Skip to main content

Class: ClipEmbedding()

Extends​

ClipEmbedding<Options>(nodes, options?): Promise<BaseNode<Metadata>[]>

Type Parameters​

• Options extends Record<string, unknown>

Parameters​

• nodes: BaseNode<Metadata>[]

• options?: Options

Returns​

Promise<BaseNode<Metadata>[]>

Defined in​

packages/llamaindex/src/embeddings/ClipEmbedding.ts:29

Constructors​

new ClipEmbedding()​

new ClipEmbedding(): ClipEmbedding

Returns​

ClipEmbedding

Inherited from​

MultiModalEmbedding.constructor

Defined in​

packages/core/dist/embeddings/index.d.ts:36

Properties​

embedBatchSize​

embedBatchSize: number

Inherited from​

MultiModalEmbedding.embedBatchSize

Defined in​

packages/core/dist/embeddings/index.d.ts:34

embedInfo?​

optional embedInfo: EmbeddingInfo

Inherited from​

MultiModalEmbedding.embedInfo

Defined in​

packages/core/dist/embeddings/index.d.ts:35

getTextEmbeddings()​

getTextEmbeddings: (texts) => Promise<number[][]>

Optionally override this method to retrieve multiple embeddings in a single request

Parameters​

• texts: string[]

Returns​

Promise<number[][]>

Inherited from​

MultiModalEmbedding.getTextEmbeddings

Defined in​

packages/core/dist/embeddings/index.d.ts:44

id​

id: string

Inherited from​

MultiModalEmbedding.id

Defined in​

packages/core/dist/schema/index.d.ts:171

modelType​

modelType: ClipEmbeddingModelType = ClipEmbeddingModelType.XENOVA_CLIP_VIT_BASE_PATCH16

Defined in​

packages/llamaindex/src/embeddings/ClipEmbedding.ts:30

Methods​

getImageEmbedding()​

getImageEmbedding(image): Promise<number[]>

Parameters​

• image: ImageType

Returns​

Promise<number[]>

Overrides​

MultiModalEmbedding.getImageEmbedding

Defined in​

packages/llamaindex/src/embeddings/ClipEmbedding.ts:76

getImageEmbeddings()​

getImageEmbeddings(images): Promise<number[][]>

Optionally override this method to retrieve multiple image embeddings in a single request

Parameters​

• images: ImageType[]

Returns​

Promise<number[][]>

Inherited from​

MultiModalEmbedding.getImageEmbeddings

Defined in​

packages/llamaindex/src/embeddings/MultiModalEmbedding.ts:24

getProcessor()​

getProcessor(): Promise<Processor>

Returns​

Promise<Processor>

Defined in​

packages/llamaindex/src/embeddings/ClipEmbedding.ts:46

getQueryEmbedding()​

getQueryEmbedding(query): Promise<null | number[]>

Parameters​

• query: MessageContentDetail

Returns​

Promise<null | number[]>

Inherited from​

MultiModalEmbedding.getQueryEmbedding

Defined in​

packages/llamaindex/src/embeddings/MultiModalEmbedding.ts:58

getTextEmbedding()​

getTextEmbedding(text): Promise<number[]>

Parameters​

• text: string

Returns​

Promise<number[]>

Overrides​

MultiModalEmbedding.getTextEmbedding

Defined in​

packages/llamaindex/src/embeddings/ClipEmbedding.ts:83

getTextEmbeddingsBatch()​

getTextEmbeddingsBatch(texts, options?): Promise<number[][]>

Get embeddings for a batch of texts

Parameters​

• texts: string[]

• options?: BaseEmbeddingOptions

Returns​

Promise<number[][]>

Inherited from​

MultiModalEmbedding.getTextEmbeddingsBatch

Defined in​

packages/core/dist/embeddings/index.d.ts:50

getTextModel()​

getTextModel(): Promise<CLIPTextModelWithProjection>

Returns​

Promise<CLIPTextModelWithProjection>

Defined in​

packages/llamaindex/src/embeddings/ClipEmbedding.ts:65

getTokenizer()​

getTokenizer(): Promise<PreTrainedTokenizer>

Returns​

Promise<PreTrainedTokenizer>

Defined in​

packages/llamaindex/src/embeddings/ClipEmbedding.ts:38

getVisionModel()​

getVisionModel(): Promise<CLIPVisionModelWithProjection>

Returns​

Promise<CLIPVisionModelWithProjection>

Defined in​

packages/llamaindex/src/embeddings/ClipEmbedding.ts:54

similarity()​

similarity(embedding1, embedding2, mode?): number

Parameters​

• embedding1: number[]

• embedding2: number[]

• mode?: SimilarityType

Returns​

number

Inherited from​

MultiModalEmbedding.similarity

Defined in​

packages/core/dist/embeddings/index.d.ts:37

transform()​

transform(nodes, _options?): Promise<BaseNode<Metadata>[]>

Parameters​

• nodes: BaseNode<Metadata>[]

• _options?: any

Returns​

Promise<BaseNode<Metadata>[]>

Inherited from​

MultiModalEmbedding.transform

Defined in​

packages/llamaindex/src/embeddings/MultiModalEmbedding.ts:30

truncateMaxTokens()​

truncateMaxTokens(input): string[]

Parameters​

• input: string[]

Returns​

string[]

Inherited from​

MultiModalEmbedding.truncateMaxTokens

Defined in​

packages/core/dist/embeddings/index.d.ts:51