Articles for people who
ship the stack
Original rewrites on React, Node.js, TypeScript and AI — practical notes from the same engineering practice behind our operator software. Article bodies are in English.
Tagged: retrieval
Ontology-Aware GraphRAG: When Vectors Need Typed Relationships
How identifier anchors, ontology contracts, rank fusion, and cite-or-reject gates fix RAG failures on CVEs, multi-hop ownership, and unspoken graph facts.
2819 wordsRead articleChunking is the whole retrieval system: Spring AI 800 vs 128 trap
When the splitter emits 800-token chunks but the embedder only reads 128, retrieval cannot see the truncated tail. Chunk size, window, and overlap are the retrieval system.
3727 wordsRead articleChunk Documents Around the Evidence an Answer Needs
Choose chunk boundaries by inspecting which facts must travel together, then test retrieval under a fixed context budget.
592 wordsRead articleBeyond Top-K: Relevance Thresholds, Hybrid Search and Reranking in RAG
See why a vector database plus an LLM is not a production RAG system, and how chunking, similarity thresholds, hybrid search, reranking and evaluation close the gap.
1628 wordsRead article
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.