rag-patterns

RAG Patterns Skill

Core Patterns

1. Hybrid Search

Combine dense (vector) and sparse (BM25) retrieval with RRF fusion:

# RAG-MCP hybrid search
result = await hybrid_search_kb(
    query="rate limiting configuration",
    service="nginx",
    limit=10
)

2. Corrective RAG (CRAG)

Self-correcting retrieval with relevance validation:

result = await crag_search(
    query="fuzzy query",
    relevance_threshold=0.4,
    max_retries=2
)

# Or via smart_query
result = await smart_query(query="...", use_crag=True)

3. HyDE (Hypothetical Document Embeddings)

Generate hypothetical answers for better retrieval on conceptual queries:

result = await smart_query(
    query="conceptual question about design patterns",
    use_hyde=True
)

4. Multi-hop Retrieval

Complex queries requiring multiple retrieval steps:

result = await multi_hop_search(
    query="Compare nginx with varnish for Magento cache",
    max_hops=3
)

# Or via smart_query
result = await smart_query(query="compare A vs B", use_multi_hop=True)

---

Indexing Best Practices

Aspect	Recommendation
Chunk size	512-1024 tokens
Overlap	10-20% of chunk
Structure	Preserve headers, sections
Metadata	Include title, path, date, category, tags
Frontmatter	YAML with standardized fields

Frontmatter Template

---
title: "Document Title"
service: {project-name}
category: reference|howto|procedures|troubleshooting|decisions|best-practices
tags: [tag1, tag2, tag3]
last_updated: "YYYY-MM-DD"
---

---

MCP Tools Reference (v5.5.0)

Tool	Use Case	Speed
smart_query ⭐	Default for 90% of queries	2-4s
hybrid_search_kb	Raw vector + text search	<1s
get_document	Full document content	<1s
crag_search	Vague/fuzzy queries	1-3s
multi_hop_search	Complex reasoning	20-30s

Tool Selection Guide

# Default - auto-routing
smart_query("specific technical question")

# Vague query - self-correcting
crag_search("jak to skonfigurować")

# Complex comparison
multi_hop_search("nginx vs varnish performance comparison")

# Known document
get_document(path="kb/reference/architecture.md")