Weaviate

Weaviate is an open-source vector database that can vectorize data at import time using built-in modules (OpenAI, Cohere, HuggingFace) or accept pre-computed vectors. It supports hybrid search combining vector similarity with BM25 keyword search.

Installation

# docker-compose.yml: Weaviate with OpenAI vectorizer module
services:
  weaviate:
    image: cr.weaviate.io/semitechnologies/weaviate:1.28.0
    ports:
      - "8080:8080"
      - "50051:50051"
    environment:
      QUERY_DEFAULTS_LIMIT: 25
      AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED: "true"
      PERSISTENCE_DATA_PATH: /var/lib/weaviate
      DEFAULT_VECTORIZER_MODULE: text2vec-openai