version: '3'
services:
  api_server:
    image: danswer/danswer-backend:latest
    build:
      context: ../../backend
      dockerfile: Dockerfile
    command: >
      /bin/sh -c "alembic upgrade head &&
      echo \"Starting Danswer Api Server\" &&
      uvicorn danswer.main:app --host 0.0.0.0 --port 8080"
    depends_on:
      - relational_db
      - index
    restart: always
    ports:
      - "8080:8080"
    environment:
      - GEN_AI_MODEL_PROVIDER=${GEN_AI_MODEL_PROVIDER:-openai}
      - GEN_AI_MODEL_VERSION=${GEN_AI_MODEL_VERSION:-gpt-3.5-turbo}
      - GEN_AI_API_KEY=${GEN_AI_API_KEY:-}
      - GEN_AI_API_ENDPOINT=${GEN_AI_API_ENDPOINT:-}
      - GEN_AI_API_VERSION=${GEN_AI_API_VERSION:-}
      - NUM_DOCUMENT_TOKENS_FED_TO_GENERATIVE_MODEL=${NUM_DOCUMENT_TOKENS_FED_TO_GENERATIVE_MODEL:-}
      - POSTGRES_HOST=relational_db
      - VESPA_HOST=index
      - AUTH_TYPE=${AUTH_TYPE:-disabled}
      - QA_TIMEOUT=${QA_TIMEOUT:-}
      - VALID_EMAIL_DOMAINS=${VALID_EMAIL_DOMAINS:-}
      - GOOGLE_OAUTH_CLIENT_ID=${GOOGLE_OAUTH_CLIENT_ID:-}
      - GOOGLE_OAUTH_CLIENT_SECRET=${GOOGLE_OAUTH_CLIENT_SECRET:-}
      - DISABLE_GENERATIVE_AI=${DISABLE_GENERATIVE_AI:-}
      - NOTION_CONNECTOR_ENABLE_RECURSIVE_PAGE_LOOKUP=${NOTION_CONNECTOR_ENABLE_RECURSIVE_PAGE_LOOKUP:-}
      - DISABLE_LLM_FILTER_EXTRACTION=${DISABLE_LLM_FILTER_EXTRACTION:-}
      # Recency Bias for search results, decay at 1 / (1 + DOC_TIME_DECAY * x years)
      - DOC_TIME_DECAY=${DOC_TIME_DECAY:-}
      # Hybrid Search Alpha (0 for entirely keyword, 1 for entirely vector)
      - HYBRID_ALPHA=${HYBRID_ALPHA:-}
      # Don't change the NLP model configs unless you know what you're doing
      - DOCUMENT_ENCODER_MODEL=${DOCUMENT_ENCODER_MODEL:-}
      - NORMALIZE_EMBEDDINGS=${NORMALIZE_EMBEDDINGS:-}
      - SIM_SCORE_RANGE_LOW=${SIM_SCORE_RANGE_LOW:-}
      - SIM_SCORE_RANGE_HIGH=${SIM_SCORE_RANGE_HIGH:-}
      - ASYM_QUERY_PREFIX=${ASYM_QUERY_PREFIX:-}
      - ASYM_PASSAGE_PREFIX=${ASYM_PASSAGE_PREFIX:-}
      - SKIP_RERANKING=${SKIP_RERANKING:-}
      - QA_PROMPT_OVERRIDE=${QA_PROMPT_OVERRIDE:-}
      - EDIT_KEYWORD_QUERY=${EDIT_KEYWORD_QUERY:-}
      - MODEL_SERVER_HOST=${MODEL_SERVER_HOST:-}
      - MODEL_SERVER_PORT=${MODEL_SERVER_PORT:-}
      # Leave this on pretty please? Nothing sensitive is collected!
      # https://docs.danswer.dev/more/telemetry
      - DISABLE_TELEMETRY=${DISABLE_TELEMETRY:-}
      # Set to debug to get more fine-grained logs
      - LOG_LEVEL=${LOG_LEVEL:-info}
    volumes:
      - local_dynamic_storage:/home/storage
      - file_connector_tmp_storage:/home/file_connector_storage
      - model_cache_torch:/root/.cache/torch/
      - model_cache_nltk:/root/nltk_data/
      - model_cache_huggingface:/root/.cache/huggingface/
  background:
    image: danswer/danswer-backend:latest
    build:
      context: ../../backend
      dockerfile: Dockerfile
    command: /usr/bin/supervisord
    depends_on:
      - relational_db
      - index
    restart: always
    environment:
      - GEN_AI_MODEL_PROVIDER=${GEN_AI_MODEL_PROVIDER:-openai}
      - GEN_AI_MODEL_VERSION=${GEN_AI_MODEL_VERSION:-gpt-3.5-turbo}
      - GEN_AI_API_KEY=${GEN_AI_API_KEY:-}
      - GEN_AI_API_ENDPOINT=${GEN_AI_API_ENDPOINT:-}
      - GEN_AI_API_VERSION=${GEN_AI_API_VERSION:-}
      - POSTGRES_HOST=relational_db
      - VESPA_HOST=index
      - NUM_INDEXING_WORKERS=${NUM_INDEXING_WORKERS:-}
      # Connector Configs
      - CONTINUE_ON_CONNECTOR_FAILURE=${CONTINUE_ON_CONNECTOR_FAILURE:-}
      - CONFLUENCE_CONNECTOR_LABELS_TO_SKIP=${CONFLUENCE_CONNECTOR_LABELS_TO_SKIP:-}
      - GONG_CONNECTOR_START_TIME=${GONG_CONNECTOR_START_TIME:-}
      - EXPERIMENTAL_SIMPLE_JOB_CLIENT_ENABLED=${EXPERIMENTAL_SIMPLE_JOB_CLIENT_ENABLED:-}
      - EXPERIMENTAL_CHECKPOINTING_ENABLED=${EXPERIMENTAL_CHECKPOINTING_ENABLED:-}
      # Danswer SlackBot Configs
      - DANSWER_BOT_SLACK_APP_TOKEN=${DANSWER_BOT_SLACK_APP_TOKEN:-}
      - DANSWER_BOT_SLACK_BOT_TOKEN=${DANSWER_BOT_SLACK_BOT_TOKEN:-}
      - DANSWER_BOT_DISABLE_DOCS_ONLY_ANSWER=${DANSWER_BOT_DISABLE_DOCS_ONLY_ANSWER:-}
      - DANSWER_BOT_DISPLAY_ERROR_MSGS=${DANSWER_BOT_DISPLAY_ERROR_MSGS:-}
      - DANSWER_BOT_RESPOND_EVERY_CHANNEL=${DANSWER_BOT_RESPOND_EVERY_CHANNEL:-}
      - NOTIFY_SLACKBOT_NO_ANSWER=${NOTIFY_SLACKBOT_NO_ANSWER:-}
      # Recency Bias for search results, decay at 1 / (1 + DOC_TIME_DECAY * x years)
      - DOC_TIME_DECAY=${DOC_TIME_DECAY:-}
      # Hybrid Search Alpha (0 for entirely keyword, 1 for entirely vector)
      - HYBRID_ALPHA=${HYBRID_ALPHA:-}
      # Don't change the NLP model configs unless you know what you're doing
      - DOCUMENT_ENCODER_MODEL=${DOCUMENT_ENCODER_MODEL:-}
      - NORMALIZE_EMBEDDINGS=${NORMALIZE_EMBEDDINGS:-}
      - SIM_SCORE_RANGE_LOW=${SIM_SCORE_RANGE_LOW:-}
      - SIM_SCORE_RANGE_HIGH=${SIM_SCORE_RANGE_HIGH:-}
      - ASYM_QUERY_PREFIX=${ASYM_QUERY_PREFIX:-}
      - ASYM_PASSAGE_PREFIX=${ASYM_PASSAGE_PREFIX:-}
      - SKIP_RERANKING=${SKIP_RERANKING:-}
      - QA_PROMPT_OVERRIDE=${QA_PROMPT_OVERRIDE:-}
      - EDIT_KEYWORD_QUERY=${EDIT_KEYWORD_QUERY:-}
      - MIN_THREADS_ML_MODELS=${MIN_THREADS_ML_MODELS:-}
      - MODEL_SERVER_HOST=${MODEL_SERVER_HOST:-}
      - MODEL_SERVER_PORT=${MODEL_SERVER_PORT:-}
      # Set to debug to get more fine-grained logs
      - LOG_LEVEL=${LOG_LEVEL:-info}
    volumes:
      - local_dynamic_storage:/home/storage
      - file_connector_tmp_storage:/home/file_connector_storage
      - model_cache_torch:/root/.cache/torch/
      - model_cache_nltk:/root/nltk_data/
      - model_cache_huggingface:/root/.cache/huggingface/
  web_server:
    image: danswer/danswer-web-server:latest
    build:
      context: ../../web
      dockerfile: Dockerfile
      args:
        - NEXT_PUBLIC_DISABLE_STREAMING=${NEXT_PUBLIC_DISABLE_STREAMING:-false}
    depends_on:
      - api_server
    restart: always
    environment:
      - INTERNAL_URL=http://api_server:8080
      - WEB_DOMAIN=${WEB_DOMAIN:-}
      - OAUTH_NAME=${OAUTH_NAME:-}
  relational_db:
    image: postgres:15.2-alpine
    restart: always
    environment:
      - POSTGRES_USER=${POSTGRES_USER:-postgres}
      - POSTGRES_PASSWORD=${POSTGRES_PASSWORD:-password}
    ports:
      - "5432:5432"
    volumes:
      - db_volume:/var/lib/postgresql/data
  # This container name cannot have an underscore in it due to Vespa expectations of the URL
  index:
    image: vespaengine/vespa:8.249.12
    restart: always
    ports:
      - "19071:19071"
      - "8081:8081"
    volumes:
      - vespa_volume:/opt/vespa/var
  nginx:
    image: nginx:1.23.4-alpine
    restart: always
    # nginx will immediately crash with `nginx: [emerg] host not found in upstream`
    # if api_server / web_server are not up 
    depends_on:
      - api_server
      - web_server
    environment:
      - DOMAIN=localhost
    ports:
      - "80:80"
      - "3000:80"  # allow for localhost:3000 usage, since that is the norm
    volumes:
      - ../data/nginx:/etc/nginx/conf.d
    # sleep a little bit to allow the web_server / api_server to start up. 
    # Without this we've seen issues where nginx shows no error logs but 
    # does not recieve any traffic
    command: > 
      /bin/sh -c "sleep 10 &&
        envsubst '$$\{DOMAIN\}' < /etc/nginx/conf.d/app.conf.template.dev > /etc/nginx/conf.d/app.conf &&
        while :; do sleep 6h & wait $${!}; nginx -s reload; done & nginx -g \"daemon off;\""
  # Run with --profile model-server to bring up the danswer-model-server container
  model_server:
    image: danswer/danswer-model-server:latest
    build:
      context: ../../backend
      dockerfile: Dockerfile.model_server
    profiles:
      - "model-server"
    command: uvicorn model_server.main:app --host 0.0.0.0 --port 9000
    restart: always
    environment:
      - DOCUMENT_ENCODER_MODEL=${DOCUMENT_ENCODER_MODEL:-}
      - NORMALIZE_EMBEDDINGS=${NORMALIZE_EMBEDDINGS:-}
      - MIN_THREADS_ML_MODELS=${MIN_THREADS_ML_MODELS:-}
      # Set to debug to get more fine-grained logs
      - LOG_LEVEL=${LOG_LEVEL:-info}
    volumes:
      - model_cache_torch:/root/.cache/torch/
      - model_cache_huggingface:/root/.cache/huggingface/
volumes:
  local_dynamic_storage:
  file_connector_tmp_storage:  # used to store files uploaded by the user temporarily while we are indexing them
  db_volume:
  vespa_volume:
  model_cache_torch:
  model_cache_nltk:
  model_cache_huggingface: