Create embeddings

embeddings.create() -> CreateEmbeddingResponse

POST/embeddings

Creates an embedding vector representing the input text.

ParametersExpand Collapse

input: Union[str, SequenceNotStr[str], Iterable[int], Iterable[Iterable[int]]]

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 all embedding models), cannot be an empty string, and any array must be 2048 dimensions or less. Example Python code for counting tokens. In addition to the per-input token limit, all embedding models enforce a maximum of 300,000 tokens summed across all inputs in a single request.

Accepts one of the following:

str

The string that will be turned into an embedding.

SequenceNotStr[str]

The array of strings that will be turned into an embedding.

Iterable[int]

The array of integers that will be turned into an embedding.

Iterable[Iterable[int]]

The array of arrays containing integers that will be turned into an embedding.

model: Union[str, EmbeddingModel]

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.

Accepts one of the following:

str

Literal["text-embedding-ada-002", "text-embedding-3-small", "text-embedding-3-large"]

Accepts one of the following:

"text-embedding-ada-002"

"text-embedding-3-small"

"text-embedding-3-large"

dimensions: Optional[int]

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

minimum1

encoding_format: Optional[Literal["float", "base64"]]

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

Accepts one of the following:

"float"

"base64"

user: Optional[str]

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

ReturnsExpand Collapse

class CreateEmbeddingResponse: …

data: List[Embedding]

The list of embeddings generated by the model.

embedding: List[float]

The embedding vector, which is a list of floats. The length of vector depends on the model as listed in the embedding guide.

index: int

The index of the embedding in the list of embeddings.

object: Literal["embedding"]

The object type, which is always "embedding".

model: str

The name of the model used to generate the embedding.

object: Literal["list"]

The object type, which is always "list".

usage: Usage

The usage information for the request.

prompt_tokens: int

The number of tokens used by the prompt.

total_tokens: int

The total number of tokens used by the request.

Create embeddings

from openai import OpenAI
client = OpenAI()

client.embeddings.create(
  model="text-embedding-ada-002",
  input="The food was delicious and the waiter...",
  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
  }
}

Returns Examples

{
  "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
  }
}