coolify/templates/compose/zep.yaml

# ignore: true
# documentation: https://help.getzep.com/concepts
# slogan: Zep enhances your AI agent's knowledge through continuous learning from user interactions, enabling personalized experiences and improved accuracy.
# tags: lowcode, nocode, ai, llm, openai, anthropic, machine-learning, rag, agents, chatbot, api, team, bot, flows, memory
# logo: svgs/zep.png
# port: 8000

services:
  postgres:
    image: ghcr.io/getzep/postgres:postgres-15
    shm_size: 128mb
    environment:
      - POSTGRES_USER=${SERVICE_USER_POSTGRES}
      - POSTGRES_PASSWORD=${SERVICE_PASSWORD_POSTGRES}
    volumes:
      - pg_data:/var/lib/postgresql/data
    healthcheck:
      test:
        - CMD-SHELL
        - "pg_isready -h localhost -U $${POSTGRES_USER} -d postgres"
      interval: 5s
      timeout: 5s
      retries: 5
  nlp:
    image: ghcr.io/getzep/zep-nlp-server:0.4
    environment:
      - SERVICE_FQDN_NLP_5557
      - ZEP_OPENAI_API_KEY=${OPENAI_API_KEY}
      - ZEP_AUTH_SECRET=${SERVICE_PASSWORD_AUTHSECRET}
      - ZEP_SERVER_WEB_ENABLED=${ZEP_SERVER_WEB_ENABLED:-false}
    healthcheck:
      test: "timeout 10s bash -c ':> /dev/tcp/127.0.0.1/5557' || exit 1"
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 45s
  zep:
    image: ghcr.io/getzep/zep:latest
    depends_on:
      postgres:
        condition: service_healthy
      nlp:
        condition: service_healthy
    environment:
      - SERVICE_FQDN_ZEP_8000
      - ZEP_STORE_POSTGRES_DSN=postgres://${SERVICE_USER_POSTGRES}:${SERVICE_PASSWORD_POSTGRES}@postgres:5432/postgres?sslmode=disable
      - ZEP_NLP_SERVER_URL=http://nlp:5557
      - ZEP_EXTRACTORS_DOCUMENTS_EMBEDDINGS_SERVICE=${EXTRACTORS_DOCUMENTS_EMBEDDINGS_SERVICE:-openai}
      - ZEP_EXTRACTORS_DOCUMENTS_EMBEDDINGS_DIMENSIONS=${EXTRACTORS_DOCUMENTS_EMBEDDINGS_DIMENSIONS:-1536}
      - ZEP_EXTRACTORS_MESSAGES_EMBEDDINGS_SERVICE=${EXTRACTORS_MESSAGES_EMBEDDINGS_SERVICE:-openai}
      - ZEP_EXTRACTORS_MESSAGES_EMBEDDINGS_DIMENSIONS=${EXTRACTORS_MESSAGES_EMBEDDINGS_DIMENSIONS:-1536}
      - ZEP_EXTRACTORS_MESSAGES_SUMMARIZER_EMBEDDINGS_SERVICE=${EXTRACTORS_MESSAGES_SUMMARIZER_EMBEDDINGS_SERVICE:-openai}
      - ZEP_EXTRACTORS_MESSAGES_SUMMARIZER_EMBEDDINGS_DIMENSIONS=${EXTRACTORS_MESSAGES_SUMMARIZER_EMBEDDINGS_DIMENSIONS:-1536}
      - ZEP_OPENAI_API_KEY=${OPENAI_API_KEY}
      - ZEP_AUTH_SECRET=${SERVICE_PASSWORD_AUTHSECRET}
      - ZEP_SERVER_WEB_ENABLED=${ZEP_SERVER_WEB_ENABLED:-false}
    volumes:
      - type: bind
        source: ./config.yaml
        target: /app/config.yaml
        content: |
          llm:
            # openai or anthropic
            service: "openai"
            # OpenAI: gpt-3.5-turbo, gpt-4, gpt-3.5-turbo-1106, gpt-3.5-turbo-16k, gpt-4-32k, gpt-4o-mini, gpt-4o-mini-2024-07-18; Anthropic: claude-instant-1 or claude-2
            model: "gpt-4o-mini"
            ## OpenAI-specific settings
            # Only used for Azure OpenAI API
            azure_openai_endpoint:
            # for Azure OpenAI API deployment, the model may be deployed with custom deployment names
            # set the deployment names if you encounter in logs HTTP 404 errors:
            #   "The API deployment for this resource does not exist."
            azure_openai:
            # llm.model name is used as deployment name as reasonable default if not set
            # assuming base model is deployed with deployment name matching model name
            #   llm_deployment: "gpt-4o-mini-customname"
            # embeddings deployment is required when Zep is configured to use OpenAI embeddings
            #   embedding_deployment: "text-embedding-ada-002-customname"
            # Use only with an alternate OpenAI-compatible API endpoint
              llm_deployment:
              embedding_deployment:
            openai_endpoint:
            openai_org_id:
          nlp:
            server_url: "http://localhost:5557"
          memory:
            message_window: 12
          extractors:
            documents:
              embeddings:
                enabled: true
                chunk_size: 1000
                dimensions: 384
                service: "local"
          #      dimensions: 1536
          #      service: "openai"
            messages:
              summarizer:
                enabled: true
                entities:
                  enabled: true
                embeddings:
                  enabled: true
                  dimensions: 384
                  service: "local"
              entities:
                enabled: true
              intent:
                enabled: true
              embeddings:
                enabled: true
                dimensions: 384
                service: "local"
          #      dimensions: 1536
          #      service: "openai"
          store:
            type: "postgres"
            postgres:
              dsn: "postgres://postgres:postgres@localhost:5432/?sslmode=disable"
          server:
            # Specify the host to listen on. Defaults to 0.0.0.0
            host: 0.0.0.0
            port: 8000
            # Is the Web UI enabled?
            # Warning: The Web UI is not secured by authentication and should not be enabled if
            # Zep is exposed to the public internet.
            web_enabled: true
            # The maximum size of a request body, in bytes. Defaults to 5MB.
            max_request_size: 5242880
          auth:
            # Set to true to enable authentication
            required: true
            # Do not use this secret in production. The ZEP_AUTH_SECRET environment variable should be
            # set to a cryptographically secure secret. See the Zep docs for details.
            secret: "do-not-use-this-secret-in-production"
          data:
            #  PurgeEvery is the period between hard deletes, in minutes.
            #  If set to 0 or undefined, hard deletes will not be performed.
            purge_every: 60
          log:
            level: "info"
          opentelemetry:
            enabled: false
          # Custom Prompts Configuration
          # Allows customization of extractor prompts.
          custom_prompts:
            summarizer_prompts:
              # Anthropic Guidelines:
              # - Use XML-style tags like <current_summary> as element identifiers.
              # - Include {{.PrevSummary}} and {{.MessagesJoined}} as template variables.
              # - Clearly explain model instructions, e.g., "Review content inside <current_summary></current_summary> tags".
              # - Provide a clear example within the prompt.
              #
              # Example format:
              # anthropic: |
              #   <YOUR INSTRUCTIONS HERE>
              #   <example>
              #     <PROVIDE AN EXAMPLE>
              #   </example>
              #   <current_summary>{{.PrevSummary}}</current_summary>
              #   <new_lines>{{.MessagesJoined}}</new_lines>
              #   Response without preamble.
              #
              # If left empty, the default Anthropic summary prompt from zep/pkg/extractors/prompts.go will be used.
              anthropic: |

              # OpenAI summarizer prompt configuration.
              # Guidelines:
              # - Include {{.PrevSummary}} and {{.MessagesJoined}} as template variables.
              # - Provide a clear example within the prompt.
              #
              # Example format:
              # openai: |
              #   <YOUR INSTRUCTIONS HERE>
              #   Example:
              #     <PROVIDE AN EXAMPLE>
              #   Current summary: {{.PrevSummary}}
              #   New lines of conversation: {{.MessagesJoined}}
              #   New summary:`
              #
              # If left empty, the default OpenAI summary prompt from zep/pkg/extractors/prompts.go will be used.
              openai: |
    healthcheck:
      test: "timeout 10s bash -c ':> /dev/tcp/127.0.0.1/8000' || exit 1"
      interval: 5s
      timeout: 10s
      retries: 3
      start_period: 40s