rag▌

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

Build RAG pipelines combining web search and LLMs for grounded, sourced AI responses. \n \n Integrates multiple search tools (Tavily, Exa) and LLM providers (Claude, GPT-4, Gemini via OpenRouter) via the inference.sh CLI \n Supports three core patterns: simple search-plus-answer, multi-source research aggregation, and URL content extraction with analysis \n Includes ready-to-use examples for fact-checking, research reports, and iterative deep-dive queries with built-in source attribution \n Best

Comprehensive patterns for building production RAG systems. Each category has individual rule files in rules/ loaded on-demand.

Complete RAG pipeline for document ingestion, embedding, retrieval, and LLM-powered response generation. \n \n Supports multiple document loaders (PDF, web pages, directories) and persistent vector stores (Chroma, FAISS, Pinecone) with configurable chunk size and overlap for optimal context preservation \n Includes similarity search, MMR (Maximal Marginal Relevance) retrieval, and metadata filtering to balance relevance and diversity in results \n Works with OpenAI embeddings and integrates seam