RAG & Search Engineering — Complete Reference

Build production-grade retrieval systems with hybrid search, grounded generation, and measurable quality.

This skill covers:

• RAG: Chunking, contextual retrieval, grounding, adaptive/self-correcting systems
• Search: BM25, vector search, hybrid fusion, ranking pipelines
• Evaluation: recall@k, nDCG, MRR, groundedness metrics

Modern Best Practices (December 2025):

• Separate retrieval quality from answer quality; evaluate both (RAG paper: https://arxiv.org/abs/2005.11401).
• Default to hybrid retrieval (sparse + dense) with reranking when precision matters (DPR: https://arxiv.org/abs/2004.04906).
• Treat freshness/invalidation as first-class; staleness is a correctness bug, not a UX issue.
• Add grounding gates: answerability checks, citation coverage checks, and refusal-on-missing-context defaults.
• Threat-model RAG: retrieved text is untrusted input (OWASP LLM Top 10: https://owasp.org/www-project-top-10-for-large-language-model-applications/).

Default posture: deterministic pipeline, bounded context, explicit failure handling, and telemetry for every stage.

Scope note: For prompt structure and output contracts used in the generation phase, see ai-prompt-engineering.

Quick Reference

Decision Tree: RAG Architecture Selection

Building RAG system: [Architecture Path]
    ├─ Document type?
    │   ├─ Page/section-structured? → Structure-aware chunking (pages/sections + metadata)
    │   ├─ Technical docs/code? → Structure-aware + code-aware chunking (symbols, headers)
    │   └─ Simple content? → Fixed-size token chunking with overlap (baseline)
    │
    ├─ Retrieval accuracy low?
    │   ├─ Query ambiguity? → Query rewriting + multi-query expansion + filters
    │   ├─ Noisy results? → Add reranker + better metadata filters
    │   └─ Mixed queries? → Hybrid retrieval (sparse + dense) + reranking
    │
    ├─ Dataset size?
    │   ├─ <100k chunks? → Flat index (exact search)
    │   ├─ 100k-10M? → HNSW (low latency)
    │   └─ >10M? → IVF/ScaNN/DiskANN (scalable)
    │
    └─ Production quality?
        └─ Add: ACLs, freshness/invalidation, eval gates, and telemetry (end-to-end)

Core Concepts (Vendor-Agnostic)

• Pipeline stages: ingest → chunk → embed → index → retrieve → rerank → pack context → generate → verify.
• Two evaluation planes: retrieval relevance (did we fetch the right evidence?) vs generation fidelity (did we use it correctly?).
• Freshness model: staleness budget, invalidation triggers, and rebuild strategy (incremental vs full).
• Trust boundaries: retrieved content is untrusted; apply the same rigor as user input (OWASP LLM Top 10: https://owasp.org/www-project-top-10-for-large-language-model-applications/).

Implementation Practices (Tooling Examples)

• Use a retrieval API contract: query, filters, top_k, trace_id, and returned evidence IDs.
• Instrument each stage with tracing/metrics (OpenTelemetry GenAI semantic conventions: https://opentelemetry.io/docs/specs/semconv/gen-ai/).
• Add caches deliberately: embeddings cache, retrieval cache (query+filters), and response cache (with invalidation).

Do / Avoid

Do

• Do keep retrieval deterministic: fixed top_k, stable ranking, explicit filters.
• Do enforce document-level ACLs at retrieval time (not only at generation time).
• Do include citations with stable IDs and verify citation coverage in tests.

Avoid

• Avoid shipping RAG without a test set and regression gate.
• Avoid “stuff everything” context packing; it increases cost and can reduce accuracy.
• Avoid mixing corpora without metadata and tenant isolation.

When to Use This Skill

Claude should invoke this skill when the user asks:

• "Help me design a RAG pipeline."
• "How should I chunk this document?"
• "Optimize retrieval for my use case."
• "My RAG system is hallucinating — fix it."
• "Choose the right vector database / index type."
• "Create a RAG evaluation framework."
• "Debug why retrieval gives irrelevant results."

Related Skills

For adjacent topics, reference these skills:

• ai-llm - Prompting, fine-tuning, instruction datasets
• ai-agents - Agentic RAG workflows and tool routing
• ai-llm-inference - Serving performance, quantization, batching
• ai-mlops - Deployment, monitoring, security, privacy, and governance
• ai-prompt-engineering - Prompt patterns for RAG generation phase

Detailed Guides

Core RAG Architecture

• Pipeline Architecture - End-to-end RAG pipeline structure, ingestion, freshness, index hygiene, embedding selection
• Chunking Strategies - Chunking tradeoffs, evaluation approach, and production pitfalls
• Index Selection Guide - Vector database configuration, HNSW/IVF/Flat selection, parameter tuning

Advanced Retrieval Techniques

• Retrieval Patterns - Dense retrieval, hybrid search, query preprocessing, reranking workflow, metadata filtering
• Contextual Retrieval Guide - Chunk context augmentation technique; validate impact on your corpus
• Grounding Checklists - Context compression, hallucination control, citation patterns, answerability validation

Production & Evaluation

• RAG Evaluation Guide - Recall@K, nDCG, groundedness, RAGAS/TruLens, A/B testing, sliced evaluation
• Advanced RAG Patterns - Graph/multimodal RAG, online evaluation, telemetry, shadow/canary testing, adaptive retrieval
• RAG Troubleshooting - Failure mode triage, debugging irrelevant results, hallucination fixes

Existing Detailed Patterns

• Chunking Patterns - Technical implementation details for all chunking approaches
• Retrieval Patterns - Low-level retrieval implementation patterns

Templates

System Design (Start Here)

• RAG System Design

Chunking & Ingestion

• Basic Chunking
• Code Chunking
• Long Document Chunking

Embedding & Indexing

• Index Configuration
• Metadata Schema

Retrieval & Reranking

• Retrieval Pipeline
• Hybrid Search
• Reranking

Context Packaging & Grounding

• Context Packing
• Grounding

Evaluation

• RAG Evaluation
• RAG Test Set

Navigation

Resources

• resources/rag-evaluation-guide.md
• resources/rag-troubleshooting.md
• resources/contextual-retrieval-guide.md
• resources/pipeline-architecture.md
• resources/advanced-rag-patterns.md
• resources/chunking-strategies.md
• resources/grounding-checklists.md
• resources/index-selection-guide.md
• resources/retrieval-patterns.md
• resources/chunking-patterns.md

Templates

• templates/context/template-context-packing.md
• templates/context/template-grounding.md
• templates/design/rag-system-design.md
• templates/chunking/template-basic-chunking.md
• templates/chunking/template-code-chunking.md
• templates/chunking/template-long-doc-chunking.md
• templates/retrieval/template-retrieval-pipeline.md
• templates/retrieval/template-hybrid-search.md
• templates/retrieval/template-reranking.md
• templates/eval/template-rag-eval.md
• templates/eval/template-rag-testset.jsonl
• templates/indexing/template-index-config.md
• templates/indexing/template-metadata-schema.md

Data

• data/sources.json — Curated external references

External Resources

See data/sources.json for:

• Embedding models (OpenAI, Cohere, Sentence Transformers, Voyage AI, Jina)
• Vector DBs (FAISS, Pinecone, Qdrant, Weaviate, Milvus, Chroma, pgvector, LanceDB)
• Hybrid search libraries (Elasticsearch, OpenSearch, Typesense, Meilisearch)
• Reranking models (Cohere Rerank, Jina Reranker, RankGPT, Flashrank)
• Evaluation frameworks (RAGAS, TruLens, DeepEval, BEIR)
• RAG frameworks (LlamaIndex, LangChain, Haystack, txtai)
• Advanced techniques (RAG Fusion, CRAG, Self-RAG, Contextual Retrieval)
• Production platforms (Vectara, AWS Kendra)

Use this skill whenever the user needs retrieval-augmented system design or debugging, not prompt work or deployment.