AzureOpenAIEmbeddingsOptions interface

  • Reference
Package:
@microsoft/teams-ai

Options for configuring an OpenAIEmbeddings to generate embeddings using an Azure OpenAI hosted model.

Extends
BaseOpenAIEmbeddingsOptions

Properties

azureApiKey

API key to use when making requests to Azure OpenAI.
azureApiVersion

Optional. Version of the API being called. Defaults to 2023-05-15.
azureDeployment

Name of the Azure OpenAI deployment (model) to use.
azureEndpoint

Deployment endpoint to use.

Inherited Properties

dimensions

Optional. Number of dimensions to use when generating embeddings.
logRequests

Optional. Whether to log requests to the console.
requestConfig

Optional. Request options to use when calling the OpenAI API.
retryPolicy

Optional. Retry policy to use when calling the OpenAI API.

Property Details

azureApiKey

API key to use when making requests to Azure OpenAI.

azureApiKey: string

Property Value

string

azureApiVersion

Optional. Version of the API being called. Defaults to 2023-05-15.

azureApiVersion?: string

Property Value

string

azureDeployment

Name of the Azure OpenAI deployment (model) to use.

azureDeployment: string

Property Value

string

azureEndpoint

Deployment endpoint to use.

azureEndpoint: string

Property Value

string

Inherited Property Details

dimensions

Optional. Number of dimensions to use when generating embeddings.

dimensions?: number

Property Value

number

Remarks

Only valid for embedding models that support dynamic dimensionality.

Inherited From BaseOpenAIEmbeddingsOptions.dimensions

logRequests

Optional. Whether to log requests to the console.

logRequests?: boolean

Property Value

boolean

Remarks

This is useful for debugging prompts and defaults to false.

Inherited From BaseOpenAIEmbeddingsOptions.logRequests

requestConfig

Optional. Request options to use when calling the OpenAI API.

requestConfig?: AxiosRequestConfig<any>

Property Value

AxiosRequestConfig<any>

Inherited From BaseOpenAIEmbeddingsOptions.requestConfig

retryPolicy

Optional. Retry policy to use when calling the OpenAI API.

retryPolicy?: number[]

Property Value

number[]

Remarks

The default retry policy is [2000, 5000] which means that the first retry will be after 2 seconds and the second retry will be after 5 seconds.

Inherited From BaseOpenAIEmbeddingsOptions.retryPolicy