Module: AzureOpenaiClient::EmbeddingsCreateRequestInput

Defined in:
lib/azure_openai_client/models/embeddings_create_request_input.rb

Overview

Input text to get embeddings for, encoded as a string. To get embeddings for multiple inputs in a single request, pass an array of strings. Each input must not exceed 2048 tokens in length. Unless you are embedding code, we suggest replacing newlines (\n) in your input with a single space, as we have observed inferior results when newlines are present.

Class Method Summary collapse

Class Method Details

.build(data) ⇒ Object

Builds the object

Parameters:

  • Data (Mixed) —

    to be matched against the list of oneOf items

Returns:

  • (Object) —

    Returns the model or the data itself



31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
 
# File 'lib/azure_openai_client/models/embeddings_create_request_input.rb', line 31

def build(data)
  # Go through the list of oneOf items and attempt to identify the appropriate one.
  # Note:
  # - We do not attempt to check whether exactly one item matches.
  # - No advanced validation of types in some cases (e.g. "x: { type: string }" will happily match { x: 123 })
  #   due to the way the deserialization is made in the base_object template (it just casts without verifying).
  # - TODO: scalar values are de facto behaving as if they were nullable.
  # - TODO: logging when debugging is set.
  openapi_one_of.each do |klass|
    begin
      next if klass == :AnyType # "nullable: true"
      typed_data = find_and_cast_into_type(klass, data)
      return typed_data if typed_data
    rescue # rescue all errors so we keep iterating even if the current item lookup raises
    end
  end

  openapi_one_of.include?(:AnyType) ? data : nil
end

.openapi_one_of ⇒ Object

List of class defined in oneOf (OpenAPI v3)



21
22
23
24
25
26
 
# File 'lib/azure_openai_client/models/embeddings_create_request_input.rb', line 21

def openapi_one_of
  [
    :'Array<String>',
    :'String'
  ]
end