AI ENGINEERING
RAG Engineering / 10Secure and Operate a RAG System
Carry authorization through retrieval, context, caches, and citations. Define trust boundaries, revocation behavior, and operational controls.
Tag / 10 articles
#rag-engineering
Blog posts tagged with rag-engineering
AI ENGINEERING
RAG Engineering / 09Evaluate Retrieval and Gate Regressions
Separate retrieval coverage, context quality, and answer support. Calculate ranking metrics and design reproducible regression gates.
AI ENGINEERING
RAG Engineering / 08Grounded Answers, Citation Validation, and Failure Recovery
Separate schema validity, citation identity, and factual support; design bounded repair, honest abstention, and streaming behavior around those distinct guarantees.
AI ENGINEERING
RAG Engineering / 07Query Planning and Safe Structured Retrieval
Translate questions into bounded retrieval plans, preserve metadata constraints, and verify SQL result semantics with a worked incident-table example.
AI ENGINEERING
RAG Engineering / 06Hybrid Search, RRF, and Bounded Corrective Retrieval
Work through reciprocal rank fusion, distinguish full-text search from BM25, and evaluate reranking and corrective retrieval without treating scores as confidence.
AI ENGINEERING
RAG Engineering / 05Context Assembly, Parent Retrieval, and Multimodal Evidence
Turn retrieved candidates into useful context by preserving qualifiers, tracking expansion provenance, budgeting tokens, and separating image retrieval from visual answering.
AI ENGINEERING
RAG Engineering / 04Embedding Models and Vector Index Compatibility
Understand vector geometry, pin the full encoding contract, and evaluate approximate search under real filters before migrating an embedding index.
AI ENGINEERING
RAG Engineering / 03Versioned Ingestion and Safe Index Publication
Design document ingestion around immutable representations, idempotent jobs, and atomic publication so failed updates cannot silently replace searchable evidence.
AI ENGINEERING
RAG Engineering / 02Chunking, Parsing, and the Evidence You Lose
Compare chunk boundaries on the same source, preserve qualifiers and table structure, and evaluate retrieval against stable evidence rather than arbitrary chunk IDs.
AI ENGINEERING
RAG Engineering / 01How RAG Works, from Documents to Answers
Understand how RAG connects documents to an LLM: build an index, retrieve passages, assemble context, and return an answer with traceable sources.