class
Qdrant::Api::CreateCollection
- Qdrant::Api::CreateCollection
- Reference
- Object
Overview
Operation for creating new collection and (optionally) specify index params
Included Modules
- JSON::Serializable
- Qdrant::Api::Serializable
- Qdrant::Api::Validation
- YAML::Serializable
Defined in:
qdrant-api/models/create_collection.crConstructors
- .new(ctx : YAML::ParseContext, node : YAML::Nodes::Node)
- .new(pull : JSON::PullParser)
-
.new(vectors : VectorsConfig | Nil = nil, shard_number : Int32 | Nil = nil, sharding_method : ShardingMethod | Nil = nil, replication_factor : Int32 | Nil = nil, write_consistency_factor : Int32 | Nil = nil, on_disk_payload : Bool | Nil = nil, hnsw_config : HnswConfigDiff | Nil = nil, wal_config : WalConfigDiff | Nil = nil, optimizers_config : OptimizersConfigDiff | Nil = nil, quantization_config : QuantizationConfig | Nil = nil, sparse_vectors : Hash(String, SparseVectorParams) | Nil = nil, strict_mode_config : StrictModeConfig | Nil = nil, metadata : Hash(String, JSON::Any) | Nil = nil)
Initializes the object @param [Hash] attributes Model attributes in the form of hash
- .new(*, __pull_for_json_serializable pull : JSON::PullParser)
- .new(*, __context_for_yaml_serializable ctx : YAML::ParseContext, __node_for_yaml_serializable node : YAML::Nodes::Node)
Instance Method Summary
-
#==(other : self)
Returns
trueif this reference is the same as other. -
#hash(hasher)
See
Object#hash(hasher) -
#hnsw_config : HnswConfigDiff | Nil
Custom params for HNSW index.
-
#hnsw_config=(hnsw_config : HnswConfigDiff | Nil)
Custom params for HNSW index.
-
#list_invalid_properties
Show invalid properties with the reasons.
-
#metadata : Hash(String, JSON::Any) | Nil
Arbitrary JSON metadata for the collection This can be used to store application-specific information such as creation time, migration data, inference model info, etc.
-
#metadata=(metadata : Hash(String, JSON::Any) | Nil)
Arbitrary JSON metadata for the collection This can be used to store application-specific information such as creation time, migration data, inference model info, etc.
-
#on_disk_payload : Bool | Nil
If true - point's payload will not be stored in memory.
-
#on_disk_payload=(on_disk_payload : Bool | Nil)
If true - point's payload will not be stored in memory.
-
#optimizers_config : OptimizersConfigDiff | Nil
Custom params for Optimizers.
-
#optimizers_config=(optimizers_config : OptimizersConfigDiff | Nil)
Custom params for Optimizers.
-
#quantization_config : QuantizationConfig | Nil
Quantization parameters.
-
#quantization_config=(quantization_config : QuantizationConfig | Nil)
Quantization parameters.
-
#replication_factor : Int32 | Nil
Number of shards replicas.
-
#replication_factor=(value : Int32 | Nil)
Number of shards replicas.
- #replication_factor_validation_error(value) : String | Nil
-
#shard_number : Int32 | Nil
For auto sharding: Number of shards in collection.
-
#shard_number=(value : Int32 | Nil)
For auto sharding: Number of shards in collection.
- #shard_number_validation_error(value) : String | Nil
-
#sharding_method : ShardingMethod | Nil
Sharding method Default is Auto - points are distributed across all available shards Custom - points are distributed across shards according to shard key
-
#sharding_method=(sharding_method : ShardingMethod | Nil)
Sharding method Default is Auto - points are distributed across all available shards Custom - points are distributed across shards according to shard key
-
#sparse_vectors : Hash(String, SparseVectorParams) | Nil
Sparse vector data config.
-
#sparse_vectors=(sparse_vectors : Hash(String, SparseVectorParams) | Nil)
Sparse vector data config.
-
#strict_mode_config : StrictModeConfig | Nil
Strict-mode config.
-
#strict_mode_config=(strict_mode_config : StrictModeConfig | Nil)
Strict-mode config.
-
#valid?
Check to see if the all the properties in the model are valid @return true if the model is valid
-
#vectors : VectorsConfig | Nil
Optional properties
-
#vectors=(vectors : VectorsConfig | Nil)
Optional properties
-
#wal_config : WalConfigDiff | Nil
Custom params for WAL.
-
#wal_config=(wal_config : WalConfigDiff | Nil)
Custom params for WAL.
-
#write_consistency_factor : Int32 | Nil
Defines how many replicas should apply the operation for us to consider it successful.
-
#write_consistency_factor=(value : Int32 | Nil)
Defines how many replicas should apply the operation for us to consider it successful.
- #write_consistency_factor_validation_error(value) : String | Nil
Macros inherited from module Qdrant::Api::Validation
validates(name, klass, nilable, **rules)
validates
Instance methods inherited from module Qdrant::Api::Serializable
eql?(other)
eql?,
to_body : Hash(String, JSON::Any)
to_body,
to_h : Hash(String, JSON::Any)
to_h,
to_s(io : IO) : Nil
to_s
Constructor Detail
Initializes the object @param [Hash] attributes Model attributes in the form of hash
Instance Method Detail
Returns true if this reference is the same as other. Invokes same?.
Custom params for HNSW index. If none - values from service configuration file are used.
Custom params for HNSW index. If none - values from service configuration file are used.
Show invalid properties with the reasons. Usually used together with valid? @return Array for valid properties with the reasons
Arbitrary JSON metadata for the collection This can be used to store application-specific information such as creation time, migration data, inference model info, etc.
Arbitrary JSON metadata for the collection This can be used to store application-specific information such as creation time, migration data, inference model info, etc.
If true - point's payload 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
If true - point's payload 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
Custom params for Optimizers. If none - values from service configuration file are used.
Custom params for Optimizers. If none - values from service configuration file are used.
Quantization parameters. If none - quantization is disabled.
Quantization parameters. If none - quantization is disabled.
For auto sharding: Number of shards in collection. - Default is 1 for standalone, otherwise equal to the number of nodes - Minimum is 1 For custom sharding: Number of shards in collection per shard group. - Default is 1, meaning that each shard key will be mapped to a single shard - Minimum is 1
For auto sharding: Number of shards in collection. - Default is 1 for standalone, otherwise equal to the number of nodes - Minimum is 1 For custom sharding: Number of shards in collection per shard group. - Default is 1, meaning that each shard key will be mapped to a single shard - Minimum is 1
Sharding method Default is Auto - points are distributed across all available shards Custom - points are distributed across shards according to shard key
Sharding method Default is Auto - points are distributed across all available shards Custom - points are distributed across shards according to shard key
Sparse vector data config.
Check to see if the all the properties in the model are valid @return true if the model is valid
Custom params for WAL. If none - values from service configuration file are used.
Custom params for WAL. If none - values from service configuration file are used.
Defines how many replicas should apply the operation for us to consider it successful. Increasing this number will make the collection more resilient to inconsistencies, but will also make it fail if not enough replicas are available. Does not have any performance impact.
Defines how many replicas should apply the operation for us to consider it successful. Increasing this number will make the collection more resilient to inconsistencies, but will also make it fail if not enough replicas are available. Does not have any performance impact.