Class: LlamaEmbedding

Constructors

new LlamaEmbedding()

new LlamaEmbedding(options: LlamaEmbeddingOptions): LlamaEmbedding

Parameters

Parameter	Type
options	LlamaEmbeddingOptions

Returns

LlamaEmbedding

Defined in

evaluator/LlamaEmbedding.ts:13

Properties

vector

readonly vector: readonly number[];

Defined in

evaluator/LlamaEmbedding.ts:11

Methods

toJSON()

toJSON(): LlamaEmbeddingJSON

Returns

LlamaEmbeddingJSON

Defined in

evaluator/LlamaEmbedding.ts:17

---

calculateCosineSimilarity()

calculateCosineSimilarity(other: readonly number[] | LlamaEmbeddingJSON | LlamaEmbedding): number

Calculates the cosine similarity between this embedding and another embedding.

Note that you should only compare embeddings created by the exact same model file.

Parameters

Parameter	Type
other	readonly number[] | LlamaEmbeddingJSON | LlamaEmbedding

Returns

number

A value between 0 and 1 representing the similarity between the embedding vectors, where 1 means the embeddings are identical.

Defined in

evaluator/LlamaEmbedding.ts:31

---

fromJSON()

static fromJSON(json: LlamaEmbeddingJSON): LlamaEmbedding

Parameters

Parameter	Type
json	LlamaEmbeddingJSON

Returns

LlamaEmbedding

Defined in

evaluator/LlamaEmbedding.ts:65