All articles
BLOG / TOPIC
RAG and retrieval
Retrieval-augmented generation grounds a model in your own documents. These articles cover the full production architecture and the failure that surprises most teams: retrieval that looks right while the answer is wrong.
5 articles on this topic
Ordered from foundations to advanced, newest first within each level.
- Embeddings and Vector Search, Explained for EngineersHow embeddings and vector search work: similarity, nearest-neighbour indexes, filters, hybrid search and the version trap, explained step by step for engineers.Foundations 10 min readLast reviewed 2026-10-11
- Prompting, RAG or Fine-Tuning: A Decision GuideWhich technique first? A decision guide for prompting, RAG and fine-tuning: what each changes, what it costs to maintain and how to decide with an evaluation.Foundations 10 min readLast reviewed 2026-10-11
- Why Good Retrieval Still Produces Bad AnswersDebug RAG failures with a runnable Python exercise that separates retrieval misses, dropped evidence, unsupported claims and incorrect refusals.Intermediate 8 min readLast reviewed 2026-10-11
- The Enterprise AI Engineering BlueprintA reference architecture for enterprise AI: gateway, orchestration, RAG, MCP tools, identity, guardrails, evaluation, observability and governance.Advanced 16 min readLast reviewed 2026-10-11
- Production RAG Architecture: A Complete GuideThe full production RAG architecture: ingestion, chunking, embeddings, hybrid search, reranking, generation, evaluation and observability, with code.Advanced 14 min readLast reviewed 2026-10-11