Files
lancedb/docs/src/js/interfaces/embedding.EmbeddingFunction.md
Weston Pace e21b56293c docs: add a reference to @lancedb/lance in the docs (#1166)
We aren't yet ready to switch over the examples since almost all JS
examples rely on embeddings and we haven't yet ported those over.
However, this makes it possible for those that are interested to start
using `@lancedb/lancedb`
2024-04-05 16:34:39 -07:00

3.2 KiB

@lancedb/lancedb / Exports / embedding / EmbeddingFunction

Interface: EmbeddingFunction<T>

embedding.EmbeddingFunction

An embedding function that automatically creates vector representation for a given column.

Type parameters

Name
T

Implemented by

Table of contents

Properties

Properties

destColumn

Optional destColumn: string

The name of the column that will contain the embedding

By default this is "vector"

Defined in

embedding/embedding_function.ts:49


embed

embed: (data: T[]) => Promise<number[][]>

Creates a vector representation for the given values.

Type declaration

▸ (data): Promise<number[][]>

Creates a vector representation for the given values.

Parameters
Name Type
data T[]
Returns

Promise<number[][]>

Defined in

embedding/embedding_function.ts:62


embeddingDataType

Optional embeddingDataType: Float<Floats>

The data type of the embedding

The embedding function should return number. This will be converted into an Arrow float array. By default this will be Float32 but this property can be used to control the conversion.

Defined in

embedding/embedding_function.ts:33


embeddingDimension

Optional embeddingDimension: number

The dimension of the embedding

This is optional, normally this can be determined by looking at the results of embed. If this is not specified, and there is an attempt to apply the embedding to an empty table, then that process will fail.

Defined in

embedding/embedding_function.ts:42


excludeSource

Optional excludeSource: boolean

Should the source column be excluded from the resulting table

By default the source column is included. Set this to true and only the embedding will be stored.

Defined in

embedding/embedding_function.ts:57


sourceColumn

sourceColumn: string

The name of the column that will be used as input for the Embedding Function.

Defined in

embedding/embedding_function.ts:24