๐—ช๐—ต๐˜† ๐— ๐˜† ๐—™๐—ถ๐—ฟ๐˜€๐˜ ๐—ฅ๐—”๐—š ๐—Ÿ๐—ฎ๐˜†๐—ฒ๐—ฟ ๐—ฆ๐˜๐—ฎ๐—ฟ๐˜๐˜€ ๐—ถ๐—ป ๐—ฃ๐—ผ๐˜€๐˜๐—ด๐—ฟ๐—ฒ๐˜€

Many people rush to pick a vector database when building RAG workflows.

They ask the wrong first question.

The right question is: What approved knowledge should the workflow use before an AI makes a decision?

In operational AI, models should not rely on raw memory. The context you need already exists in your systems. This includes:

Most of this data is already relational. You have leads, workflow names, stages, and logs.

The real challenge is not writing text. The challenge is retrieving the right context and showing which source influenced the decision.

I start my retrieval layer in Postgres with pgvector.

This choice keeps everything in one place. You can store:

A retrieval layer is not real until it has failure criteria. You must be able to answer:

A RAG layer looks smart even when it pulls the wrong context. You need to link the retrieval step and the AI decision step.

You need a single view that shows:

Standalone vector databases have a place. Use them if you need massive search traffic or complex filtering.

But for revenue and operations, prioritize control and auditability.

Starting with Postgres gives you:

Focus on schema clarity instead of architectural novelty.

Source: https://dev.to/rkrisa/why-my-first-rag-layer-starts-in-postgres-not-in-a-standalone-vector-database-29e0

Optional learning community: https://t.me/GyaanSetuAi