OpenAI Embeddings Format

OpenAI Embeddings Format

This page overview

Official documentation

OpenAI Embeddings

📝 Introduction

Get vector representations of the provided input text. These vectors can be easily used by machine learning models and algorithms. For related guidance, see the Embeddings Guide.

Please note:

• Some models may have limits on the total number of input tokens
• You can use the sample Python code to calculate the number of tokens
• For example, the output vector dimension of the text-embedding-ada-002 model is 1536

💡 Request Examples

Create text embeddings ✅

curl https://4All API地址/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $4All API_API_KEY" \
  -d '{
    "input": "The food was delicious and the waiter...",
    "model": "text-embedding-ada-002",
    "encoding_format": "float"
  }'

Response example:

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

Create embeddings in batch ✅

curl https://4All API地址/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $4All API_API_KEY" \
  -d '{
    "input": ["The food was delicious", "The waiter was friendly"],
    "model": "text-embedding-ada-002",
    "encoding_format": "float"
  }'

Response example:

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [
        0.0023064255,
        // ... (1536 floating-point numbers)
      ],
      "index": 0
    },
    {
      "object": "embedding",
      "embedding": [
        -0.008815289,
        // ... (1536 floating-point numbers)
      ],
      "index": 1
    }
  ],
  "model": "text-embedding-ada-002",
  "usage": {
    "prompt_tokens": 12,
    "total_tokens": 12
  }
}

📮 Request

Endpoint

POST /v1/embeddings

Create embedding vectors that represent the input text.

Authentication Method

Include the following in the request headers for API key authentication:

Authorization: Bearer $4All API_API_KEY

Where $OPENAI_API_KEY is your API key.

Request Body Parameters

input

• Type: string or array
• Required: Yes

The input text to embed, encoded as a string or an array of tokens. To embed multiple inputs in a single request, pass an array of strings or an array of token arrays. The input must not exceed the model’s maximum input token limit (text-embedding-ada-002 supports up to 8192 tokens), must not be an empty string, and any array dimension must be less than or equal to 2048.

model

• Type: string
• Required: Yes

The model ID to use. You can use the List models API to view all available models, or refer to the model overview for their descriptions.

encoding_format

• Type: string
• Required: No
• Default: float

The format of the returned embeddings. Can be float or base64.

dimensions

• Type: integer
• Required: No

The number of dimensions the generated output embedding should have. Supported only for text-embedding-3 and later models.

user

• Type: string
• Required: No

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

📥 Response

Successful Response

Returns a list of embedding objects.

object

• Type: string
• Description: Object type, value is "list"

data

• Type: array
• Description: Array containing embedding objects
• Attributes:
• object: Object type, value is "embedding"
• embedding: Embedding vector, a list of floating-point numbers. The vector length depends on the model
• index: The index of the embedding in the list

model

• Type: string
• Description: The name of the model used

usage

• Type: object
• Description: Token usage statistics
• Attributes:
• prompt_tokens: Number of tokens used by the prompt
• total_tokens: Total number of tokens

Embedding Object

Represents the embedding vector returned by the embeddings endpoint.

{
  "object": "embedding",
  "embedding": [
    0.0023064255,
    -0.009327292,
    // ... (a total of 1536 floating-point numbers for ada-002)
    -0.0028842222
  ],
  "index": 0
}

index

• Type: integer
• Description: The index of the embedding in the list

embedding

• Type: array
• Description: Embedding vector, a list of floating-point numbers. The vector length depends on the model; see the Embeddings Guide for details

object

• Type: string
• Description: Object type, always "embedding"

Error Response

When a request fails, the API returns an error response object with an HTTP status code in the 4XX-5XX range.

Common Error Status Codes

• 401 Unauthorized: Invalid API key or API key not provided
• 400 Bad Request: Invalid request parameters, such as empty input or exceeding the token limit
• 429 Too Many Requests: API rate limit exceeded
• 500 Internal Server Error: Internal server error

Error response example:

{
  "error": {
    "message": "The input exceeds the maximum length. Please reduce the length of your input.",
    "type": "invalid_request_error",
    "param": "input",
    "code": "context_length_exceeded"
  }
}