Merge pull request alexrudall#269 from ch0ngxian/main

Move audios related methods to Audios.rb from Client.rb

Author: alexrudall

CHANGELOG.md

@@ -5,6 +5,18 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [5.0.0] - 2023-08-14
+
+### Added
+
+- Support multi-tenant use of the gem! Each client now holds its own config, so you can create unlimited clients in the same project, for example to Azure and OpenAI, or for different headers, access keys, etc.
+- [BREAKING-ish] This change should only break your usage of ruby-openai if you are directly calling class methods like `OpenAI::Client.get` for some reason, as they are now instance methods. Normal usage of the gem should be unaffected, just you can make new clients and they'll keep their own config if you want, overriding the global config.
+- Huge thanks to [@petergoldstein](https://github.com/petergoldstein) for his original work on this, [@cthulhu](https://github.com/cthulhu) for testing and many others for reviews and suggestions.
+
+### Changed
+
+- [BREAKING] Move audio related method to Audio model from Client model. You will need to update your code to handle this change, changing `client.translate` to `client.audio.translate` and `client.transcribe` to `client.audio.transcribe`.
+
 ## [4.3.2] - 2023-08-14
 
 ### Fixed

Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    ruby-openai (4.3.2)
+    ruby-openai (5.0.0)
       faraday (>= 1)
       faraday-multipart (>= 1)
 

README.md

@@ -417,7 +417,7 @@ Whisper is a speech to text model that can be used to generate text based on aud
 The translations API takes as input the audio file in any of the supported languages and transcribes the audio into English.
 
 ```ruby
-response = client.translate(
+response = client.audio.translate(
     parameters: {
         model: "whisper-1",
         file: File.open("path_to_file", "rb"),
@@ -431,7 +431,7 @@ puts response["text"]
 The transcriptions API takes as input the audio file you want to transcribe and returns the text in the desired output file format.
 
 ```ruby
-response = client.transcribe(
+response = client.audio.transcribe(
     parameters: {
         model: "whisper-1",
         file: File.open("path_to_file", "rb"),

lib/openai.rb

@@ -7,6 +7,7 @@
 require_relative "openai/finetunes"
 require_relative "openai/images"
 require_relative "openai/models"
+require_relative "openai/audio"
 require_relative "openai/version"
 
 module OpenAI

lib/openai/audio.rb

@@ -0,0 +1,15 @@
+module OpenAI
+  class Audio
+    def initialize(client:)
+      @client = client
+    end
+
+    def transcribe(parameters: {})
+      @client.multipart_post(path: "/audio/transcriptions", parameters: parameters)
+    end
+
+    def translate(parameters: {})
+      @client.multipart_post(path: "/audio/translations", parameters: parameters)
+    end
+  end
+end

lib/openai/client.rb

@@ -37,6 +37,10 @@ def embeddings(parameters: {})
       json_post(path: "/embeddings", parameters: parameters)
     end
 
+    def audio
+      @audio ||= OpenAI::Audio.new(client: self)
+    end
+
     def files
       @files ||= OpenAI::Files.new(client: self)
     end
@@ -57,14 +61,6 @@ def moderations(parameters: {})
       json_post(path: "/moderations", parameters: parameters)
     end
 
-    def transcribe(parameters: {})
-      multipart_post(path: "/audio/transcriptions", parameters: parameters)
-    end
-
-    def translate(parameters: {})
-      multipart_post(path: "/audio/translations", parameters: parameters)
-    end
-
     def azure?
       @api_type&.to_sym == :azure
     end

lib/openai/version.rb

@@ -1,3 +1,3 @@
 module OpenAI
-  VERSION = "4.3.2".freeze
+  VERSION = "5.0.0".freeze
 end

spec/fixtures/cassettes/whisper-1_translate.yml renamed to spec/fixtures/cassettes/audio_whisper-1_transcribe.yml

@@ -1,54 +1,56 @@
 RSpec.describe OpenAI::Client do
-  describe "#transcribe" do
-    context "with audio", :vcr do
-      let(:filename) { "audio_sample.mp3" }
-      let(:audio) { File.join(RSPEC_ROOT, "fixtures/files", filename) }
+  describe "#audio" do
+    describe "#transcribe" do
+      context "with audio", :vcr do
+        let(:filename) { "audio_sample.mp3" }
+        let(:audio) { File.join(RSPEC_ROOT, "fixtures/files", filename) }
 
-      let(:response) do
-        OpenAI::Client.new.transcribe(
-          parameters: {
-            model: model,
-            file: File.open(audio, "rb")
-          }
-        )
-      end
-      let(:content) { response["text"] }
-      let(:cassette) { "#{model} transcribe".downcase }
+        let(:response) do
+          OpenAI::Client.new.audio.transcribe(
+            parameters: {
+              model: model,
+              file: File.open(audio, "rb")
+            }
+          )
+        end
+        let(:content) { response["text"] }
+        let(:cassette) { "audio #{model} transcribe".downcase }
 
-      context "with model: whisper-1" do
-        let(:model) { "whisper-1" }
+        context "with model: whisper-1" do
+          let(:model) { "whisper-1" }
 
-        it "succeeds" do
-          VCR.use_cassette(cassette) do
-            expect(content.empty?).to eq(false)
+          it "succeeds" do
+            VCR.use_cassette(cassette) do
+              expect(content.empty?).to eq(false)
+            end
           end
         end
       end
     end
-  end
 
-  describe "#translate" do
-    context "with audio", :vcr do
-      let(:filename) { "audio_sample.mp3" }
-      let(:audio) { File.join(RSPEC_ROOT, "fixtures/files", filename) }
+    describe "#translate" do
+      context "with audio", :vcr do
+        let(:filename) { "audio_sample.mp3" }
+        let(:audio) { File.join(RSPEC_ROOT, "fixtures/files", filename) }
 
-      let(:response) do
-        OpenAI::Client.new.translate(
-          parameters: {
-            model: model,
-            file: File.open(audio, "rb")
-          }
-        )
-      end
-      let(:content) { response["text"] }
-      let(:cassette) { "#{model} translate".downcase }
+        let(:response) do
+          OpenAI::Client.new.audio.translate(
+            parameters: {
+              model: model,
+              file: File.open(audio, "rb")
+            }
+          )
+        end
+        let(:content) { response["text"] }
+        let(:cassette) { "audio #{model} translate".downcase }
 
-      context "with model: whisper-1" do
-        let(:model) { "whisper-1" }
+        context "with model: whisper-1" do
+          let(:model) { "whisper-1" }
 
-        it "succeeds" do
-          VCR.use_cassette(cassette) do
-            expect(content.empty?).to eq(false)
+          it "succeeds" do
+            VCR.use_cassette(cassette) do
+              expect(content.empty?).to eq(false)
+            end
           end
         end
       end