Vector Search Done Right: Best Practices, Qwen3 Dimension Control, and Why Reranking Is Non-NegotiableThree things your RAG pipeline on Databricks needs to get right — and why most pipelines get at least one of them wrong.The Problem With “Good Enough”…
Adding content staleness tracking, CDC-based updates, and recency-weighted retrieval to a Databricks RAG pipelineYou built a RAG system. It parses PDFs, chunks them, embeds them, retrieves relevant context. It even remembers conversations across turns …
Your RAG Agent Forgets Everything After One Message – Here’s How I Fixed It with Databricks LakebaseBuilding a context-aware RAG system end-to-end: from PDF parsing to multi-turn conversations that actually rememberMost RAG tutorials show you how to bu…
Two similarity score formulas. One silent assumption. A ~270× discrepancy waiting to bite you.If you’ve read the Databricks Vector Search documentation, you’ve probably come across two similarity score formulas:Cosine-form: score = 1 / (3 − 2·cosθ)Eucl…
A production-grade, end-to-end reference covering installation, CLAUDE.md, Hooks, GitHub Actions, MCP, Sub-Agents, FastMCP, and everything in between.Off late I was digging deep into something that I honestly couldn’t stop thinking about — how to use C…
A complete setup walkthrough with real code, real gotchas, and honest trade-offs on when SQL-based vector storage wins — and when it doesn’t🗺️ The Vector Database Landscape in 2025The options for storing and searching embeddings have never been richer….