RAG & Context

Getting the right information in front of the model. Retrieval pipelines, graph-based and hybrid indexes, chunking and reranking, effective context length, and when retrieval still beats a longer window.

Articles

Diagram of the RAG retrieval ladder: retrieve top-k candidates then rerank to lift the right chunk, feeding a generation step capped by what was retrieved.

RAG12 min read

RAG Interview Questions: The Retrieval Ladder Behind the Hype

A senior practitioner's guide to RAG interview questions: the escalation from naive retrieval to chunking, reranking, evaluation, and GraphRAG, with the trap at every rung.

Roei ZAUG 30, 2026

Diagram of agent memory: raw interactions consolidated into durable facts on write, valid facts recalled while superseded ones are forgotten

AI AgentsRAG14 min read

Agent Memory Beyond RAG: Why Your Agent Needs a Write Path, Not a Retriever

Agent memory is not RAG: it needs a write path, not just retrieval. Memory types, temporal knowledge graphs, forgetting by design, and why chat logs fall short.

Roei ZJUL 17, 2026

Diagram contrasting a full advertised context window with the much shorter effective length where recall holds, the gap labeled context rot

EvaluationRAG16 min read

Effective Context Length: Why 1M-Token Windows Fall Short, and When RAG Still Wins

Effective context length is far shorter than the advertised window. What RULER and NoLiMa reveal about 1M-token models, why context rots, and when RAG still wins.

Roei ZJUN 21, 2026

RAG24 min read

RAG in 2026: From Vector Search to Context Engines and GraphRAG

Explore RAG in 2026: from naive vector search to GraphRAG, agentic retrieval, ColPali, and context engines. A deep technical guide for AI practitioners.

Roei ZAPR 23, 2026

Key Terms

Chunking Context Engineering Cross-Encoder Effective Context Length GraphRAG Hybrid Search Lost-in-the-Middle RAG (Retrieval-Augmented Generation)Recall@k Reranking Vector Database