Embeddings

Create embeddings

embeddings.create(**kwargs) -> CreateEmbeddingResponse

post /embeddings

Creates an embedding vector representing the input text.

Parameters

input: String | Array[String] | Array[Integer] | Array[Array[Integer]]

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.
- String = String
  
  The string that will be turned into an embedding.
- ArrayOfStrings = Array[String]
  
  The array of strings that will be turned into an embedding.
- ArrayOfTokens = Array[Integer]
  
  The array of integers that will be turned into an embedding.
- ArrayOfTokenArrays = Array[Array[Integer]]
  
  The array of arrays containing integers that will be turned into an embedding.
model: String | 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.
- String = String
- EmbeddingModel = :"text-embedding-ada-002" | :"text-embedding-3-small" | :"text-embedding-3-large"
  - :"text-embedding-ada-002"
  - :"text-embedding-3-small"
  - :"text-embedding-3-large"
dimensions: Integer

The number of dimensions the resulting output embeddings should have. Only supported in text-embedding-3 and later models.
encoding_format: :float | :base64

The format to return the embeddings in. Can be either float or base64.
- :float
- :base64
user: String

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

Returns

class CreateEmbeddingResponse
- data: Array[Embedding]
  
  The list of embeddings generated by the model.
  - embedding: Array[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: Integer
    
    The index of the embedding in the list of embeddings.
  - object: :embedding
    
    The object type, which is always "embedding".
    - :embedding
- model: String
  
  The name of the model used to generate the embedding.
- object: :list
  
  The object type, which is always "list".
  - :list
- usage: Usage{ prompt_tokens, total_tokens}
  
  The usage information for the request.
  - prompt_tokens: Integer
    
    The number of tokens used by the prompt.
  - total_tokens: Integer
    
    The total number of tokens used by the request.

Example

require "openai"

openai = OpenAI::Client.new(api_key: "My API Key")

create_embedding_response = openai.embeddings.create(
  input: "The quick brown fox jumped over the lazy dog",
  model: :"text-embedding-3-small"
)

puts(create_embedding_response)

Response

{
  "data": [
    {
      "embedding": [
        0
      ],
      "index": 0,
      "object": "embedding"
    }
  ],
  "model": "model",
  "object": "list",
  "usage": {
    "prompt_tokens": 0,
    "total_tokens": 0
  }
}

Domain Types

Create Embedding Response

class CreateEmbeddingResponse
- data: Array[Embedding]
  
  The list of embeddings generated by the model.
  - embedding: Array[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: Integer
    
    The index of the embedding in the list of embeddings.
  - object: :embedding
    
    The object type, which is always "embedding".
    - :embedding
- model: String
  
  The name of the model used to generate the embedding.
- object: :list
  
  The object type, which is always "list".
  - :list
- usage: Usage{ prompt_tokens, total_tokens}
  
  The usage information for the request.
  - prompt_tokens: Integer
    
    The number of tokens used by the prompt.
  - total_tokens: Integer
    
    The total number of tokens used by the request.

Embedding

class Embedding

Represents an embedding vector returned by embedding endpoint.
- embedding: Array[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: Integer
  
  The index of the embedding in the list of embeddings.
- object: :embedding
  
  The object type, which is always "embedding".
  - :embedding

Embedding Model

EmbeddingModel = :"text-embedding-ada-002" | :"text-embedding-3-small" | :"text-embedding-3-large"
- :"text-embedding-ada-002"
- :"text-embedding-3-small"
- :"text-embedding-3-large"

ruby/resources/embeddings/index.md +218 −0 created

1# Embeddings

3## Create embeddings

5`embeddings.create(**kwargs) -> CreateEmbeddingResponse`

7**post** `/embeddings`

9Creates an embedding vector representing the input text.

11### Parameters

13- `input: String | Array[String] | Array[Integer] | Array[Array[Integer]]`

15 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](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) 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.

17 - `String = String`

19 The string that will be turned into an embedding.

21 - `ArrayOfStrings = Array[String]`

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

25 - `ArrayOfTokens = Array[Integer]`

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

29 - `ArrayOfTokenArrays = Array[Array[Integer]]`

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

33- `model: String | EmbeddingModel`

35 ID of the model to use. You can use the [List models](https://platform.openai.com/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](https://platform.openai.com/docs/models) for descriptions of them.

37 - `String = String`

39 - `EmbeddingModel = :"text-embedding-ada-002" | :"text-embedding-3-small" | :"text-embedding-3-large"`

41 - `:"text-embedding-ada-002"`

43 - `:"text-embedding-3-small"`

45 - `:"text-embedding-3-large"`

47- `dimensions: Integer`

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

51- `encoding_format: :float | :base64`

53 The format to return the embeddings in. Can be either `float` or [`base64`](https://pypi.org/project/pybase64/).

55 - `:float`

57 - `:base64`

59- `user: String`

61 A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).

63### Returns

65- `class CreateEmbeddingResponse`

67 - `data: Array[Embedding]`

69 The list of embeddings generated by the model.

71 - `embedding: Array[Float]`

73 The embedding vector, which is a list of floats. The length of vector depends on the model as listed in the [embedding guide](https://platform.openai.com/docs/guides/embeddings).

75 - `index: Integer`

77 The index of the embedding in the list of embeddings.

79 - `object: :embedding`

81 The object type, which is always "embedding".

83 - `:embedding`

85 - `model: String`

87 The name of the model used to generate the embedding.

89 - `object: :list`

91 The object type, which is always "list".

93 - `:list`

95 - `usage: Usage{ prompt_tokens, total_tokens}`

97 The usage information for the request.

99 - `prompt_tokens: Integer`

100

101 The number of tokens used by the prompt.

102

103 - `total_tokens: Integer`

104

105 The total number of tokens used by the request.

106

107### Example

108

109```ruby

110require "openai"

111

112openai = OpenAI::Client.new(api_key: "My API Key")

113

114create_embedding_response = openai.embeddings.create(

115 input: "The quick brown fox jumped over the lazy dog",

116 model: :"text-embedding-3-small"

117)

118

119puts(create_embedding_response)

120```

121

122#### Response

123

124```json

125{

126 "data": [

127 {

128 "embedding": [

129 0

130 ],

131 "index": 0,

132 "object": "embedding"

133 }

134 ],

135 "model": "model",

136 "object": "list",

137 "usage": {

138 "prompt_tokens": 0,

139 "total_tokens": 0

140 }

141}

142```

143

144## Domain Types

145

146### Create Embedding Response

147

148- `class CreateEmbeddingResponse`

149

150 - `data: Array[Embedding]`

151

152 The list of embeddings generated by the model.

153

154 - `embedding: Array[Float]`

155

156 The embedding vector, which is a list of floats. The length of vector depends on the model as listed in the [embedding guide](https://platform.openai.com/docs/guides/embeddings).

157

158 - `index: Integer`

159

160 The index of the embedding in the list of embeddings.

161

162 - `object: :embedding`

163

164 The object type, which is always "embedding".

165

166 - `:embedding`

167

168 - `model: String`

169

170 The name of the model used to generate the embedding.

171

172 - `object: :list`

173

174 The object type, which is always "list".

175

176 - `:list`

177

178 - `usage: Usage{ prompt_tokens, total_tokens}`

179

180 The usage information for the request.

181

182 - `prompt_tokens: Integer`

183

184 The number of tokens used by the prompt.

185

186 - `total_tokens: Integer`

187

188 The total number of tokens used by the request.

189

190### Embedding

191

192- `class Embedding`

193

194 Represents an embedding vector returned by embedding endpoint.

195

196 - `embedding: Array[Float]`

197

198 The embedding vector, which is a list of floats. The length of vector depends on the model as listed in the [embedding guide](https://platform.openai.com/docs/guides/embeddings).

199

200 - `index: Integer`

201

202 The index of the embedding in the list of embeddings.

203

204 - `object: :embedding`

205

206 The object type, which is always "embedding".

207

208 - `:embedding`

209

210### Embedding Model

211

212- `EmbeddingModel = :"text-embedding-ada-002" | :"text-embedding-3-small" | :"text-embedding-3-large"`

213

214 - `:"text-embedding-ada-002"`

215

216 - `:"text-embedding-3-small"`

217

218 - `:"text-embedding-3-large"`