Optional
fields: Partial<OpenAIEmbeddingsParams> & Partial<AzureOpenAIInput> & { Optional
azureADTokenOptional
azureOptional
azureOptional
azureOptional
azureOptional
azureThe maximum number of documents to embed in a single request. This is limited by the OpenAI API to a maximum of 2048.
The async caller should be used by subclasses to make any async calls, which will thus benefit from the concurrency and retry logic.
Protected
clientProtected
clientOptional
dimensionsThe number of dimensions the resulting output embeddings should have.
Only supported in text-embedding-3
and later models.
Model name to use
Optional
organizationWhether to strip new lines from the input text. This is recommended by OpenAI for older models, but may not be suitable for all use cases. See: https://github.com/openai/openai-python/issues/418#issuecomment-1525939500
Optional
timeoutTimeout to use when making requests to OpenAI.
Method to generate embeddings for an array of documents. Splits the documents into batches and makes requests to the OpenAI API to generate embeddings.
Array of documents to generate embeddings for.
Promise that resolves to a 2D array of embeddings for each document.
Protected
embeddingPrivate method to make a request to the OpenAI API to generate embeddings. Handles the retry logic and returns the response from the API.
Request to send to the OpenAI API.
Promise that resolves to the response from the API.
Class for generating embeddings using the OpenAI API.
To use with Azure, import the
AzureOpenAIEmbeddings
class.Example