InferenceModelFactory.MultimodalMultiVectorEmbedding Method
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.
The result for one item when vectorKind is multi: one vector per token, for late-interaction (MaxSim) scoring.
public static Azure.Data.AI.MultimodalMultiVectorEmbedding MultimodalMultiVectorEmbedding(int index = 0, string id = default, Azure.Data.AI.EmbeddingContentKind contentKind = default, int? width = default, int? height = default, Azure.Data.AI.EmbeddingImageFormat? format = default, long? tokens = default, long? visualTokens = default, bool? isTruncated = default, long? inputTokens = default, System.Collections.Generic.IEnumerable<int> shape = default, BinaryData multiEmbedding = default);
static member MultimodalMultiVectorEmbedding : int * string * Azure.Data.AI.EmbeddingContentKind * Nullable<int> * Nullable<int> * Nullable<Azure.Data.AI.EmbeddingImageFormat> * Nullable<int64> * Nullable<int64> * Nullable<bool> * Nullable<int64> * seq<int> * BinaryData -> Azure.Data.AI.MultimodalMultiVectorEmbedding
Public Shared Function MultimodalMultiVectorEmbedding (Optional index As Integer = 0, Optional id As String = Nothing, Optional contentKind As EmbeddingContentKind = Nothing, Optional width As Nullable(Of Integer) = Nothing, Optional height As Nullable(Of Integer) = Nothing, Optional format As Nullable(Of EmbeddingImageFormat) = Nothing, Optional tokens As Nullable(Of Long) = Nothing, Optional visualTokens As Nullable(Of Long) = Nothing, Optional isTruncated As Nullable(Of Boolean) = Nothing, Optional inputTokens As Nullable(Of Long) = Nothing, Optional shape As IEnumerable(Of Integer) = Nothing, Optional multiEmbedding As BinaryData = Nothing) As MultimodalMultiVectorEmbedding
Parameters
- index
- Int32
The zero-based position of the item in the request.
- id
- String
The item's id from the request, if it had one.
- contentKind
- EmbeddingContentKind
The item's content kind, as supplied in the request's kind.
- format
- Nullable<EmbeddingImageFormat>
For images: the detected image format.
The tokens the model read for this item, including any text the service adds to queries and, for images, the image prompt and image tokens. For a truncated item, the tokens embedded. Omitted when the model doesn't report it.
true when the item was over the model's token limit and only its start was embedded; warnings then has an
EMBEDDING_INPUT_TRUNCATED entry for it. Omitted otherwise.
- shape
- IEnumerable<Int32>
The number of vectors and the number of dimensions: [vectors, dimensions].
- multiEmbedding
- BinaryData
The vectors: an array of arrays of numbers, or, when encodingFormat is base64, one base64 string of all their
little-endian outputDataKind values in row-major order. Decode it and reshape it to shape.
Returns
A new MultimodalMultiVectorEmbedding instance for mocking.