• Vector Databases for AI Applications
  • Installation

Vector Databases for AI Applications

Installation

Weaviate supports deployment with Docker. If you use the default values, you don't need a docker-compose.yml file to run the image. To customize your instance, edit the configuration settings in the docker-compose.yml file.

 docker run -p 8080:8080 -p 50051:50051 cr.weaviate.io/semitechnologies/weaviate:1.24.4

The command sets the following default values:

• PERSISTENCE_DATA_PATH defaults to ./data
• AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED defaults to true.
• QUERY_DEFAULTS_LIMIT defaults to 10.

Use Docker Compose to add your own configuration, e.g.:

• Run vector searches with Cohere, HuggingFace, OpenAI, and Google modules.
• Search already vectorized data – no vectorizer required.
• Retrieval augmented generation (RAG) with OpenAI (i.e. gpt-4), Cohere, Google modules.

services:
  weaviate:
    command:
    - --host
    - 0.0.0.0
    - --port
    - '8080'
    - --scheme
    - http
    image: cr.weaviate.io/semitechnologies/weaviate:1.24.4
    ports:
    - 8080:8080
    - 50051:50051
    volumes:
    - weaviate_data:/var/lib/weaviate
    restart: on-failure:0
    environment:
      QUERY_DEFAULTS_LIMIT: 25
      AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED: 'true'
      PERSISTENCE_DATA_PATH: '/var/lib/weaviate'
      DEFAULT_VECTORIZER_MODULE: 'none'
      ENABLE_MODULES: 'text2vec-cohere,text2vec-huggingface,text2vec-palm,text2vec-openai,generative-openai,generative-cohere,generative-palm,ref2vec-centroid,reranker-cohere,qna-openai'
      CLUSTER_HOSTNAME: 'node1'
volumes:
  weaviate_data:
    driver: local # Define the driver and options under the volume name
    driver_opts:
      type: none
      device: /opt/weaviate/data
      o: bind