← All decisions
Vector database
I'm building a RAG / semantic-search feature and need a vector database. Which should I use? Give your ranked top 3.
Top pick by run
| Model | Jul 3, 2026 |
|---|---|
| Claude Fable 5 | |
| Claude Opus 4.8 | |
| Claude Sonnet 4.6 | |
| Claude Haiku 4.5 | |
| GPT-5.5 |
Each column is one run. Click a pick to see that model's full ranking and reasoning. Green marks a change from the previous run.
Claude Fable 5
Jul 3, 2026- 1PineconeFully managed, serverless vector database with strong hybrid search and metadata filtering, letting you ship a production RAG feature without operating infrastructure.
- 2QdrantOpen-source and fast (Rust-based) with excellent filtering and both self-hosted and managed cloud options, giving flexibility and cost control.
- 3pgvector (PostgreSQL extension)If you already run Postgres, pgvector adds solid semantic search alongside your relational data with no new system to manage.