One and only one of the two 'floatEmbedding' and 'quantizedEmbedding' will contain data, based on whether or not the embedder was configured to perform scalar quantization.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2024-05-07 UTC."],[],[],null,["# Embedding interface\n\n\u003cbr /\u003e\n\nList of embeddings with an optional timestamp.\n\nOne and only one of the two 'floatEmbedding' and 'quantizedEmbedding' will contain data, based on whether or not the embedder was configured to perform scalar quantization.\n\n**Signature:** \n\n export declare interface Embedding \n\nProperties\n----------\n\n| Property | Type | Description |\n|--------------------------------------------------------------------------|------------|------------------------------------------------------------------------------------------------------|\n| [floatEmbedding](./tasks-text.embedding#embeddingfloatembedding) | number\\[\\] | Floating-point embedding. Empty if the embedder was configured to perform scalar-quantization. |\n| [headIndex](./tasks-text.embedding#embeddingheadindex) | number | The index of the classifier head these categories refer to. This is useful for multi-head models. |\n| [headName](./tasks-text.embedding#embeddingheadname) | string | The name of the classifier head, which is the corresponding tensor metadata name. |\n| [quantizedEmbedding](./tasks-text.embedding#embeddingquantizedembedding) | Uint8Array | Scalar-quantized embedding. Empty if the embedder was not configured to perform scalar quantization. |\n\nEmbedding.floatEmbedding\n------------------------\n\nFloating-point embedding. Empty if the embedder was configured to perform scalar-quantization.\n\n**Signature:** \n\n floatEmbedding?: number[];\n\nEmbedding.headIndex\n-------------------\n\nThe index of the classifier head these categories refer to. This is useful for multi-head models.\n\n**Signature:** \n\n headIndex: number;\n\nEmbedding.headName\n------------------\n\nThe name of the classifier head, which is the corresponding tensor metadata name.\n\n**Signature:** \n\n headName: string;\n\nEmbedding.quantizedEmbedding\n----------------------------\n\nScalar-quantized embedding. Empty if the embedder was not configured to perform scalar quantization.\n\n**Signature:** \n\n quantizedEmbedding?: Uint8Array;"]]