rag-architect

Step-by-step guidance to build a RAG pipeline from scratch

Evaluate RAG pipeline quality with comprehensive metrics

Debug RAG pipeline issues with systematic retrieval and generation analysis

Build autonomous RAG agents that reason, plan, and use tools for complex retrieval tasks. Use this skill when simple retrieve-and-generate isn't enough. Activate when: agentic RAG, RAG agent, multi-step retrieval, tool-using RAG, autonomous retrieval, query decomposition.

Expert guidance on document chunking strategies for RAG systems. Use this skill when designing how to split documents for vector embeddings. Activate when: chunking, chunk size, text splitting, document segmentation, overlap, semantic chunking, recursive splitting.

Implement Corrective RAG (CRAG) with retrieval validation, fallback strategies, and self-correction. Use this skill when RAG outputs need quality guarantees and automatic error correction. Activate when: CRAG, corrective RAG, retrieval validation, fallback search, self-correcting RAG, grounded generation.

Implement GraphRAG patterns combining knowledge graphs with retrieval for complex reasoning. Use this skill when building RAG over interconnected data or needing relationship-aware retrieval. Activate when: GraphRAG, knowledge graph, graph retrieval, entity relationships, Neo4j RAG, graph database, connected data.

Implement hybrid search combining dense vectors and sparse retrieval for optimal RAG results. Use this skill when vector search alone isn't providing accurate results. Activate when: hybrid search, BM25, keyword search, sparse retrieval, dense retrieval, reranking, ensemble retrieval.

Comprehensive checklist for deploying RAG systems to production with reliability and scale. Use this skill when preparing RAG for production deployment. Activate when: production RAG, RAG deployment, RAG checklist, RAG scaling, RAG monitoring, production-ready RAG.

Comprehensive RAG evaluation with retrieval metrics, generation quality, and end-to-end testing. Use this skill when measuring and improving RAG system performance. Activate when: RAG evaluation, RAGAS, retrieval metrics, generation quality, RAG testing, MRR, recall, faithfulness.

Pinecone vector database for similarity search

Weaviate vector database with hybrid search

Qdrant vector database for high-performance search

Neo4j graph database for GraphRAG patterns

Elasticsearch for hybrid keyword + vector search

OpenAI API for embeddings and generation