Class: LLM::OpenAI::Responses

Inherits:

Object

• Object
• LLM::OpenAI::Responses

Defined in:

lib/llm/providers/openai/responses.rb

Overview

The LLM::OpenAI::Responses class provides an interface for OpenAI's response API.

Examples:

example #1

#!/usr/bin/env ruby
require "llm"

llm = LLM.openai(key: ENV["KEY"])
res1 = llm.responses.create "Your task is to answer the user's questions", role: :developer
res2 = llm.responses.create "5 + 5 = X ?", role: :user, previous_response_id: res1.id
[res1, res2].each { llm.responses.delete(_1) }

Instance Method Summary

• #create(prompt, params = {}) ⇒ LLM::Response

  Create a response.

• #delete(response) ⇒ LLM::Object

  Deletes a response.

• #get(response, **params) ⇒ LLM::Response

  Get a response.

• #initialize(provider) ⇒ LLM::OpenAI::Responses constructor

  Returns a new Responses object.

Constructor Details

#initialize(provider) ⇒ LLM::OpenAI::Responses

Returns a new Responses object

Parameters:

• provider (LLM::Provider)

# File 'lib/llm/providers/openai/responses.rb', line 24

def initialize(provider)
  @provider = provider
end

Instance Method Details

#create(prompt, params = {}) ⇒ LLM::Response

Create a response

Parameters:

• prompt (String) —

  The input prompt to be completed

• params (Hash) (defaults to: {}) —

  The parameters to maintain throughout the conversation. Any parameter the provider supports can be included and not only those listed here.

Returns:

• (LLM::Response)

Raises:

• (LLM::PromptError) —

  When given an object a provider does not understand

See Also:

• OpenAI docs

# File 'lib/llm/providers/openai/responses.rb', line 37

def create(prompt, params = {})
  params = {role: :user, model: @provider.default_model}.merge!(params)
  tools  = resolve_tools(params.delete(:tools))
  params = [params, adapt_schema(params), adapt_tools(tools)].inject({}, &:merge!).compact
  role, stream = params.delete(:role), params.delete(:stream)
  params[:stream] = true if stream.respond_to?(:<<) || stream == true
  req = Net::HTTP::Post.new("/v1/responses", headers)
  messages = [*(params.delete(:input) || []), LLM::Message.new(role, prompt)]
  body = LLM.json.dump({input: [adapt(messages, mode: :response)].flatten}.merge!(params))
  set_body_stream(req, StringIO.new(body))
  res = execute(request: req, stream:, stream_parser:)
  ResponseAdapter.adapt(res, type: :responds)
    .extend(Module.new { define_method(:__tools__) { tools } })
end

#delete(response) ⇒ LLM::Object

Deletes a response

Parameters:

• response (#id, #to_s) —

  Response ID

Returns:

• (LLM::Object) —

  Response body

See Also:

• OpenAI docs

# File 'lib/llm/providers/openai/responses.rb', line 72

def delete(response)
  response_id = response.respond_to?(:id) ? response.id : response
  req = Net::HTTP::Delete.new("/v1/responses/#{response_id}", headers)
  res = execute(request: req)
  LLM::Response.new(res)
end

#get(response, **params) ⇒ LLM::Response

Get a response

Parameters:

• response (#id, #to_s) —

  Response ID

Returns:

• (LLM::Response)

See Also:

• OpenAI docs

# File 'lib/llm/providers/openai/responses.rb', line 58

def get(response, **params)
  response_id = response.respond_to?(:id) ? response.id : response
  query = URI.encode_www_form(params)
  req = Net::HTTP::Get.new("/v1/responses/#{response_id}?#{query}", headers)
  res = execute(request: req)
  ResponseAdapter.adapt(res, type: :responds)
end