VectorSearchCompression Class
Definition
Important
Some information relates to prerelease product that may be substantially modified before it’s released. Microsoft makes no warranties, express or implied, with respect to the information provided here.
Contains configuration options specific to the compression method used during indexing or querying. Please note VectorSearchCompression is the base class. According to the scenario, a derived class of the base class might need to be assigned here, or this property needs to be casted to one of the possible derived classes. The available derived classes include BinaryQuantizationCompression and ScalarQuantizationCompression.
public abstract class VectorSearchCompression[System.ClientModel.Primitives.PersistableModelProxy(typeof(Azure.Search.Documents.Models.UnknownVectorSearchCompression))]
public abstract class VectorSearchCompression : System.ClientModel.Primitives.IJsonModel<Azure.Search.Documents.Indexes.Models.VectorSearchCompression>, System.ClientModel.Primitives.IPersistableModel<Azure.Search.Documents.Indexes.Models.VectorSearchCompression>type VectorSearchCompression = class[<System.ClientModel.Primitives.PersistableModelProxy(typeof(Azure.Search.Documents.Models.UnknownVectorSearchCompression))>]
type VectorSearchCompression = class
interface IJsonModel<VectorSearchCompression>
interface IPersistableModel<VectorSearchCompression>Public MustInherit Class VectorSearchCompressionPublic MustInherit Class VectorSearchCompression
Implements IJsonModel(Of VectorSearchCompression), IPersistableModel(Of VectorSearchCompression)- Inheritance
-
VectorSearchCompression
- Derived
- Attributes
- Implements
Constructors
| VectorSearchCompression(String) |
Initializes a new instance of VectorSearchCompression. |
Properties
| CompressionName |
The name to associate with this particular configuration. |
| DefaultOversampling |
Default oversampling factor. Oversampling will internally request more documents (specified by this multiplier) in the initial search. This increases the set of results that will be reranked using recomputed similarity scores from full-precision vectors. Minimum value is 1, meaning no oversampling (1x). This parameter can only be set when rerankWithOriginalVectors is true. Higher values improve recall at the expense of latency. |
| RerankWithOriginalVectors |
If set to true, once the ordered set of results calculated using compressed vectors are obtained, they will be reranked again by recalculating the full-precision similarity scores. This will improve recall at the expense of latency. |
| RescoringOptions |
Contains the options for rescoring. |
| TruncationDimension |
The number of dimensions to truncate the vectors to. Truncating the vectors reduces the size of the vectors and the amount of data that needs to be transferred during search. This can save storage cost and improve search performance at the expense of recall. It should be only used for embeddings trained with Matryoshka Representation Learning (MRL) such as OpenAI text-embedding-3-large (small). The default value is null, which means no truncation. |
Methods
| JsonModelWriteCore(Utf8JsonWriter, ModelReaderWriterOptions) |
Explicit Interface Implementations
| IJsonModel<VectorSearchCompression>.Create(Utf8JsonReader, ModelReaderWriterOptions) |
Reads one JSON value (including objects or arrays) from the provided reader and converts it to a model. |
| IJsonModel<VectorSearchCompression>.Write(Utf8JsonWriter, ModelReaderWriterOptions) |
Writes the model to the provided Utf8JsonWriter. |
| IPersistableModel<VectorSearchCompression>.Create(BinaryData, ModelReaderWriterOptions) |
Converts the provided BinaryData into a model. |
| IPersistableModel<VectorSearchCompression>.GetFormatFromOptions(ModelReaderWriterOptions) |
Gets the data interchange format (JSON, Xml, etc) that the model uses when communicating with the service. |
| IPersistableModel<VectorSearchCompression>.Write(ModelReaderWriterOptions) |
Writes the model into a BinaryData. |
