Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: Chunking
Index-Time RAG Quality: Chunk Types, Cleanup and Retrieval Labels
Index-time RAG quality: build text, table and image chunks, scrub parser noise, and add LLM-written retrieval labels that roughly halved failed lookups.
12 min readThree Ways Production RAG Fails: Fragmented Context, Drift and Misuse
Three ways production RAG fails: fragmented context from chunking, drift as the knowledge base grows, and misuse despite good retrieval, with layer-level fixes.
11 min readMultiDocFusion: Hierarchy-Aware Chunking for RAG on Long PDFs
MultiDocFusion keeps section context in every chunk of a long PDF: layout detection, OCR, a header-tree LLM and DFS grouping, for 8-15% better RAG retrieval.
7 min readChunk Size and Overlap in RAG: Stride, Token Limits and Seams
How to chunk a long book for RAG: choose size and overlap, understand stride, stay under the embedding token limit, store metadata and see overlap in a real split.
8 min readChunking Strategies for Production RAG: Fixed-Size, Semantic and Parent-Child
A practical tour of RAG chunking from fixed-size and recursive splitting to parent-child, propositions, late chunking, RAPTOR, tables, code and benchmarking.
22 min readParent-Child Chunking and Hierarchical Indexing for Better RAG Retrieval
Why small chunks win the match but lose the answer, and how parent-child chunking, dedup expansion and hierarchical indexing restore context in RAG retrieval.
10 min readWhy RAG Fails on Real Documents: Chunking, Hybrid Search, Reranking and Evals
Why RAG fails on real documents and the patterns that fix it: a two-phase design, chunking choices, hybrid search, reranking and evaluating retrieval alone.
7 min readRAG with LangChain from Scratch: Loaders, Chunks, Embeddings, Evaluation
Build a document Q&A system step by step: loading files, chunking, embeddings, the indexing and retrieval phases, and how to score retrieval and answers.
8 min readChunking: The Overlooked RAG Decision Behind Wrong Answers
Why splitting documents badly caps retrieval quality, how structure-aware and parent-child chunking help, and how to measure whether your chunks work.
7 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.