qdrant/config/config.yaml

log_level: INFO

# Logging configuration
# Qdrant logs to stdout. You may configure to also write logs to a file on disk.
# Be aware that this file may grow indefinitely.
# logger:
#   # Logging format, supports `text` and `json`
#   format: text
#   on_disk:
#     enabled: true
#     log_file: path/to/log/file.log
#     log_level: INFO
#     # Logging format, supports `text` and `json`
#     format: text
#     buffer_size_bytes: 1024

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

  # Where to store snapshots
  snapshots_path: ./snapshots

  snapshots_config:
    # Where to store snapshots: "local", "s3", "gcs" or "azure"
    snapshots_storage: local

    # Amazon S3 or any S3-compatible storage. Fields left unset are resolved
    # from the AWS_* environment and the default credential chain.
    # s3_config:
    #   bucket: ""
    #   # Optional key prefix, objects become <prefix>/snapshots/...
    #   prefix: ""
    #   region: ""
    #   access_key: ""
    #   secret_key: ""
    #   # Custom endpoint, for MinIO and similar
    #   endpoint_url: ""

    # Google Cloud Storage. Without credential fields, Application Default
    # Credentials are used: GOOGLE_* environment, gcloud config or the
    # metadata server on GCE and GKE.
    # gcs_config:
    #   bucket: ""
    #   # Optional object name prefix, objects become <prefix>/snapshots/...
    #   prefix: ""
    #   # Use at most one of the following
    #   service_account_path: ""
    #   service_account_key: ""
    #   application_credentials_path: ""
    #   # Custom endpoint, for fake-gcs-server and similar
    #   endpoint_url: ""

    # Azure Blob Storage. Without credential fields, the default chain is
    # used: AZURE_* environment, managed identity or the Azure CLI.
    # azure_config:
    #   account: ""
    #   container: ""
    #   # Optional blob name prefix, blobs become <prefix>/snapshots/...
    #   prefix: ""
    #   # Use one authentication method
    #   access_key: ""
    #   sas_token: ""
    #   client_id: ""
    #   client_secret: ""
    #   tenant_id: ""
    #   # Custom endpoint, for Azurite and similar
    #   endpoint_url: ""

  # Where to store temporary files
  # If null, temporary snapshots are stored in: storage/snapshots_temp/
  temp_path: null

  # Deprecated: use `payload.memory` instead.
  # If true - point payloads will not be stored in memory.
  # It will be read from the disk every time it is requested.
  # This setting saves RAM by (slightly) increasing the response time.
  # Note: those payload values that are involved in filtering and are indexed - remain in RAM.
  #
  # Default: true
  on_disk_payload: true

  # Default payload storage configuration for newly created collections.
  # Overrides the deprecated `on_disk_payload` flag if both are set.
  # payload:
  #   # Memory placement of the payload storage: cold or cached.
  #   memory: cold

  # Load-time memory mode. Only affects how segments are loaded on startup;
  # does not modify any persisted configuration. Intended as a recovery knob
  # when a node crash-loops on out-of-memory.
  #
  # Options:
  # - disabled (default): load segments as persisted.
  # - no_resident: downgrade components to their on-disk variants where
  #   possible — quantization loads as if always_ram=false, payload field
  #   indexes as if on_disk=true, payload storage as mmap (not populated).
  # - no_populate: same as no_resident, plus skip mmap prefault on load for
  #   vectors, HNSW graph and payload storage.
  #low_memory_mode: disabled

  # Maximum number of concurrent updates to shard replicas
  # If `null` - maximum concurrency is used.
  update_concurrency: null

  # 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

    # Number of closed WAL segments to keep
    wal_retain_closed: 1

  # Normal node - receives all updates and answers all queries
  node_type: "Normal"

  # Listener node - receives all updates, but does not answer search/read queries
  # Useful for setting up a dedicated backup node
  # node_type: "Listener"

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

    # CPU budget, how many CPUs (threads) to allocate for an optimization job.
    # If 0 - auto selection, keep 1 or more CPUs unallocated depending on CPU size
    # If negative - subtract this number of CPUs from the available CPUs.
    # If positive - use this exact number of CPUs.
    optimizer_cpu_budget: 0

    # Prevent DDoS of too many concurrent updates in distributed mode.
    # One external update usually triggers multiple internal updates, which breaks internal
    # timings. For example, the health check timing and consensus timing.
    # If null - auto selection.
    update_rate_limit: null

    # Limit for number of incoming automatic shard transfers per collection on this node, does not affect user-requested transfers.
    # The same value should be used on all nodes in a cluster.
    # Default is to allow 1 transfer.
    # If null - allow unlimited transfers.
    #incoming_shard_transfers_limit: 1

    # Limit for number of outgoing automatic shard transfers per collection on this node, does not affect user-requested transfers.
    # The same value should be used on all nodes in a cluster.
    # Default is to allow 1 transfer.
    # If null - allow unlimited transfers.
    #outgoing_shard_transfers_limit: 1

    # Enable async scorer which uses io_uring when rescoring.
    # Only supported on Linux, must be enabled in your kernel.
    # See: <https://qdrant.tech/articles/io_uring/#and-what-about-qdrant>
    #async_scorer: false

    # Whether components readable through either a memory mapping or io_uring should use
    # io_uring. Only has an effect on Linux.
    #
    # - unset (default): the immutable vector storages follow `async_scorer`, nothing else
    #   uses io_uring.
    # - "disabled": no component uses io_uring.
    # - "auto": use io_uring for components with a `cold` memory placement, where reads hit
    #   the disk. Components meant to sit in RAM keep using mmap, which is faster there.
    #io_uring: disabled

    # Maximum number of collections to load concurrently.
    #max_concurrent_collection_loads: 1
    # Maximum number of local shards to load concurrently when loading a collection.
    #max_concurrent_shard_loads: 1
    # Maximum number of segments to load concurrently when loading a local shard.
    #max_concurrent_segment_loads: 8

  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.
    # If `default_segment_number = 0`, will be automatically selected by the number of available CPUs
    default_segment_number: 0

    # Do not create segments larger than this size (in KiloBytes).
    # 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.
    # Note: 1Kb = 1 vector of size 256
    # If not set, will be automatically selected considering the number of available CPUs.
    max_segment_size_kb: null

    # Maximum size (in KiloBytes) of vectors allowed for plain index.
    # Default value based on experiments and observations.
    # Note: 1Kb = 1 vector of size 256
    # To explicitly disable vector indexing, set to `0`.
    # If not set, the default value will be used.
    indexing_threshold_kb: 10000

    # Interval between forced flushes.
    flush_interval_sec: 5

    # Max number of threads (jobs) for running optimizations per shard.
    # Note: each optimization job will also use `max_indexing_threads` threads by itself for index building.
    # If null - have no limit and choose dynamically to saturate CPU.
    # If 0 - no optimization threads, optimizations will be disabled.
    max_optimization_threads: null

  # This section has the same options as 'optimizers' above. All values specified here will overwrite the collections
  # optimizers configs regardless of the config above and the options specified at collection creation.
  #optimizers_overwrite:
  #  deleted_threshold: 0.2
  #  vacuum_min_vector_number: 1000
  #  default_segment_number: 0
  #  max_segment_size_kb: null
  #  indexing_threshold_kb: 10000
  #  flush_interval_sec: 5
  #  max_optimization_threads: null

  # Default parameters of HNSW Index. Could be overridden for each collection or named vector 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 size threshold (in KiloBytes) below which full-scan is preferred over HNSW search.
    # This measures the total size of vectors being queried against.
    # When the maximum estimated amount of points that a condition satisfies is smaller than
    # `full_scan_threshold_kb`, the query planner will use full-scan search instead of HNSW index
    # traversal for better performance.
    # Note: 1Kb = 1 vector of size 256
    full_scan_threshold_kb: 10000

    # Number of parallel threads used for background index building.
    # If 0 - automatically select.
    # Best to keep between 8 and 16 to prevent likelihood of building broken/inefficient HNSW graphs.
    # On small CPUs, less threads are used.
    max_indexing_threads: 0

    # Deprecated: use `memory` instead.
    # Store HNSW index on disk. If set to false, index will be stored in RAM. Default: false
    on_disk: false

    # Memory placement of the HNSW index: cold, cached or pinned.
    # Overrides the deprecated `on_disk` flag if both are set.
    # memory: cached

    # Custom M param for hnsw graph built for payload index. If not set, default M will be used.
    payload_m: null

  # Default shard transfer method to use if none is defined.
  # If null - don't have a shard transfer preference, choose automatically.
  # If stream_records, snapshot or wal_delta - prefer this specific method.
  # More info: https://qdrant.tech/documentation/guides/distributed_deployment/#shard-transfer-method
  shard_transfer_method: null

  # Default parameters for collections
  collection:
    # Number of replicas of each shard that network tries to maintain
    replication_factor: 1

    # How many replicas should apply the operation for us to consider it successful
    write_consistency_factor: 1

    # Default parameters for vectors.
    vectors:
      # Deprecated: use `memory` instead.
      # Whether vectors should be stored in memory or on disk.
      on_disk: null

      # Memory placement of the vector storage: cold or cached.
      # Overrides the deprecated `on_disk` flag if both are set.
      # memory: null

    # shard_number_per_node: 1

    # Default quantization configuration.
    # More info: https://qdrant.tech/documentation/guides/quantization
    quantization: null

    # Default strict mode parameters for newly created collections.
    #strict_mode:
      # Whether strict mode is enabled for a collection or not.
      #enabled: false

      # Max allowed `limit` parameter for all APIs that don't have their own max limit.
      #max_query_limit: null

      # Max allowed `timeout` parameter.
      #max_timeout: null

      # Allow usage of unindexed fields in retrieval based (eg. search) filters.
      #unindexed_filtering_retrieve: null

      # Allow usage of unindexed fields in filtered updates (eg. delete by payload).
      #unindexed_filtering_update: null

      # Max HNSW value allowed in search parameters.
      #search_max_hnsw_ef: null

      # Whether exact search is allowed or not.
      #search_allow_exact: null

      # Max oversampling value allowed in search.
      #search_max_oversampling: null

  # Maximum number of collections allowed to be created
  # If null - no limit.
  max_collections: null

  # Cluster-wide resource quotas.
  #
  # Memory and disk are node-wide resources, so their limits are configured once for the whole
  # cluster instead of per collection. Quotas reject updates that would consume more of a resource,
  # regardless of whether strict mode is enabled for the collection being written to. The deprecated
  # `max_resident_memory_percent` in a collection's strict mode config can tighten the memory limit
  # for that collection, but never lift it.
  #
  # A limit that is reached has to be cleared by `release_margin_percent` before the node accepts
  # writes again. Without that margin a resource resting on its limit would put the node in and out
  # of service on the noise between two readings, restarting a shard recovery every time.
  #
  # These values only seed the quota manager on the first start. Afterwards the quota config is read
  # from (and written to) `quota.json` in the storage directory, which is kept in sync across the
  # cluster through consensus and can be changed with the `PUT /quotas` API.
  #
  # If this section is absent - no quota is enforced.
  #quotas:
    # Whether the limits below are enforced.
    #enabled: false

    # Reject memory-consuming updates once process resident memory reaches this percentage of total
    # system memory (or of the cgroup limit, if one applies).
    # If null - resident memory is not capped.
    #max_resident_memory_percent: null

    # Reject disk-consuming updates once the filesystem hosting the storage directory is filled to
    # this percentage of its capacity.
    # If null - disk usage is not capped.
    #max_disk_usage_percent: null

    # How many percentage points below its limit a resource has to fall before this node starts
    # accepting work again. Raise it where usage is volatile; 0 releases as soon as usage is back
    # under the limit.
    # If null - the built-in default of 5 applies.
    #release_margin_percent: null

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 - available cores minus one, with a minimum of 1.
  # If missing - Same as storage.max_search_threads
  max_workers: 0

  # Host to bind the service on
  host: 0.0.0.0

  # HTTP(S) port to bind the service on
  http_port: 6333

  # Keep-alive timeout for incoming HTTP connections in seconds.
  # Default: 5
  # http_keep_alive_timeout_sec: 5

  # Timeout for reading HTTP request data from clients in seconds.
  # Default: 5
  # http_client_request_timeout_sec: 5

  # Timeout for client disconnect handling in seconds.
  # Default: 5
  # http_client_disconnect_timeout_sec: 5

  # gRPC port to bind the service on.
  # If `null` - gRPC is disabled. Default: 6334
  # Commenting this key in an overlay does not disable gRPC; the base config
  # still supplies 6334. Set `null` to disable.
  grpc_port: 6334

  # Enable CORS headers in REST API.
  # If enabled, browsers would be allowed to query REST endpoints regardless of query origin.
  # More info: https://developer.mozilla.org/en-US/docs/Web/HTTP/CORS
  # Default: true
  enable_cors: true

  # Enable HTTPS for the REST and gRPC API
  enable_tls: false

  # Check user HTTPS client certificate against CA file specified in tls config
  verify_https_client_certificate: false

  # Set an api-key.
  # If set, all requests must include a header with the api-key.
  # example header: `api-key: <API-KEY>`
  #
  # If you enable this you should also enable TLS.
  # (Either above or via an external service like nginx.)
  # Sending an api-key over an unencrypted channel is insecure.
  #
  # Uncomment to enable.
  # api_key: your_secret_api_key_here

  # Set an api-key for read-only operations.
  # If set, all requests must include a header with the api-key.
  # example header: `api-key: <API-KEY>`
  #
  # If you enable this you should also enable TLS.
  # (Either above or via an external service like nginx.)
  # Sending an api-key over an unencrypted channel is insecure.
  #
  # Uncomment to enable.
  # read_only_api_key: your_secret_read_only_api_key_here

  # Uncomment to enable JWT Role Based Access Control (RBAC).
  # If enabled, you can generate JWT tokens with fine-grained rules for access control.
  # Use generated token instead of API key.
  #
  # jwt_rbac: true

  # Enforce API key / JWT authentication on the internal (p2p) gRPC API.
  # The regular api_key is always forwarded on internal requests, but the
  # receiving side only verifies it when this flag is enabled. Keep disabled
  # during a rolling upgrade so older peers (that do not attach a key yet)
  # can still reach newer peers, then turn it on once every node is upgraded.
  #
  # enforce_internal_auth: true

  # Hardware reporting adds information to the API responses with a
  # hint on how many resources were used to execute the request.
  #
  # Warning: experimental, this feature is still under development and is not supported yet.
  #
  # Uncomment to enable.
  # hardware_reporting: true
  #
  # Uncomment to enable.
  # Prefix for the names of metrics in the /metrics API.
  # metrics_prefix: qdrant_

  # Allow snapshot recovery from remote HTTP/HTTPS URLs.
  # If disabled, snapshot recovery will only work with local files and uploads.
  # Disabling this can mitigate SSRF risks in environments where the Qdrant node
  # has access to internal resources that should not be reachable by users.
  # Default: true
  # enable_snapshot_url_recovery: true

cluster:
  # Use `enabled: true` to run Qdrant in distributed deployment mode
  enabled: false

  # Configuration of the inter-cluster communication
  p2p:
    # Port for internal communication between peers
    port: 6335

    # Use TLS for communication between peers
    enable_tls: false

  # Configuration related to distributed consensus algorithm
  consensus:
    # How frequently peers should ping each other.
    # Setting this parameter to lower value will allow consensus
    # to detect disconnected nodes earlier, but too frequent
    # tick period may create significant network and CPU overhead.
    # We encourage you NOT to change this parameter unless you know what you are doing.
    tick_period_ms: 100

    # Compact consensus operations once we have this amount of applied
    # operations. Allows peers to join quickly with a consensus snapshot without
    # replaying a huge amount of operations.
    # If 0 - disable compaction
    compact_wal_entries: 128

# Set to true to prevent service from sending usage statistics to the developers.
# Read more: https://qdrant.tech/documentation/guides/telemetry
telemetry_disabled: false

# TLS configuration.
# Required if either service.enable_tls or cluster.p2p.enable_tls is true.
tls:
  # Server certificate chain file
  cert: ./tls/cert.pem

  # Server private key file
  key: ./tls/key.pem

  # Certificate authority certificate file.
  # This certificate will be used to validate the certificates
  # presented by other nodes during inter-cluster communication.
  #
  # If verify_https_client_certificate is true, it will verify
  # HTTPS client certificate
  #
  # Required if cluster.p2p.enable_tls is true.
  ca_cert: ./tls/cacert.pem

  # TTL in seconds to reload certificate from disk, useful for certificate rotations.
  # Only works for HTTPS endpoints. Does not support gRPC (and intra-cluster communication).
  # If `null` - TTL is disabled.
  cert_ttl: 3600

# Audit logging configuration.
# When enabled, Qdrant writes structured JSON audit log entries for every
# access-checked API request.
#
# audit:
#   enabled: false
#   dir: ./storage/audit
#   rotation: daily
#   max_log_files: 7
#   # If true, use X-Forwarded-For header to determine client IP in audit logs.
#   # Only enable this when running behind a trusted reverse proxy or load balancer.
#   # WARNING: Enabling this without a trusted proxy allows clients to spoof their IP.
#   # Default: false
#   trust_forwarded_headers: false