Create embeddings

Creates an embedding vector representing the input text.

curl --location --request POST 'https://api.openai.com/v1/embeddings' \ --header 'Authorization: Bearer $OPENAI_API_KEY' \ --header 'Content-Type: application/json' \ --data-raw '{ "input": "The food was delicious and the waiter...", "model": "text-embedding-ada-002", "encoding_format": "float" }'

{ "object": "list", "data": [ { "object": "embedding", "embedding": [ 0.0023064255, -0.009327292, .... (1536 floats total for ada-002) -0.0028842222, ], "index": 0 } ], "model": "text-embedding-ada-002", "usage": { "prompt_tokens": 8, "total_tokens": 8 } }

Request

Authorization

Provide your bearer token in the

Authorization

header when making requests to protected resources.

Example:

Authorization: Bearer ********************

Header Params

Authorization

string

required

Example:

Bearer $OPENAI_API_KEY

Content-Type

string

required

Example:

application/json

Body Params application/json

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. Example Python code for counting tokens.

model

string

required

ID of the model to use. You can use the List models API to see all of your available models, or see our Model overview for descriptions of them.

encoding_format

string

required

The format to return the embeddings in. Can be either float or base64.

Examples

application/json

Body

object

string

required

data

array [object {3}]

required

object

string

optional

embedding

array[number]

optional

index

integer

optional

model

string

required

usage

object

required

prompt_tokens

integer

required

total_tokens

integer

required

Request

Responses