Feb 4 · 10 min read · SaaS companies live and die by their metrics. Data is collected in operational systems, copied into warehouses, transformed through pipelines, and finally visualized in dashboards. Finance teams learn where to click. Analysts learn how to maintain th...
Join discussion
Feb 4 · 14 min read · Vector databases are often introduced as tools for semantic similarity search. In practice, that understanding breaks down the moment you try to build a real RAG system. In this article, I explain what vector databases actually do inside modern retri...
Join discussionDec 18, 2025 · 11 min read · MariaDB is a widely used open-source relational database that powers eCommerce operations with features like high availability, scalability, and flexible storage engine options. Platforms such as WooCommerce rely on it to manage product catalogs, cus...
Join discussion
Nov 3, 2025 · 5 min read · Introduction When I first built my retrieval pipeline, it seemed solid, a combination of dense embeddings and lexical search fused together with Reciprocal Rank Fusion (RRF).It worked well enough for most queries… until I started noticing subtle but ...
Join discussionSep 2, 2025 · 9 min read · As large language models (LLMs) and vector search become increasingly common in enterprise AI stacks, one of the quiet but persistent challenges is precision. Semantic search excels at retrieving conceptually similar content, but it can fail when exa...
Join discussion
Aug 31, 2025 · 6 min read · Search systems are always broken. Mend them with care, and like Kintsugi, they become more beautiful. Recently I’ve been diving deep in improving search & retrieval for Littlebird and here are some notes worth sharing. Turbopuffer Tpuf is an amazing...
Join discussion
Aug 22, 2025 · 5 min read · Retrieval Augmented Generation (RAG) has quickly evolved from simple document lookups to sophisticated, production-grade systems. Advancing beyond basics means improving scalability, accuracy, cost, and real-world robustness using advanced retrieval,...
Join discussion
Jul 21, 2025 · 23 min read · Introduction: The RAG Hype is Real, But So Are Its Failures Retrieval-Augmented Generation (RAG) has taken the AI world by storm, promising to anchor Large Language Models (LLMs) in factual, up-to-date, and proprietary data. The concept is elegant: r...
Join discussion
May 17, 2025 · 11 min read · In this article, we'll implement hybrid semantic search using MongoDB Atlas Full-Text Search and Vector Search. This approach powers a fast, relevant search experience by combining keyword and semantic understanding. We'll use a FastAPI backend for c...
Join discussion
