Platform · 2022–now · AI Present
Vector DB gold rush
Specialized embedding stores sold as the default. Mid-market folded back into Postgres — after the vendor tour.
The gold rush sold standalone vector infra for demos that outgrew nothing. Specialized stores stick at extreme scale; everyone else needed an extension, good chunking, and fewer invoices. The hype layer faded; the retrieval problem did not.
Context
Demos consolidate; evals remain
AI pair programming changed how code is typed faster than how it is reviewed. Agent frameworks and standalone vector stores sorted into demos versus durable plumbing; mid-market RAG folded back into Postgres. The permanent layer is familiar: evals that gate deploys, model routing for cost, tool protocols instead of plugin snowflakes, and humans who own production. Autopilot rewrites and vibe-shipped auth middleware are still big-bang migrations with better slides — and a longer on-call.
Compare with
Related
Framework · 2023–now
LLM app frameworks
LangChain-class glue gave way to vendor SDKs and thin wrappers. The durable pieces are boring: evals, retrieval, and product UX.
Platform · 1974–now
SQL / Relational
Declarative data that outlived every ORM fashion cycle. Postgres and friends keep winning by being boring.
Platform · 2010–now
Elasticsearch
Full-text search and log analytics at scale. Powerful, hungry, and everywhere in observability stacks.
Platform · 2023–now
Postgres + pgvector
Embeddings back in the database you already run. The default for mid-market RAG — not the quiet alternative.
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.
Practice · 2023–now
Embed everything
If it is text, vectorize it. Semantic search cosplay for problems that needed a better filter.
$ Embedding pipelines for tickets, PDFs, Slack, and the cafeteria menu — then nobody measured retrieval quality. Vector bills and reindex jobs became the product.