.Architecture scenarioHard~12 minArtificial IntelligenceGenerative AILarge Language ModelsPractice

13Evaluate RAG retrievalBuilds a query-and-relevance dataset and separates retrieval recall, ranking quality, context quality, and generated-answer quality.Architecture scenarioHard~15 minArtificial IntelligenceGenerative AILarge Language ModelsPractice

14Keep a RAG index freshCoordinates source changes, versions, tombstones, reconciliation, and query-time freshness without treating the index as authoritative.Architecture scenarioHard~12 minArtificial IntelligenceGenerative AILarge Language ModelsPractice

15Migrate embedding indexesRebuilds and compares incompatible vector spaces using versioned indexes, shadow queries, atomic cutover, and rollback.Architecture scenarioHard~15 minArtificial IntelligenceGenerative AILarge Language ModelsPractice

16Secure RAG retrievalCarries source permissions into ingestion and query-time filtering while failing closed across retrieval, caching, and citations.Architecture scenarioHard~15 minArtificial IntelligenceGenerative AILarge Language ModelsPractice

17Diagnose missed RAG evidenceTraces a missed answer through source ingestion, parsing, chunking, filtering, query construction, retrieval, fusion, and ranking.Debugging scenarioHard~15 minArtificial IntelligenceGenerative AILarge Language ModelsPractice

18Design production RAGCombines governed ingestion, authorized hybrid retrieval, reranking, grounded generation, citations, evaluation, observability, and fallback.Architecture scenarioHard~20 minArtificial IntelligenceGenerative AILarge Language ModelsPractice

Choose RAG chunking

Medium / ~10 min

5Preserve document structureMedium / ~7 min

6RAG index metadataMedium / ~10 min

7Build a retrieval queryMedium / ~10 min

8Keyword vs vector vs hybridMedium / ~10 min

+10 more drills in this section