Practice · 2023–now · AI Present
Embed everything
If it is text, vectorize it. Semantic search cosplay for problems that needed a better filter.
Why Embed everything became a costly fad
Embed-everything failed as a default because embeddings without evals are expensive autocomplete. It stuck where semantic search has a clear metric. The costly fad was treating vectors as a substitute for information architecture.
Cost of the fad
What Embed everything cost
Embedding pipelines for tickets, PDFs, Slack, and the cafeteria menu — then nobody measured retrieval quality. Vector bills and reindex jobs became the product.
Patterns
Compare with
Related
Platform · 2022–now
Vector DB gold rush
Specialized embedding stores sold as the default. Mid-market folded back into Postgres — after the vendor tour.
Practice · 2023–now
RAG as default architecture
Retrieval-augmented generation as the answer to every knowledge problem — then "just stuff the window" as the counter-fad. Often right; often Postgres with pgvector would suffice.
$ Teams stood up vector pipelines, chunking strategies, and rerankers before asking if fine-tuning or a SQL query would answer the question. Retrieval infra became the product.
Platform · 2023–now
Postgres + pgvector
Embeddings back in the database you already run. The default for mid-market RAG — not the quiet alternative.