Class OllamaEmbeddings

Hierarchy (View Summary)

BaseDynamicToolInput
- OllamaEmbeddings

Index

Constructors

Properties

baseUrl client keepAlive? model requestOptions? truncate

Methods

_convertOptions embedDocuments embedQuery

Constructors

constructor

new OllamaEmbeddings(fields?: OllamaEmbeddingsParams): OllamaEmbeddings
Parameters
- Optionalfields: OllamaEmbeddingsParams
Returns OllamaEmbeddings
Overrides Embeddings.constructor
- Defined in remotes/langchain-ai/langchainjs/v1/libs/providers/langchain-ollama/src/embeddings.ts:69

Properties

baseUrl

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

client

client: Ollama

`Optional`keepAlive

keepAlive?: string | number

model

model: string = "mxbai-embed-large"

`Optional`requestOptions

requestOptions?: Partial<Options>

truncate

truncate: boolean = false

Methods

_convertOptions

_convertOptions(requestOptions: OllamaCamelCaseOptions): Partial<OllamaOptions>
convert camelCased Ollama request options like "useMMap" to the snake_cased equivalent which the ollama API actually uses. Used only for consistency with the llms/Ollama and chatModels/Ollama classes
Parameters
- requestOptions: OllamaCamelCaseOptions
Returns Partial<OllamaOptions>
- Defined in remotes/langchain-ai/langchainjs/v1/libs/providers/langchain-ollama/src/embeddings.ts:91

embedDocuments

embedDocuments(texts: string[]): Promise<number[][]>
Parameters
- texts: string[]
Returns Promise<number[][]>
- Defined in remotes/langchain-ai/langchainjs/v1/libs/providers/langchain-ollama/src/embeddings.ts:141

embedQuery

embedQuery(text: string): Promise<number[]>
Parameters
- text: string
Returns Promise<number[]>
- Defined in remotes/langchain-ai/langchainjs/v1/libs/providers/langchain-ollama/src/embeddings.ts:145