Vibeleaderboard

Which vector database should I use for RAG?

Below a few million vectors, the extension in the database you already run — usually pgvector — is the right answer. A dedicated vector database earns its operational cost at scale, not at the start.

Surveyed 17 September 2026

Add vector search

Open in Tools →
No.Tool
  1. 01
    PostgreSQL

    Open-source SQL database with JSON support, full-text search, and extensions such as PostGIS and pgvector.

    Developer Tools
  2. 02
    Supabase

    Open-source Firebase alternative combining a Postgres database with auth, realtime, storage, and edge functions.

    Developer Tools
  3. 03
    Pinecone

    Serverless managed vector database for storing and querying embeddings at scale, common as a RAG retrieval layer.

    Developer Tools
  4. 04
    Neon

    Postgres run serverlessly, where databases branch, scale themselves, and provision instantly.

    Developer Tools
  5. 05
    Redis

    In-memory key-value store used for caching, queues, session storage, and real-time data workloads.

    Developer Tools
  6. 06
    MongoDB

    Document database with flexible JSON schemas, offered as a managed cloud service through Atlas.

    Developer Tools

A curated selection in editorial order. Use the fit and evidence to judge it for your task. Something missing?

What to look for

  • 01Do you actually need a separate service? One less system to operate is worth a lot below a few million vectors.
  • 02Can you filter by metadata and vector in one query? Splitting them wrecks both recall and latency.
  • 03Does it support hybrid search? Pure semantic retrieval misses exact identifiers, names, and error codes.

Common questions

Is pgvector good enough for production RAG?
For most applications, yes. With an HNSW index it handles millions of vectors at low latency, and keeping embeddings beside your relational data makes filtered queries straightforward.
Why does my RAG miss obvious results?
Usually chunking or pure-semantic retrieval. Chunks that split a fact across boundaries never match well, and embeddings alone are poor at exact terms — add keyword search alongside.

More in Understand the AI landscape