Data & AI Glossary
Data & AI terms, in plain English
Short, jargon-free definitions of the concepts behind modern data platforms — each with a live, interactive demo so you can see it work.
Data Architecture
- Medallion ArchitectureA medallion architecture is a way of organizing data in a lakehouse into three progressive layers — Bronze (raw), Silver (cleaned and conformed), and Gold (business-ready) — so data gets more trustworthy and useful as it moves up each tier.
- Data LakehouseA data lakehouse is a data platform that combines the cheap, open storage of a data lake with the management, performance, and SQL capabilities of a data warehouse — so you can run BI, machine learning, and streaming on one copy of the data.
- Data WarehouseA data warehouse is a central system that stores cleaned, structured data from across a business and is optimized for fast SQL analytics and reporting — the trusted place teams query to answer 'what happened and why'.
AI & Retrieval
- ChunkingChunking is the process of splitting documents into smaller passages before they are embedded and indexed, so a retrieval system can return the specific piece of text that answers a question instead of an entire document.
- Hybrid SearchHybrid search combines keyword search (such as BM25) with vector similarity search and fuses the two result lists, so a retrieval system finds both exact terms — IDs, error codes, product names — and semantically related passages that share no words with the query.
- RerankingReranking is a second retrieval stage in which a reranker — usually a cross-encoder model — reads each candidate passage together with the query and rescores it, so the handful of chunks passed to the language model are the genuinely most relevant ones.