ruby-openai 3.4.0 → 3.6.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f3d2b8f98be44b7f33fce40f271bccc3dc1c72237df7ad64baed43f4ea79fb51
-  data.tar.gz: f19cc5e7155b47e6f7ccb7c5642679e5d8f7a6600e6d4f9e592ebc16313b74f0
+  metadata.gz: 0cee1b8ea9256b9e74487bd152c640acf176ee65f7860521b3ee9f0901dddb5f
+  data.tar.gz: 12bb3313fbcfd6d9098a13975b2ea9784126e603a321a63e4540891efbf720ab
 SHA512:
-  metadata.gz: 8f2c05fae48718593ea7990c480f6108844a698a943c8db2e3e01f3e31e95ede1ca2a5bd0dec5364a9b1730698c3802e24eecec585d20e59b03e1a421c8a3c4e
-  data.tar.gz: 303d6df6cea50a4f9ac50f8cab7329e585e201aeb2532709b161b830896cc1e733e0c48dfa6ebff22d13d930c3a0ff76425b8e0294c7e175a1bc4e07b84710a2
+  metadata.gz: c684505ae1469c9066c2b6731dc6e9ee32b4efed151a005bf83f6c070991d60d714122bb10dc7a6239dcbf99fbee9486397d22de0df74287754ac5088460732c
+  data.tar.gz: 70381208b506f04536ced0db66b1519e34d3dfc368796c9f17e7994fa8f95d46f902746f4513ae570a7e41d36d788a88c6ca69f6b999b88ad6be247f6547b913

data/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).
 
+## [3.6.0] - 2023-03-22
+
+### Added
+
+- Add much-needed ability to increase HTTParty timeout, and set default to 120 seconds. Thanks to [@mbackermann](https://github.com/mbackermann) for the PR and to everyone who requested this!
+
+## [3.5.0] - 2023-03-02
+
+### Added
+
+- Add Client#transcribe and Client translate endpoints - Whisper over the wire! Thanks to [@Clemalfroy](https://github.com/Clemalfroy)
+
 ## [3.4.0] - 2023-03-01
 
 ### Added

data/Gemfile

@@ -7,6 +7,6 @@ gem "byebug", "~> 11.1.3"
 gem "dotenv", "~> 2.8.1"
 gem "rake", "~> 13.0"
 gem "rspec", "~> 3.12"
-gem "rubocop", "~> 1.46.0"
+gem "rubocop", "~> 1.48.1"
 gem "vcr", "~> 6.1.0"
 gem "webmock", "~> 3.18.1"

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    ruby-openai (3.4.0)
+    ruby-openai (3.6.0)
       httparty (>= 0.18.1)
 
 GEM
@@ -23,7 +23,7 @@ GEM
     mini_mime (1.1.2)
     multi_xml (0.6.0)
     parallel (1.22.1)
-    parser (3.2.1.0)
+    parser (3.2.1.1)
       ast (~> 2.4.1)
     public_suffix (5.0.1)
     rainbow (3.1.1)
@@ -43,7 +43,7 @@ GEM
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.12.0)
     rspec-support (3.12.0)
-    rubocop (1.46.0)
+    rubocop (1.48.1)
       json (~> 2.3)
       parallel (~> 1.10)
       parser (>= 3.2.0.0)
@@ -53,9 +53,9 @@ GEM
       rubocop-ast (>= 1.26.0, < 2.0)
       ruby-progressbar (~> 1.7)
       unicode-display_width (>= 2.4.0, < 3.0)
-    rubocop-ast (1.26.0)
+    rubocop-ast (1.27.0)
       parser (>= 3.2.1.0)
-    ruby-progressbar (1.11.0)
+    ruby-progressbar (1.13.0)
     unicode-display_width (2.4.2)
     vcr (6.1.0)
     webmock (3.18.1)
@@ -71,7 +71,7 @@ DEPENDENCIES
   dotenv (~> 2.8.1)
   rake (~> 13.0)
   rspec (~> 3.12)
-  rubocop (~> 1.46.0)
+  rubocop (~> 1.48.1)
   ruby-openai!
   vcr (~> 6.1.0)
   webmock (~> 3.18.1)

data/README.md

@@ -7,16 +7,16 @@
 
 Use the [OpenAI API](https://openai.com/blog/openai-api/) with Ruby! 🤖❤️
 
-Generate text with ChatGPT, create images with DALL·E, or write code with Codex...
+Generate text with ChatGPT, transcribe or translate audio with Whisper, create images with DALL·E, or write code with Codex...
 
-## Installation
+Check out [Ruby AI Builders](https://discord.gg/k4Uc224xVD) on Discord!
 
 ### Bundler
 
 Add this line to your application's Gemfile:
 
 ```ruby
-    gem "ruby-openai"
+gem "ruby-openai"
 ```
 
 And then execute:
@@ -32,7 +32,7 @@ $ gem install ruby-openai
 and require with:
 
 ```ruby
-    require "openai"
+require "openai"
 ```
 
 ## Upgrading
@@ -49,7 +49,7 @@ The `::Ruby::OpenAI` module has been removed and all classes have been moved und
 For a quick test you can pass your token directly to a new client:
 
 ```ruby
-    client = OpenAI::Client.new(access_token: "access_token_goes_here")
+client = OpenAI::Client.new(access_token: "access_token_goes_here")
 ```
 
 ### With Config
@@ -57,16 +57,34 @@ For a quick test you can pass your token directly to a new client:
 For a more robust setup, you can configure the gem with your API keys, for example in an `openai.rb` initializer file. Never hardcode secrets into your codebase - instead use something like [dotenv](https://github.com/motdotla/dotenv) to pass the keys safely into your environments.
 
 ```ruby
-    OpenAI.configure do |config|
-        config.access_token = ENV.fetch('OPENAI_ACCESS_TOKEN')
-        config.organization_id = ENV.fetch('OPENAI_ORGANIZATION_ID') # Optional.
-    end
+OpenAI.configure do |config|
+    config.access_token = ENV.fetch('OPENAI_ACCESS_TOKEN')
+    config.organization_id = ENV.fetch('OPENAI_ORGANIZATION_ID') # Optional.
+end
 ```
 
 Then you can create a client like this:
 
 ```ruby
-    client = OpenAI::Client.new
+client = OpenAI::Client.new
+```
+
+#### Setting request timeout
+
+The default timeout for any OpenAI request is 120 seconds. You can change that passing the `request_timeout` when initializing the client:
+
+```ruby
+    client = OpenAI::Client.new(access_token: "access_token_goes_here", request_timeout: 25)
+```
+
+or when configuring the gem:
+
+```ruby
+    OpenAI.configure do |config|
+        config.access_token = ENV.fetch('OPENAI_ACCESS_TOKEN')
+        config.organization_id = ENV.fetch('OPENAI_ORGANIZATION_ID') # Optional.
+        config.request_timeout = 25 # Optional
+    end
 ```
 
 ### Models
@@ -74,8 +92,8 @@ Then you can create a client like this:
 There are different models that can be used to generate text. For a full list and to retrieve information about a single models:
 
 ```ruby
-    client.models.list
-    client.models.retrieve(id: "text-ada-001")
+client.models.list
+client.models.retrieve(id: "text-ada-001")
 ```
 
 #### Examples
@@ -91,17 +109,17 @@ There are different models that can be used to generate text. For a full list an
 
 ### ChatGPT
 
-ChatGPT is a model that can be used to generate text in a conversational style. You can use it to generate a response to a sequence of [messages](https://platform.openai.com/docs/guides/chat/introduction):
+ChatGPT is a model that can be used to generate text in a conversational style. You can use it to [generate a response](https://platform.openai.com/docs/api-reference/chat/create) to a sequence of [messages](https://platform.openai.com/docs/guides/chat/introduction):
 
 ```ruby
-    response = client.chat(
-        parameters: {
-            model: "gpt-3.5-turbo",
-            messages: [{ role: "user", content: "Hello!"}],
-        })
-    puts response.dig("choices", 0, "message", "content")
-    => "Hello! How may I assist you today?"
-
+response = client.chat(
+    parameters: {
+        model: "gpt-3.5-turbo", # Required.
+        messages: [{ role: "user", content: "Hello!"}], # Required.
+        temperature: 0.7,
+    })
+puts response.dig("choices", 0, "message", "content")
+# => "Hello! How may I assist you today?"
 ```
 
 ### Completions
@@ -109,14 +127,14 @@ ChatGPT is a model that can be used to generate text in a conversational style.
 Hit the OpenAI API for a completion using other GPT-3 models:
 
 ```ruby
-    response = client.completions(
-        parameters: {
-            model: "text-davinci-001",
-            prompt: "Once upon a time",
-            max_tokens: 5
-        })
-    puts response["choices"].map { |c| c["text"] }
-    => [", there lived a great"]
+response = client.completions(
+    parameters: {
+        model: "text-davinci-001",
+        prompt: "Once upon a time",
+        max_tokens: 5
+    })
+puts response["choices"].map { |c| c["text"] }
+# => [", there lived a great"]
 ```
 
 ### Edits
@@ -124,15 +142,15 @@ Hit the OpenAI API for a completion using other GPT-3 models:
 Send a string and some instructions for what to do to the string:
 
 ```ruby
-    response = client.edits(
-        parameters: {
-            model: "text-davinci-edit-001",
-            input: "What day of the wek is it?",
-            instruction: "Fix the spelling mistakes"
-        }
-    )
-    puts response.dig("choices", 0, "text")
-    => What day of the week is it?
+response = client.edits(
+    parameters: {
+        model: "text-davinci-edit-001",
+        input: "What day of the wek is it?",
+        instruction: "Fix the spelling mistakes"
+    }
+)
+puts response.dig("choices", 0, "text")
+# => What day of the week is it?
 ```
 
 ### Embeddings
@@ -140,12 +158,12 @@ Send a string and some instructions for what to do to the string:
 You can use the embeddings endpoint to get a vector of numbers representing an input. You can then compare these vectors for different inputs to efficiently check how similar the inputs are.
 
 ```ruby
-    client.embeddings(
-        parameters: {
-            model: "babbage-similarity",
-            input: "The food was delicious and the waiter..."
-        }
-    )
+client.embeddings(
+    parameters: {
+        model: "babbage-similarity",
+        input: "The food was delicious and the waiter..."
+    }
+)
 ```
 
 ### Files
@@ -153,18 +171,18 @@ You can use the embeddings endpoint to get a vector of numbers representing an i
 Put your data in a `.jsonl` file like this:
 
 ```json
-    {"prompt":"Overjoyed with my new phone! ->", "completion":" positive"}
-    {"prompt":"@lakers disappoint for a third straight night ->", "completion":" negative"}
+{"prompt":"Overjoyed with my new phone! ->", "completion":" positive"}
+{"prompt":"@lakers disappoint for a third straight night ->", "completion":" negative"}
 ```
 
 and pass the path to `client.files.upload` to upload it to OpenAI, and then interact with it:
 
 ```ruby
-    client.files.upload(parameters: { file: "path/to/sentiment.jsonl", purpose: "fine-tune" })
-    client.files.list
-    client.files.retrieve(id: 123)
-    client.files.content(id: 123)
-    client.files.delete(id: 123)
+client.files.upload(parameters: { file: "path/to/sentiment.jsonl", purpose: "fine-tune" })
+client.files.list
+client.files.retrieve(id: 123)
+client.files.content(id: 123)
+client.files.delete(id: 123)
 ```
 
 ### Fine-tunes
@@ -172,51 +190,51 @@ and pass the path to `client.files.upload` to upload it to OpenAI, and then inte
 Upload your fine-tuning data in a `.jsonl` file as above and get its ID:
 
 ```ruby
-    response = client.files.upload(parameters: { file: "path/to/sentiment.jsonl", purpose: "fine-tune" })
-    file_id = JSON.parse(response.body)["id"]
+response = client.files.upload(parameters: { file: "path/to/sentiment.jsonl", purpose: "fine-tune" })
+file_id = JSON.parse(response.body)["id"]
 ```
 
 You can then use this file ID to create a fine-tune model:
 
 ```ruby
-    response = client.finetunes.create(
-        parameters: {
-        training_file: file_id,
-        model: "text-ada-001"
-    })
-    fine_tune_id = JSON.parse(response.body)["id"]
+response = client.finetunes.create(
+    parameters: {
+    training_file: file_id,
+    model: "text-ada-001"
+})
+fine_tune_id = JSON.parse(response.body)["id"]
 ```
 
 That will give you the fine-tune ID. If you made a mistake you can cancel the fine-tune model before it is processed:
 
 ```ruby
-    client.finetunes.cancel(id: fine_tune_id)
+client.finetunes.cancel(id: fine_tune_id)
 ```
 
 You may need to wait a short time for processing to complete. Once processed, you can use list or retrieve to get the name of the fine-tuned model:
 
 ```ruby
-    client.finetunes.list
-    response = client.finetunes.retrieve(id: fine_tune_id)
-    fine_tuned_model = JSON.parse(response.body)["fine_tuned_model"]
+client.finetunes.list
+response = client.finetunes.retrieve(id: fine_tune_id)
+fine_tuned_model = JSON.parse(response.body)["fine_tuned_model"]
 ```
 
 This fine-tuned model name can then be used in completions:
 
 ```ruby
-    response = client.completions(
-        parameters: {
-            model: fine_tuned_model,
-            prompt: "I love Mondays!"
-        }
-    )
-    JSON.parse(response.body)["choices"].map { |c| c["text"] }
+response = client.completions(
+    parameters: {
+        model: fine_tuned_model,
+        prompt: "I love Mondays!"
+    }
+)
+JSON.parse(response.body)["choices"].map { |c| c["text"] }
 ```
 
 You can delete the fine-tuned model when you are done with it:
 
 ```ruby
-    client.finetunes.delete(fine_tuned_model: fine_tuned_model)
+client.finetunes.delete(fine_tuned_model: fine_tuned_model)
 ```
 
 ### Image Generation
@@ -225,9 +243,9 @@ Generate an image using DALL·E! The size of any generated images must be one of
 if not specified the image will default to `1024x1024`.
 
 ```ruby
-    response = client.images.generate(parameters: { prompt: "A baby sea otter cooking pasta wearing a hat of some sort", size: "256x256" })
-    puts response.dig("data", 0, "url")
-    => "https://oaidalleapiprodscus.blob.core.windows.net/private/org-Rf437IxKhh..."
+response = client.images.generate(parameters: { prompt: "A baby sea otter cooking pasta wearing a hat of some sort", size: "256x256" })
+puts response.dig("data", 0, "url")
+# => "https://oaidalleapiprodscus.blob.core.windows.net/private/org-Rf437IxKhh..."
 ```
 
 ![Ruby](https://i.ibb.co/6y4HJFx/img-d-Tx-Rf-RHj-SO5-Gho-Cbd8o-LJvw3.png)
@@ -237,9 +255,9 @@ if not specified the image will default to `1024x1024`.
 Fill in the transparent part of an image, or upload a mask with transparent sections to indicate the parts of an image that can be changed according to your prompt...
 
 ```ruby
-    response = client.images.edit(parameters: { prompt: "A solid red Ruby on a blue background", image: "image.png", mask: "mask.png" })
-    puts response.dig("data", 0, "url")
-    => "https://oaidalleapiprodscus.blob.core.windows.net/private/org-Rf437IxKhh..."
+response = client.images.edit(parameters: { prompt: "A solid red Ruby on a blue background", image: "image.png", mask: "mask.png" })
+puts response.dig("data", 0, "url")
+# => "https://oaidalleapiprodscus.blob.core.windows.net/private/org-Rf437IxKhh..."
 ```
 
 ![Ruby](https://i.ibb.co/sWVh3BX/dalle-ruby.png)
@@ -249,9 +267,9 @@ Fill in the transparent part of an image, or upload a mask with transparent sect
 Create n variations of an image.
 
 ```ruby
-    response = client.images.variations(parameters: { image: "image.png", n: 2 })
-    puts response.dig("data", 0, "url")
-    => "https://oaidalleapiprodscus.blob.core.windows.net/private/org-Rf437IxKhh..."
+response = client.images.variations(parameters: { image: "image.png", n: 2 })
+puts response.dig("data", 0, "url")
+# => "https://oaidalleapiprodscus.blob.core.windows.net/private/org-Rf437IxKhh..."
 ```
 
 ![Ruby](https://i.ibb.co/TWJLP2y/img-miu-Wk-Nl0-QNy-Xtj-Lerc3c0l-NW.png)
@@ -262,9 +280,41 @@ Create n variations of an image.
 Pass a string to check if it violates OpenAI's Content Policy:
 
 ```ruby
-    response = client.moderations(parameters: { input: "I'm worried about that." })
-    puts response.dig("results", 0, "category_scores", "hate")
-    => 5.505014632944949e-05
+response = client.moderations(parameters: { input: "I'm worried about that." })
+puts response.dig("results", 0, "category_scores", "hate")
+# => 5.505014632944949e-05
+```
+
+### Whisper
+
+Whisper is a speech to text model that can be used to generate text based on audio files:
+
+#### Translate
+
+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(
+    parameters: {
+        model: "whisper-1",
+        file: File.open('path_to_file'),
+    })
+puts response.parsed_response['text']
+# => "Translation of the text"
+```
+
+#### Transcribe
+
+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(
+    parameters: {
+        model: "whisper-1",
+        file: File.open('path_to_file'),
+    })
+puts response.parsed_response['text']
+# => "Transcription of the text"
 ```
 
 ## Development

data/lib/openai/client.rb

@@ -2,9 +2,10 @@ module OpenAI
   class Client
     URI_BASE = "https://api.openai.com/".freeze
 
-    def initialize(access_token: nil, organization_id: nil)
+    def initialize(access_token: nil, organization_id: nil, request_timeout: nil)
       OpenAI.configuration.access_token = access_token if access_token
       OpenAI.configuration.organization_id = organization_id if organization_id
+      OpenAI.configuration.request_timeout = request_timeout if request_timeout
     end
 
     def chat(parameters: {})
@@ -43,10 +44,19 @@ module OpenAI
       OpenAI::Client.json_post(path: "/moderations", parameters: parameters)
     end
 
+    def transcribe(parameters: {})
+      OpenAI::Client.multipart_post(path: "/audio/transcriptions", parameters: parameters)
+    end
+
+    def translate(parameters: {})
+      OpenAI::Client.multipart_post(path: "/audio/translations", parameters: parameters)
+    end
+
     def self.get(path:)
       HTTParty.get(
         uri(path: path),
-        headers: headers
+        headers: headers,
+        timeout: request_timeout
       )
     end
 
@@ -54,7 +64,8 @@ module OpenAI
       HTTParty.post(
         uri(path: path),
         headers: headers,
-        body: parameters&.to_json
+        body: parameters&.to_json,
+        timeout: request_timeout
       )
     end
 
@@ -62,14 +73,16 @@ module OpenAI
       HTTParty.post(
         uri(path: path),
         headers: headers.merge({ "Content-Type" => "multipart/form-data" }),
-        body: parameters
+        body: parameters,
+        timeout: request_timeout
       )
     end
 
     def self.delete(path:)
       HTTParty.delete(
         uri(path: path),
-        headers: headers
+        headers: headers,
+        timeout: request_timeout
       )
     end
 
@@ -84,5 +97,9 @@ module OpenAI
         "OpenAI-Organization" => OpenAI.configuration.organization_id
       }
     end
+
+    private_class_method def self.request_timeout
+      OpenAI.configuration.request_timeout
+    end
   end
 end

data/lib/openai/version.rb

@@ -1,3 +1,3 @@
 module OpenAI
-  VERSION = "3.4.0".freeze
+  VERSION = "3.6.0".freeze
 end

data/lib/openai.rb

@@ -13,14 +13,16 @@ module OpenAI
 
   class Configuration
     attr_writer :access_token
-    attr_accessor :api_version, :organization_id
+    attr_accessor :api_version, :organization_id, :request_timeout
 
     DEFAULT_API_VERSION = "v1".freeze
+    DEFAULT_REQUEST_TIMEOUT = 120
 
     def initialize
       @access_token = nil
       @api_version = DEFAULT_API_VERSION
       @organization_id = nil
+      @request_timeout = DEFAULT_REQUEST_TIMEOUT
     end
 
     def access_token

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: ruby-openai
 version: !ruby/object:Gem::Version
-  version: 3.4.0
+  version: 3.6.0
 platform: ruby
 authors:
 - Alex
-autorequire:
+autorequire: 
 bindir: exe
 cert_chain: []
-date: 2023-03-01 00:00:00.000000000 Z
+date: 2023-03-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: httparty
@@ -24,7 +24,7 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: 0.18.1
-description:
+description: 
 email:
 - alexrudall@users.noreply.github.com
 executables: []
@@ -85,8 +85,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.4.6
-signing_key:
+rubygems_version: 3.1.4
+signing_key: 
 specification_version: 4
 summary: A Ruby gem for the OpenAI GPT-3 API
 test_files: []