Class: OpenAIEmbedding

Hierarchy

• BaseEmbedding

  ↳ OpenAIEmbedding

  ↳↳ FireworksEmbedding

  ↳↳ TogetherEmbedding

Constructors

constructor

• new OpenAIEmbedding(init?): OpenAIEmbedding

OpenAI Embedding

Parameters

Name	Type	Description
init?	Partial<OpenAIEmbedding> & { azure?: AzureOpenAIConfig }	initial parameters

Returns

OpenAIEmbedding

Overrides

BaseEmbedding.constructor

Defined in

packages/core/src/embeddings/OpenAIEmbedding.ts:57

Properties

additionalSessionOptions

• Optional additionalSessionOptions: Omit<Partial<ClientOptions>, "apiKey" | "timeout" | "maxRetries">

other session options for OpenAI

Defined in

packages/core/src/embeddings/OpenAIEmbedding.ts:45

---

apiKey

• Optional apiKey: string = undefined

api key

Defined in

packages/core/src/embeddings/OpenAIEmbedding.ts:39

---

dimensions

• dimensions: undefined | number

number of dimensions of the resulting vector, for models that support choosing fewer dimensions. undefined will default to model default

Defined in

packages/core/src/embeddings/OpenAIEmbedding.ts:34

---

embedBatchSize

• embedBatchSize: number = DEFAULT_EMBED_BATCH_SIZE

Inherited from

BaseEmbedding.embedBatchSize

Defined in

packages/core/src/embeddings/types.ts:9

---

maxRetries

• maxRetries: number

maximum number of retries, default 10

Defined in

packages/core/src/embeddings/OpenAIEmbedding.ts:41

---

model

• model: string

embeddding model. defaults to "text-embedding-ada-002"

Defined in

packages/core/src/embeddings/OpenAIEmbedding.ts:32

---

session

• session: OpenAISession

session object

Defined in

packages/core/src/embeddings/OpenAIEmbedding.ts:51

---

timeout

• Optional timeout: number

timeout in ms, default 60 seconds

Defined in

packages/core/src/embeddings/OpenAIEmbedding.ts:43

Methods

getOpenAIEmbedding

▸ getOpenAIEmbedding(input): Promise<number[][]>

Get embeddings for a batch of texts

Parameters

Name	Type
input	string[]

Returns

Promise<number[][]>

Defined in

packages/core/src/embeddings/OpenAIEmbedding.ts:111

---

getQueryEmbedding

▸ getQueryEmbedding(query): Promise<number[]>

Get embeddings for a query

Parameters

Name	Type
query	string

Returns

Promise<number[]>

Overrides

BaseEmbedding.getQueryEmbedding

Defined in

packages/core/src/embeddings/OpenAIEmbedding.ts:142

---

getTextEmbedding

▸ getTextEmbedding(text): Promise<number[]>

Get embeddings for a single text

Parameters

Name	Type
text	string

Returns

Promise<number[]>

Overrides

BaseEmbedding.getTextEmbedding

Defined in

packages/core/src/embeddings/OpenAIEmbedding.ts:133

---

getTextEmbeddings

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

Get embeddings for a batch of texts

Parameters

Name	Type
texts	string[]

Returns

Promise<number[][]>

Overrides

BaseEmbedding.getTextEmbeddings

Defined in

packages/core/src/embeddings/OpenAIEmbedding.ts:125

---

getTextEmbeddingsBatch

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

Get embeddings for a batch of texts

Parameters

Name	Type
texts	string[]
options?	Object
options.logProgress?	boolean

Returns

Promise<number[][]>

Inherited from

BaseEmbedding.getTextEmbeddingsBatch

Defined in

packages/core/src/embeddings/types.ts:42

---

similarity

▸ similarity(embedding1, embedding2, mode?): number

Parameters

Name	Type	Default value
embedding1	number[]	undefined
embedding2	number[]	undefined
mode	SimilarityType	SimilarityType.DEFAULT

Returns

number

Inherited from

BaseEmbedding.similarity

Defined in

packages/core/src/embeddings/types.ts:11

---

transform

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

Parameters

Name	Type
nodes	BaseNode<Metadata>[]
_options?	any

Returns

Promise<BaseNode<Metadata>[]>

Inherited from

BaseEmbedding.transform

Defined in

packages/core/src/embeddings/types.ts:73