Class: Lammy::OpenAI

Inherits:
Object
  • Object
show all
Defined in:
lib/lammy/openai.rb

Overview

Use the OpenAI API’s Ruby library

Constant Summary collapse

MODELS = 
%w[
  gpt-4o gpt-4o-2024-08-06 gpt-4o-2024-05-13 gpt-4o chatgpt-4o-latest

  gpt-4o-mini gpt-4o-mini-2024-07-18

  o1-preview o1-preview-2024-09-12

  o1-mini o1-mini-2024-09-12

  gpt-3.5-turbo

  gpt-4-turbo gpt-4-turbo-2024-04-09 gpt-4 gpt-4-32k gpt-4-0125-preview gpt-4-1106-preview gpt-4-vision-preview
  gpt-3.5-turbo-0125 gpt-3.5-turbo-instruct gpt-3.5-turbo-1106 gpt-3.5-turbo-0613 gpt-3.5-turbo-16k-0613
  gpt-3.5-turbo-0301 davinci-002 babbage-002
].freeze
EMBEDDINGS = 
%w[
  text-embedding-3-small text-embedding-3-large text-embedding-ada-002
].freeze

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(settings) ⇒ OpenAI

Returns a new instance of OpenAI.



32
33
34
 
# File 'lib/lammy/openai.rb', line 32

def initialize(settings)
  @settings = settings
end

Instance Attribute Details

#settings ⇒ Object (readonly)

Returns the value of attribute settings.



30
31
32
 
# File 'lib/lammy/openai.rb', line 30

def settings
  @settings
end

Instance Method Details

#chat(user_message, system_message = nil, stream = nil) ⇒ Object

Generate a response with support for structured output



37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
 
# File 'lib/lammy/openai.rb', line 37

def chat(user_message, system_message = nil, stream = nil)
  schema = schema(settings)
  messages = messages(user_message, system_message)

  request = client.chat(
    parameters: {
      model: settings[:model],
      response_format: schema,
      messages: messages,
      stream: stream ? ->(chunk) { stream.call(stream_content(chunk)) } : nil
    }.compact
  )

  return stream if stream

  response = request.dig('choices', 0, 'message', 'content')
  content = schema ? ::Hashie::Mash.new(JSON.parse(response)) : response
  array?(schema) ? content.items : content
end

#embeddings(chunks) ⇒ Object

OpenAI’s text embeddings measure the relatedness of text strings. An embedding is a vector of floating point numbers. The distance between two vectors measures their relatedness. Small distances suggest high relatedness and large distances suggest low relatedness.



60
61
62
63
64
65
66
67
68
69
70
 
# File 'lib/lammy/openai.rb', line 60

def embeddings(chunks)
  responses = chunks.map do |chunk|
    response = client.embeddings(
      parameters: { model: settings[:model], dimensions: settings[:dimensions], input: chunk }
    )

    response.dig('data', 0, 'embedding')
  end

  responses.one? ? responses.first : responses
end