“RAG”

Guides evaluation of RAG pipeline retrieval and generation quality.

Grounded knowledge retrieval, multi-source synthesis, and citation verification

Search the hybrid RAG (BM25 + vector, RRF-merged) over 17.6M chunks of historical sell-side research (Nomura, JPM, MS, BofA and hundreds more, 1982–2026).

Query the local RAG knowledge base using a python script.

Optional local retrieval (M9-OPT / ADR-003): use retrieve_knowledge_snippets when present to ground notes in files under knowledge/; map source_id to existing…

Use when | Pipeline para integrar documentos de OnlyOffice con el sistema RAG de KAI.

Efficiently perform web searches using the mcp-local-rag server with semantic similarity ranking.

Expert in building Retrieval-Augmented Generation systems.

Patterns for RAG pipelines, vector databases, embedding strategies, context-window management, and LLM orchestration.

Build, modify, or review retrieval-augmented generation systems.

Use when ingesting, searching, citing, or auditing local project knowledge for a heavy-reasoning agent, especially markdown, text, JSON, and other documents…

Chunking strategies, embedding model selection, hybrid search, reranking, eval metrics

Ejecuta flujos RAG en Obsidian para responder, resumir, reorganizar o crear notas nuevas con citas trazables.

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search.

Elite workflow for building and optimizing production-grade Retrieval-Augmented Generation (RAG) systems.

Use this skill for public-safe reasoning about RAG and LangChain pipelines, document loading, splitting, embedding, vector stores, retrievers, prompts…

Use when the user asks about internal/private knowledge, documents, policies, or any indexed corpus that should be answered from a knowledge base rather than…

Use local retrieval-augmented generation before web search to ground research in saved knowledge-base documents.

Use local retrieval-augmented generation before web search to ground research in saved sandbox documents.

Preparar um corpus local rastreável e abrir o chat especialista por meio dos módulos e da CLI do projeto.

Use when working on the Orcanos RAG pipeline, query router, chunking, retrieval, or ETL indexing.

RAG pipeline retrieval accuracy and faithfulness benchmark standard

Store embeddings beside application data in Postgres, create vector indexes, and query nearest neighbors for semantic search, RAG, recommendations, or agent…

Use when designing RAG, knowledge assistants, document chat, or retrieval systems.