Complete Configuration Reference

# Version of the config file format
version: 1.0

# Base URL for meinGPT service
meingpt_url: $MEINGPT_URL

# ================================
# VAULT CORE SETTINGS
# ================================
vault:
  # Required: Your vault credentials from meinGPT dashboard
  id: your-vault-id
  secret: $VAULT_SECRET
  
  # Standalone mode - if true, vault won't connect to meinGPT server
  standalone_mode: false
  
  # Data storage directory (acts as sync target for rclone)
  data_dir: ./tmp
  
  # Ingestion settings
  ingestion_interval: 900             # Interval in seconds between ingestion runs (0 for disabled)
  tasks_batch_size: 10               # Tasks added to event loop at once from every datapool
  chunk_size: 256                    # Size of each text chunk in tokens
  chunk_overlap: 26                  # Overlapping tokens between consecutive chunks

# ================================
# VECTOR DATABASE CONFIGURATION
# ================================
weaviate:
  # Connection settings
  connection_type: local              # "local" or "custom"
  host: localhost                     # Docker service name or IP
  port: 8001                         # Weaviate port
  grpc_host: localhost               # gRPC host for Weaviate
  grpc_port: 50051                   # gRPC port for Weaviate
  
  # Authentication (empty string for local)
  api_key: ""

# ================================
# EMBEDDING MODEL CONFIGURATION
# ================================
embedding_model:
  # Required base settings for all providers
  rpm: 3000                          # Requests per minute
  tpm: 1000000                       # Tokens per minute
  
  # Optional prompts for specialized embedding
  query_prompt: null                 # Prompt prepended to queries
  document_prompt: null              # Prompt prepended to documents
  
  # === AZURE OPENAI ===
  provider: "azure"
  api_key: $AZURE_API_KEY
  api_version: "2023-05-15"
  model: text-embedding-3-small
  endpoint: https://your-endpoint.openai.azure.com/
  embedding_dimensions: 512
  
  # === OR OPENAI ===
  # provider: "openai"
  # model: "text-embedding-ada-002"   # Default model
  # base_url: null                    # Optional custom URL
  # api_key: $OPENAI_API_KEY
  
  # === OR NEBIUS ===
  # provider: "nebius"
  # tokenizer: "BAAI/bge-multilingual-gemma2"
  # model: "bge-multilingual-gemma2"
  # base_url: "https://api.studio.nebius.ai/v1/"
  # api_key: $NEBIUS_API_KEY
  
  # === OR HUGGINGFACE LOCAL ===
  # provider: "huggingface_local"
  # model: "sentence-transformers/all-mpnet-base-v2"
  # model_kwargs: {}                  # Additional model parameters
  # encode_kwargs: {}                 # Additional encoding parameters

# ================================
# LOGGING CONFIGURATION  
# ================================
logging:
  log_level: "INFO"                  # DEBUG, INFO, WARNING, ERROR, CRITICAL
  log_to_file: true
  log_file_path: "logs/app.log"
  uvicorn_log_file_path: "logs/uvicorn.log"
  
  # Sentry error tracking
  sentry_dsn: ""                     # Sentry DSN for error tracking
  sentry_event_level: "WARNING"
  sentry_tags: {}                    # Additional tags for Sentry events
  
  # Heartbeat monitoring
  heartbeat_url: null                # URL for uptime monitoring
  heartbeat_interval_minutes: 1
  
  # System monitoring intervals (0 to disable)
  system_monitoring_interval: 0      # System usage monitoring
  storage_monitoring_interval: 0     # Storage monitoring
  database_monitoring_interval: 0    # Database monitoring

# ================================
# API RATE LIMITING
# ================================
search_requests_per_minute: 30       # Search requests per minute limit
search_results_limit: 20             # Maximum search results returned

# ================================
# DATA SOURCES CONFIGURATION
# ================================
data_pools:
  # === LOCAL FILESYSTEM ===
  - id: local
    type: local
    base_path: ./data                # Directory used as synchronization source
    
  # === AMAZON S3 ===  
  - id: s3-documents
    type: s3
    access_key_id: $AWS_ACCESS_KEY_ID
    secret_access_key: $AWS_SECRET_ACCESS_KEY
    endpoint: $S3_ENDPOINT
    bucket_name: your-bucket-name
    provider: "Other"                # AWS, MinIO, DigitalOcean, Other
    base_path: "documents/"          # Optional folder prefix
    
  # === GOOGLE DRIVE ===
  - id: google-drive
    type: drive
    refresh_token: $GOOGLE_REFRESH_TOKEN
    scope: "drive.readonly"          # drive, drive.readonly, drive.file, drive.appfolder, drive.metadata.readonly
    root_folder_id: null             # Optional specific folder
    team_drive: null                 # For shared drives
    client_id: null                  # Optional custom client
    client_secret: null
    base_path: "/"
    
  # === MICROSOFT ONEDRIVE ===
  - id: onedrive
    type: onedrive
    client_id: "4306c62e-d96d-41a0-9f59-f577e3707aba"  # Default client ID
    client_secret: null              # Optional custom client secret
    refresh_token: $ONEDRIVE_REFRESH_TOKEN
    drive_id: $ONEDRIVE_DRIVE_ID
    drive_type: "personal"           # personal, business, documentLibrary
    tenant_id: null                  # Optional custom tenant
    base_path: "/"
    
  # === CONFLUENCE ===
  - id: confluence
    type: confluence
    url: "https://company.atlassian.net"
    username: $CONFLUENCE_USERNAME
    token: $CONFLUENCE_TOKEN
    space_id: $CONFLUENCE_SPACE_ID
    base_path: null                  # Optional
    
  # === SMB/CIFS NETWORK SHARE ===
  - id: smb-share
    type: smb
    host: "server.company.com"
    user: $SMB_USERNAME
    password: $SMB_PASSWORD
    port: null                       # Optional port (default 445)
    domain: null                     # Optional domain
    spn: null                        # Optional SPN
    base_path: "/shared"
    
  # === WEBDAV ===
  - id: webdav
    type: webdav
    url: "https://webdav.company.com"
    vendor: "nextcloud"              # fastmail, nextcloud, owncloud, sharepoint, sharepoint-ntlm, rclone, other
    user: $WEBDAV_USERNAME
    password: $WEBDAV_PASSWORD
    bearer_token: null               # Alternative to username/password
    base_path: "/"