Weaviate

Vector databases Intermediate Open source Open core

A vector database with built-in hybrid search (combining vector similarity with keyword/BM25 ranking), a schema, and optional modules that generate embeddings or run RAG steps inside the database. It runs as a service and is aimed at production retrieval where hybrid search and structured filtering matter.

Strengths

Hybrid vector and keyword search, with built-in reranking and RAG
Optional integrated vectorisation for common embedding providers
REST, gRPC, and GraphQL APIs, plus multi-tenancy and replication

Weaknesses

Needs a working understanding of embeddings to use well
Large-scale deployments are resource-intensive
Setup assumes some database-administration familiarity

At a glance

Licence: BSD-3-Clause
Pricing: Open core
Platforms: Linux, Docker
GPU required: No

Works with

BGE-M3

Related guides

Building a local RAG system
Improving RAG retrieval quality

Glossary

Vector database
Embedding
RAG

Entry last verified 18 August 2026.