docker-compose.weaviate-gpu.yml

---
version: '3.4'
services:
  weaviate:
    command:
    - --host
    - 0.0.0.0
    - --port
    - '8080'
    - --scheme
    - http
    image: semitechnologies/weaviate:1.18.3
    ports:
    - 8080:8080
    restart: on-failure:0
    environment:
      TRANSFORMERS_INFERENCE_API: 'http://t2v-transformers:8080'
      QNA_INFERENCE_API: 'http://qna-transformers:8080'
      IMAGE_INFERENCE_API: 'http://i2v-neural:8080'
      NER_INFERENCE_API: 'http://ner-transformers:8080'
      SUM_INFERENCE_API: 'http://sum-transformers:8080'
      SPELLCHECK_INFERENCE_API: 'http://text-spellcheck:8080'
      OPENAI_APIKEY: $OPENAI_API_KEY
      QUERY_DEFAULTS_LIMIT: 25
      AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED: 'true'
      PERSISTENCE_DATA_PATH: '/var/lib/weaviate'
      DEFAULT_VECTORIZER_MODULE: 'text2vec-transformers'
      ENABLE_MODULES: 'text2vec-transformers,qna-transformers,ner-transformers,sum-transformers,text-spellcheck,img2vec-neural,ref2vec-centroid,generative-openai'
      CLUSTER_HOSTNAME: 'node1'
  t2v-transformers:
    image: semitechnologies/transformers-inference:sentence-transformers-multi-qa-mpnet-base-cos-v1
    environment:
      ENABLE_CUDA: '1'
      NVIDIA_VISIBLE_DEVICES: 'all'
    deploy:
      resources:
        reservations:
          devices:
          - capabilities:
            - 'gpu'
  qna-transformers:
    image: semitechnologies/qna-transformers:distilbert-base-cased-distilled-squad
    environment:
      ENABLE_CUDA: '1'
      NVIDIA_VISIBLE_DEVICES: 'all'
    deploy:
      resources:
        reservations:
          devices:
          - capabilities:
            - 'gpu'
  ner-transformers:
    image: semitechnologies/ner-transformers:dbmdz-bert-large-cased-finetuned-conll03-english
    environment:
      ENABLE_CUDA: '1'
      NVIDIA_VISIBLE_DEVICES: 'all'
    deploy:
      resources:
        reservations:
          devices:
          - capabilities:
            - 'gpu'
  sum-transformers:
    image: semitechnologies/sum-transformers:facebook-bart-large-cnn-1.0.0
    environment:
      ENABLE_CUDA: '1'
      NVIDIA_VISIBLE_DEVICES: 'all'
    deploy:
      resources:
        reservations:
          devices:
          - capabilities:
            - 'gpu'
  text-spellcheck:
    image: semitechnologies/text-spellcheck-model:pyspellchecker-en
  i2v-neural:
    image: semitechnologies/img2vec-keras:resnet50
    environment:
      ENABLE_CUDA: '1'
      NVIDIA_VISIBLE_DEVICES: 'all'
    deploy:
      resources:
        reservations:
          devices:
          - capabilities:
            - 'gpu'