Technical Blog

Data engineering, AI and production systems — with technical references and code.

Bilingual articles (PT/EN) on RAG, LLM, and production AI pipelines. Each post includes book citations with page numbers and code examples grounded in those references.

Chunking and Indexing for RAG: Size, Overlap, and Recall

How to set chunk size, overlap, and dual indexing (embedding + tsvector) to maximize recall in production RAG pipelines — with Python code and real tradeoffs.

May 31, 2026 9 min rag chunking embeddings python

Hybrid RAG in Practice: Semantic + Keyword Search

How to combine vector search and keyword retrieval for precise technical context in production RAG pipelines.

May 30, 2026 8 min rag embeddings python