Oxygen
  • Getting started
  • Introduction
  • Authentication
  • Making requests
  • Streaming
  • Endpoints
    • Chat
    • Image
    • Audio
    • Embeddings
Powered by GitBook
On this page
  1. Endpoints

Embeddings

PreviousAudio

Last updated 1 year ago

ENDPOINT : https://app.oxyapi.uk/v1/embeddings

input [string] REQUIRED

  • Input text to embed, encoded as a string or array of tokens. To embed multiple inputs in a single request, pass an array of strings or array of token arrays. The input must not exceed the max input tokens for the model (8192 tokens for text-embedding-ada-002), cannot be an empty string, and any array must be 2048 dimensions or less. for counting tokens.

model [string] REQUIRED

  • ID of the model to use. See the table for details on which models work with the Embedding API..

encoding_format [string] Optional Defaults to float

  • The format to return the embeddings in. Can be either float or .

dimensions [integer] Optional

  • The number of dimensions the resulting output embeddings should have. Only supported in text-embedding-3 and later models.

user [string] Optional

  • A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. .

Example Python code
model endpoint compatibility
base64
Learn more