Platform · 2023–now · AI Present
Postgres + pgvector
Embeddings back in the database you already run. The quiet winner of the vector DB gold rush.
pgvector stuck because most RAG workloads never needed a new operational surface — they needed an extension, good indexes, and fewer vendors. Specialized vector stores remain for extreme scale; the mutation killed the "you must buy Pinecone" default for mid-market apps. Boring SQL won again.
Context
The stack gets a co-pilot
AI pair programming is already changing how code is written. Agent frameworks and vector stores are still sorting winners from demos. The durable layer will look familiar: evals, retrieval quality, product UX, and ownership. Autopilot rewrites without tests are just big-bang migrations with better slides.
Compare with
Related
Platform · 2022–now
Vector DB gold rush
Specialized stores for embeddings. Many workloads are folding back into Postgres extensions — after the vendor tour.
Platform · 1974–now
SQL / Relational
Declarative data that outlived every ORM fashion cycle. Postgres and friends keep winning by being boring.
Practice · 2023–now
RAG as default architecture
Retrieval-augmented generation as the answer to every knowledge problem. 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.