rag▌

Role: RAG Systems Architect

Production-grade RAG system design covering chunking, embeddings, vector stores, hybrid search, reranking, and retrieval evaluation. \n \n Guides five core workflow steps: requirements analysis, vector store design, chunking strategy, retrieval pipeline configuration, and quality evaluation with checkpoints \n Supports multiple vector databases (Pinecone, Weaviate, Chroma, pgvector, Qdrant) with schema design, indexing, and sharding strategies \n Implements hybrid search combining dense vector r

You're a RAG specialist who has built systems serving millions of queries over terabytes of documents. You've seen the naive "chunk and embed" approach fail, and developed sophisticated chunking, retrieval, and reranking strategies.

Complete error analysis on RAG pipeline traces before selecting metrics. Inspect what was retrieved vs. what the model needed. Determine whether the problem is retrieval, generation, or both. Fix retrieval first.

Build RAG (Retrieval Augmented Generation) pipelines via inference.sh CLI.

Build Retrieval-Augmented Generation systems that extend AI capabilities with external knowledge sources.

Complete workflow for building RAG systems from embedding selection through evaluation and optimization. \n \n Covers eight sequential phases: requirements analysis, embedding selection, vector database setup, chunking strategy, retrieval implementation, LLM integration, caching, and evaluation \n Includes actionable steps for each phase with specific skills to invoke and copy-paste prompts for agent commands \n Addresses core RAG concerns: embedding quality, vector indexing, chunk overlap handl

Complete Retrieval-Augmented Generation systems with LangChain4j for knowledge-enhanced AI applications. \n \n Document ingestion pipelines with configurable chunking, metadata management, and embedding generation using OpenAI or custom embedding models \n Vector search and content retrieval with filtering, re-ranking, and configurable similarity thresholds for precise context matching \n RAG-enabled AI services that automatically inject retrieved context into chat models, with support for multi

Expert guidance for building retrieval-augmented generation systems with optimized embeddings, chunking, and retrieval pipelines. \n \n Covers semantic chunking, hierarchical retrieval, and hybrid search combining keyword and vector similarity matching \n Addresses critical RAG pitfalls including fixed-size chunking, embedding refresh strategies, and retrieval evaluation separate from generation quality \n Emphasizes chunking by meaning rather than token limits, multi-level indexing for precisio

Build knowledge-grounded LLM applications with vector databases, semantic search, and retrieval strategies. \n \n Supports six vector database options (Pinecone, Weaviate, Milvus, Chroma, Qdrant, pgvector) and six embedding models optimized for different use cases and providers \n Covers five advanced retrieval patterns: hybrid search combining dense and sparse retrieval, multi-query generation, contextual compression, parent document retrieval, and HyDE (hypothetical document embeddings) \n Inc