Class OllamaEmbeddings

Hierarchy

Embeddings
- OllamaEmbeddings

Index

Constructors

Properties

baseUrl caller client keepAlive model requestOptions? truncate

Methods

embedDocuments embedQuery

Constructors

constructor

new OllamaEmbeddings(fields?): OllamaEmbeddings
Parameters
- Optionalfields: OllamaEmbeddingsParams
Returns OllamaEmbeddings
Overrides Embeddings.constructor
- Defined in libs/langchain-ollama/src/embeddings.ts:56

Properties

baseUrl

baseUrl: string = "http://localhost:11434"

caller

caller: AsyncCaller

The async caller should be used by subclasses to make any async calls, which will thus benefit from the concurrency and retry logic.

client

client: Ollama

keepAlive

keepAlive: string = "5m"

model

model: string = "mxbai-embed-large"

`Optional`requestOptions

requestOptions?: Partial<Options>

truncate

truncate: boolean = false

Methods

embedDocuments

embedDocuments(texts): Promise<number[][]>
An abstract method that takes an array of documents as input and returns a promise that resolves to an array of vectors for each document.
Parameters
- texts: string[]
Returns Promise<number[][]>
A promise that resolves to an array of vectors for each document.
Overrides Embeddings.embedDocuments
- Defined in libs/langchain-ollama/src/embeddings.ts:123

embedQuery

embedQuery(text): Promise<number[]>
An abstract method that takes a single document as input and returns a promise that resolves to a vector for the query document.
Parameters
- text: string
Returns Promise<number[]>
A promise that resolves to a vector for the query document.
Overrides Embeddings.embedQuery
- Defined in libs/langchain-ollama/src/embeddings.ts:127