image:
  repository: ghcr.io/mintplex-labs/anything-llm
  pullPolicy: IfNotPresent
  tag: latest@sha256:f76f7f98ab2773f9dcbc4a3a7a27f498b19815caba8975f2ab15ec2c48476e9b
securityContext:
  container:
    readOnlyRootFilesystem: false
    runAsUser: 0
    runAsGroup: 0
    capabilities:
      add:
        - SYS_ADMIN

service:
  main:
    ports:
      main:
        protocol: http
        port: 3001

workload:
  main:
    podSpec:
      containers:
        main:
          env:
            SERVER_PORT: "{{ .Values.service.main.ports.main.port }}"
            STORAGE_DIR: "{{.Values.persistence.storage.mountPath }}"
            # forces users to use ingress if https is needed.
            # keep false.
            # remove it as they only check for existence not value
            # ENABLE_HTTPS: true
            JWT_SECRET:
              secretKeyRef:
                name: anythinglmm-secrets
                key: JWT_SECRET
            # LLM_PROVIDER='openai'
            # OPEN_AI_KEY=
            # OPEN_MODEL_PREF='gpt-3.5-turbo'

            # LLM_PROVIDER='gemini'
            # GEMINI_API_KEY=
            # GEMINI_LLM_MODEL_PREF='gemini-pro'

            # LLM_PROVIDER='azure'
            # AZURE_OPENAI_KEY=
            # AZURE_OPENAI_ENDPOINT=
            # OPEN_MODEL_PREF='my-gpt35-deployment' # This is the "deployment" on Azure you want to use. Not the base model.
            # EMBEDDING_MODEL_PREF='embedder-model' # This is the "deployment" on Azure you want to use for embeddings. Not the base model. Valid base model is text-embedding-ada-002

            # LLM_PROVIDER='anthropic'
            # ANTHROPIC_API_KEY=sk-ant-xxxx
            # ANTHROPIC_MODEL_PREF='claude-2'

            # LLM_PROVIDER='lmstudio'
            # LMSTUDIO_BASE_PATH='http://your-server:1234/v1'
            # LMSTUDIO_MODEL_TOKEN_LIMIT=4096

            # LLM_PROVIDER='localai'
            # LOCAL_AI_BASE_PATH='http://host.docker.internal:8080/v1'
            # LOCAL_AI_MODEL_PREF='luna-ai-llama2'
            # LOCAL_AI_MODEL_TOKEN_LIMIT=4096
            # LOCAL_AI_API_KEY="sk-123abc"

            # LLM_PROVIDER='ollama'
            # OLLAMA_BASE_PATH='http://host.docker.internal:11434'
            # OLLAMA_MODEL_PREF='llama2'
            # OLLAMA_MODEL_TOKEN_LIMIT=4096

            # LLM_PROVIDER='togetherai'
            # TOGETHER_AI_API_KEY='my-together-ai-key'
            # TOGETHER_AI_MODEL_PREF='mistralai/Mixtral-8x7B-Instruct-v0.1'

            # LLM_PROVIDER='mistral'
            # MISTRAL_API_KEY='example-mistral-ai-api-key'
            # MISTRAL_MODEL_PREF='mistral-tiny'

            # LLM_PROVIDER='huggingface'
            # HUGGING_FACE_LLM_ENDPOINT=https://uuid-here.us-east-1.aws.endpoints.huggingface.cloud
            # HUGGING_FACE_LLM_API_KEY=hf_xxxxxx
            # HUGGING_FACE_LLM_TOKEN_LIMIT=8000

            # EMBEDDING_ENGINE='openai'
            # OPEN_AI_KEY=sk-xxxx
            # EMBEDDING_MODEL_PREF='text-embedding-ada-002'

            # EMBEDDING_ENGINE='azure'
            # AZURE_OPENAI_ENDPOINT=
            # AZURE_OPENAI_KEY=
            # EMBEDDING_MODEL_PREF='my-embedder-model' # This is the "deployment" on Azure you want to use for embeddings. Not the base model. Valid base model is text-embedding-ada-002

            # EMBEDDING_ENGINE='localai'
            # EMBEDDING_BASE_PATH='http://localhost:8080/v1'
            # EMBEDDING_MODEL_PREF='text-embedding-ada-002'
            # EMBEDDING_MODEL_MAX_CHUNK_LENGTH=1000 # The max chunk size in chars a string to embed can be

            # Enable all below if you are using vector database: Chroma.
            # VECTOR_DB="chroma"
            # CHROMA_ENDPOINT='http://host.docker.internal:8000'
            # CHROMA_API_HEADER="X-Api-Key"
            # CHROMA_API_KEY="sk-123abc"

            # VECTOR_DB="pinecone"
            # PINECONE_API_KEY=
            # PINECONE_INDEX=

            # VECTOR_DB="lancedb"

            # VECTOR_DB="weaviate"
            # WEAVIATE_ENDPOINT="http://localhost:8080"
            # WEAVIATE_API_KEY=

            # VECTOR_DB="qdrant"
            # QDRANT_ENDPOINT="http://localhost:6333"
            # QDRANT_API_KEY=

            # VECTOR_DB="milvus"
            # MILVUS_ADDRESS="http://localhost:19530"
            # MILVUS_USERNAME=
            # MILVUS_PASSWORD=

            # VECTOR_DB="zilliz"
            # ZILLIZ_ENDPOINT="https://sample.api.gcp-us-west1.zillizcloud.com"
            # ZILLIZ_API_TOKEN=api-token-here

            # VECTOR_DB="astra"
            # ASTRA_DB_APPLICATION_TOKEN=
            # ASTRA_DB_ENDPOINT=

            # AUTH_TOKEN="hunter2" # This is the password to your application if remote hosting.
            # DISABLE_TELEMETRY="false"

            # Documentation on how to use https://github.com/kamronbatman/joi-password-complexity
            # Default is only 8 char minimum
            PASSWORDMINCHAR: 8
            PASSWORDMAXCHAR: 250
            PASSWORDLOWERCASE: 1
            PASSWORDUPPERCASE: 1
            PASSWORDNUMERIC: 1
            PASSWORDSYMBOL: 1
            PASSWORDREQUIREMENTS: 4

persistence:
  storage:
    enabled: true
    mountPath: "/app/server/storage"
  hotdir:
    enabled: true
    mountPath: "/app/collector/hotdir"
  outputs:
    enabled: true
    mountPath: "/app/collector/outputs"

portal:
  open:
    enabled: true