#data-engineering
5 articles
Document Ingestion Pipelines: The Unglamorous 80% of RAG
PDF parsing, metadata design, PII scrubbing, chunk-at-ingest vs chunk-at-query, and incremental index updates — the ingestion work that determines whether RAG succeeds or fails.
Structured Data Extraction with LLMs
How to turn unstructured documents into typed, validated records using Pydantic AI and instructor — the entity extraction patterns that actually hold in production.
Synthetic Data Engineering: Pipelines, Quality, and Model Collapse Risks
How to build production-grade synthetic data pipelines for LLM fine-tuning—Magpie, Evol-Instruct, quality filters—and why model collapse is a real but avoidable failure.
SFT and Instruction Tuning: Data Is the Job
Supervised fine-tuning fundamentals with an honest look at why 1,000 curated examples reliably beat 100,000 scraped ones, and the training recipes that actually work.
Chunking Strategies That Actually Matter: From Fixed-Size to Late Chunking
Chunking is the highest-variance, least-discussed decision in RAG. The wrong strategy silently kills retrieval quality no matter how good your embeddings are.