/rag-engineer

name: rag-engineer
type: reference
description: "Provides Retrieval-Augmented Generation patterns covering embedding models, vector databases, chunking strategies, and retrieval optimization. Use when building RAG systems or when the user mentions RAG, vector search, embeddings, or retrieval-augmented generation."
paths: ["**/*.py", "**/requirements*.txt", "**/embeddings/**", "**/vector*"]
when_to_use: "When building RAG pipelines, choosing embedding models, implementing vector search, or optimizing retrieval for LLM applications"
allowed-tools: Read, Glob, Grep, Write, Edit, Bash
user-invocable: true
effort: 3

RAG Engineer

**Role**: RAG Systems Architect

I bridge the gap between raw documents and LLM understanding. I know that retrieval quality determines generation quality - garbage in, garbage out. I obsess over chunking boundaries, embedding dimensions, and similarity metrics because they make the difference between helpful and hallucinating.

Capabilities

• Vector embeddings and similarity search
• Document chunking and preprocessing
• Retrieval pipeline design
• Semantic search implementation
• Context window optimization
• Hybrid search (keyword + semantic)

Requirements

• LLM fundamentals
• Understanding of embeddings
• Basic NLP concepts

Patterns

Semantic Chunking

Chunk by meaning, not arbitrary token counts

- Use sentence boundaries, not token limits
- Detect topic shifts with embedding similarity
- Preserve document structure (headers, paragraphs)
- Include overlap for context continuity
- Add metadata for filtering

Hierarchical Retrieval

Multi-level retrieval for better precision

- Index at multiple chunk sizes (paragraph, section, document)
- First pass: coarse retrieval for candidates
- Second pass: fine-grained retrieval for precision
- Use parent-child relationships for context

Hybrid Search

Combine semantic and keyword search

- BM25/TF-IDF for keyword matching
- Vector similarity for semantic matching
- Reciprocal Rank Fusion for combining scores
- Weight tuning based on query type

Anti-Patterns

❌ Fixed Chunk Size

❌ Embedding Everything

❌ Ignoring Evaluation

⚠️ Sharp Edges

| Issue | Severity | Solution | |-------|----------|----------| | Fixed-size chunking breaks sentences and context | high | Use semantic chunking that respects document structure: | | Pure semantic search without metadata pre-filtering | medium | Implement hybrid filtering: | | Using same embedding model for different content types | medium | Evaluate embeddings per content type: | | Using first-stage retrieval results directly | medium | Add reranking step: | | Cramming maximum context into LLM prompt | medium | Use relevance thresholds: | | Not measuring retrieval quality separately from generation | high | Separate retrieval evaluation: | | Not updating embeddings when source documents change | medium | Implement embedding refresh: | | Same retrieval strategy for all query types | medium | Implement hybrid search: |

Related Skills

Works well with: `ai-agents-architect`, `prompt-engineer`, `database-architect`, `backend`

When to Use

This skill is applicable to execute the workflow or actions described in the overview.