config.yaml

storage:
  # Where to store all the data
  storage_path: ./storage

  # Write-ahead-log related configuration
  wal:
    # Size of a single WAL segment
    wal_capacity_mb: 32

    # Number of WAL segments to create ahead of actual data requirement
    wal_segments_ahead: 0


  performance:
    # Number of parallel threads used for search operations. If 0 - auto selection.
    max_search_threads: 0

  optimizers:
    # The minimal fraction of deleted vectors in a segment, required to perform segment optimization
    deleted_threshold: 0.2

    # The minimal number of vectors in a segment, required to perform segment optimization
    vacuum_min_vector_number: 1000

    # Target amount of segments optimizer will try to keep.
    # Real amount of segments may vary depending on multiple parameters:
    #  - Amount of stored points
    #  - Current write RPS
    #
    # It is recommended to select default number of segments as a factor of the number of search threads,
    # so that each segment would be handled evenly by one of the threads
    default_segment_number: 5

    # Do not create segments larger this number of points.
    # Large segments might require disproportionately long indexation times,
    # therefore it makes sense to limit the size of segments.
    #
    # If indexation speed have more priority for your - make this parameter lower.
    # If search speed is more important - make this parameter higher.
    max_segment_size: 200000

    # Maximum number of vectors to store in-memory per segment.
    # Segments larger than this threshold will be stored as read-only memmaped file.
    memmap_threshold: 50000

    # Maximum number of vectors allowed for plain index.
    # Default value based on https://github.com/google-research/google-research/blob/master/scann/docs/algorithms.md
    indexing_threshold: 20000

    # Starting from this amount of vectors per-segment the engine will start building index for payload.
    payload_indexing_threshold: 10000

    # Minimum interval between forced flushes.
    flush_interval_sec: 10
    
    # Max number of threads, which can be used for optimization. If 0 - `NUM_CPU - 1` will be used
    max_optimization_threads: 0

  # Default parameters of HNSW Index. Could be override for each collection individually
  hnsw_index:
    # Number of edges per node in the index graph. Larger the value - more accurate the search, more space required.
    m: 16
    # Number of neighbours to consider during the index building. Larger the value - more accurate the search, more time required to build index.
    ef_construct: 100
    # Minimal amount of points for additional payload-based indexing.
    # If payload chunk is smaller than `full_scan_threshold` additional indexing won't be used -
    # in this case full-scan search should be preferred by query planner and additional indexing is not required.
    full_scan_threshold: 10000

service:

  # Maximum size of POST data in a single request in megabytes
  max_request_size_mb: 32

  # Number of parallel workers used for serving the api. If 0 - equal to the number of available cores.
  # If missing - Same as storage.max_search_threads
  max_workers: 0

  # Host to bind the service on
  host: 0.0.0.0

  # HTTP port to bind the service on
  port: 6333

  # GRPC port to bind the service on
  grpc_port: 6334