Skip to content
BENIBIX Learn

Weaviate

AI🔎 Retrieval & SearchVector Databases

Also known as Weaviate Vector Database, Weaviate Cloud

A free vector database. It mixes search by meaning and by words.

Think of it like

It is like a shop that sorts goods by shape and by name label. You can find things either way.

Example

A news site stores 400,000 articles in Weaviate. One query finds stories about "rate cuts" that also mention "Bank of England" by name.

Why it matters

Real questions mix ideas and exact names. Doing both in one query keeps the app simpler.

Definition

Weaviate is an open-source vector database written in the Go language. It stores your objects and their vectors side by side. It can call an embedding model for you when you add data. It mixes meaning search with keyword search in one query, which is hybrid search. You can run it yourself or rent it as a cloud service.
You can run Weaviate yourself. It can search by words and by meaning.

Common mistake

Leaving the keyword and meaning weights at the default. Test the mix on your own questions.

Key takeaways

  1. 1
    Objects and vectors. Stored side by side.
  2. 2
    Hybrid built in. Meaning plus keywords in one query.
  3. 3
    Run or rent. Open source, or a cloud service.