ruby-openai 5.1.0 → 6.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 6ea6e5d9149ffa94f53c0952491e827a5a082830cb5a4ecbdafe4e4d2523f54e
-  data.tar.gz: 1e8072b9fce1c48612b0120e1df4d6f45e422daec13a41e4b985f60d6cc07f6a
+  metadata.gz: 88af78318c57c49636755099d6c8837e62762dee65e27465160b1d3778721edd
+  data.tar.gz: d6abf778678cf1813ce61efcf5874ecb0e4157a9cb08f6e958948b6d4f5d74ab
 SHA512:
-  metadata.gz: 00b71588418d3c33fb2511147e9a500755cf864c1d4cd7c420599b7b7af7d10bd4bb0b1490ce5399efbf38ce2527461ad40c21f20685b6aba40db275d7c9c633
-  data.tar.gz: e2574855121d6ed5126aa809b32feab815b1bd8f668c9eff1d3f6c9e9a25ed83cbb45c19e1900695b814d79b708a9cedfaf911ea5112ba2ff6eadcc76332f980
+  metadata.gz: 046c91484f51ea3973698c2bd3a7ff627df3a8413097757e4cd7debaf540ee40eb162cfdc6df41b2973cba3a5ef17014c8c18f544c777a5a45d93cb8530fe232
+  data.tar.gz: 196cd9c830e5e2639c16fc02431b2dfad8286cc098c85b47c6c42c2c64a2f570a8412f021846ffdff0c057a184a298c43c82e69b0f2ad1b25f048b0c76969422

data/.devcontainer/Dockerfile

@@ -0,0 +1,16 @@
+FROM ruby:3.2.2-slim-bullseye
+
+ENV TZ="Europe/London"
+
+RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \
+  && apt-get -y install --no-install-recommends \
+  apt-utils \
+  build-essential \
+  curl \
+  git \
+  vim \
+  zsh
+
+RUN gem install bundler
+
+WORKDIR /workspace

data/.devcontainer/devcontainer.json

@@ -0,0 +1,36 @@
+// For format details, see https://aka.ms/devcontainer.json. For config options, see the README at:
+// https://github.com/microsoft/vscode-dev-containers/tree/v0.245.2/containers/ruby-rails-postgres
+// Update the VARIANT arg in docker-compose.yml to pick a Ruby version
+{
+  "name": "ruby-openai",
+  "dockerComposeFile": "docker-compose.yml",
+  "service": "app",
+  "workspaceFolder": "/workspace",
+  "containerEnv": {
+    "GITHUB_TOKEN": "${localEnv:GITHUB_TOKEN}",
+    "GITHUB_USER": "${localEnv:GITHUB_USER}"
+  },
+  // Configure tool-specific properties.
+  "customizations": {
+    // Configure properties specific to VS Code.
+    "vscode": {
+      // Add the IDs of extensions you want installed when the container is created.
+      "extensions": [
+        "rebornix.Ruby",
+        "sleistner.vscode-fileutils",
+        "ms-azuretools.vscode-docker",
+        "samverschueren.final-newline",
+        "GitHub.copilot",
+        "usernamehw.remove-empty-lines",
+        "wingrunr21.vscode-ruby",
+      ]
+    }
+  },
+  // Use 'postCreateCommand' to run commands after the container is created.
+  "postCreateCommand": "bundle install",
+  // Comment out to connect as root instead. More info: https://aka.ms/vscode-remote/containers/non-root.
+  "features": {
+    "git": "os-provided",
+    "github-cli": "latest"
+  }
+}

data/.devcontainer/docker-compose.yml

@@ -0,0 +1,19 @@
+version: "3"
+
+services:
+  app:
+    build:
+      context: ..
+      dockerfile: .devcontainer/Dockerfile
+
+    volumes:
+      - ..:/workspace:cached
+      - bundle_cache:/bundle
+
+    command: sleep infinity
+
+    environment:
+      TZ: Europe/London
+
+volumes:
+  bundle_cache:

data/.github/FUNDING.yml

@@ -0,0 +1,13 @@
+# These are supported funding model platforms
+
+github: alexrudall
+patreon: # Replace with a single Patreon username
+open_collective: # Replace with a single Open Collective username
+ko_fi: # Replace with a single Ko-fi username
+tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
+community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
+liberapay: # Replace with a single Liberapay username
+issuehunt: # Replace with a single IssueHunt username
+otechie: # Replace with a single Otechie username
+lfx_crowdfunding: # Replace with a single LFX Crowdfunding project-name e.g., cloud-foundry
+custom: # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']

data/CHANGELOG.md

@@ -5,6 +5,26 @@ 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).
 
+## [6.0.0] - 2023-11-06
+
+### Added
+
+- [BREAKING] HTTP errors will now be raised by ruby-openai as Faraday:Errors, including when streaming! Implemented by [@atesgoral](https://github.com/atesgoral)
+- [BREAKING] Switch from legacy Finetunes to the new Fine-tune-jobs endpoints. Implemented by [@lancecarlson](https://github.com/lancecarlson)
+- [BREAKING] Remove deprecated Completions endpoints - use Chat instead.
+
+### Fix
+
+- [BREAKING] Fix issue where :stream parameters where replaced by a boolean in the client application. Thanks to [@martinjaimem](https://github.com/martinjaimem), [@vickymadrid03](https://github.com/vickymadrid03) and [@nicastelo](https://github.com/nicastelo) for spotting and fixing this issue.
+
+## [5.2.0] - 2023-10-30
+
+### Fix
+
+- Added more spec-compliant SSE parsing: see here https://html.spec.whatwg.org/multipage/server-sent-events.html#event-stream-interpretation
+- Fixes issue where OpenAI or an intermediary returns only partial JSON per chunk of streamed data
+- Huge thanks to [@atesgoral](https://github.com/atesgoral) for this important fix!
+
 ## [5.1.0] - 2023-08-20
 
 ### Added

data/Gemfile

@@ -5,8 +5,8 @@ gemspec
 
 gem "byebug", "~> 11.1.3"
 gem "dotenv", "~> 2.8.1"
-gem "rake", "~> 13.0"
+gem "rake", "~> 13.1"
 gem "rspec", "~> 3.12"
 gem "rubocop", "~> 1.50.2"
 gem "vcr", "~> 6.1.0"
-gem "webmock", "~> 3.18.1"
+gem "webmock", "~> 3.19.1"

data/Gemfile.lock

@@ -1,22 +1,26 @@
 PATH
   remote: .
   specs:
-    ruby-openai (5.1.0)
+    ruby-openai (6.0.0)
+      event_stream_parser (>= 0.3.0, < 1.0.0)
       faraday (>= 1)
       faraday-multipart (>= 1)
 
 GEM
   remote: https://rubygems.org/
   specs:
-    addressable (2.8.1)
+    addressable (2.8.5)
       public_suffix (>= 2.0.2, < 6.0)
     ast (2.4.2)
+    base64 (0.1.1)
     byebug (11.1.3)
     crack (0.4.5)
       rexml
     diff-lcs (1.5.0)
     dotenv (2.8.1)
-    faraday (2.7.10)
+    event_stream_parser (0.3.0)
+    faraday (2.7.11)
+      base64
       faraday-net_http (>= 2.0, < 3.1)
       ruby2_keywords (>= 0.0.4)
     faraday-multipart (1.0.4)
@@ -28,11 +32,11 @@ GEM
     parallel (1.22.1)
     parser (3.2.2.0)
       ast (~> 2.4.1)
-    public_suffix (5.0.1)
+    public_suffix (5.0.3)
     rainbow (3.1.1)
-    rake (13.0.6)
+    rake (13.1.0)
     regexp_parser (2.8.0)
-    rexml (3.2.5)
+    rexml (3.2.6)
     rspec (3.12.0)
       rspec-core (~> 3.12.0)
       rspec-expectations (~> 3.12.0)
@@ -62,7 +66,7 @@ GEM
     ruby2_keywords (0.0.5)
     unicode-display_width (2.4.2)
     vcr (6.1.0)
-    webmock (3.18.1)
+    webmock (3.19.1)
       addressable (>= 2.8.0)
       crack (>= 0.3.2)
       hashdiff (>= 0.4.0, < 2.0.0)
@@ -73,12 +77,12 @@ PLATFORMS
 DEPENDENCIES
   byebug (~> 11.1.3)
   dotenv (~> 2.8.1)
-  rake (~> 13.0)
+  rake (~> 13.1)
   rspec (~> 3.12)
   rubocop (~> 1.50.2)
   ruby-openai!
   vcr (~> 6.1.0)
-  webmock (~> 3.18.1)
+  webmock (~> 3.19.1)
 
 BUNDLED WITH
    2.4.5

data/README.md

@@ -8,11 +8,9 @@ Use the [OpenAI API](https://openai.com/blog/openai-api/) with Ruby! 🤖❤️
 
 Stream text with GPT-4, transcribe and translate audio with Whisper, or create images with DALL·E...
 
-[Ruby AI Builders Discord](https://discord.gg/k4Uc224xVD)
+🚢 Based in the UK and want to hire me? Now you can! [railsai.com](https://railsai.com?utm_source=ruby-openai&utm_medium=readme&utm_id=26072023)
 
-[Quick guide to streaming ChatGPT with Rails 7 and Hotwire](https://gist.github.com/alexrudall/cb5ee1e109353ef358adb4e66631799d)
-
-Follow me on [Twitter](https://twitter.com/alexrudall) for more Ruby / AI content
+[🎮 Ruby AI Builders Discord](https://discord.gg/k4Uc224xVD) | [🐦 Twitter](https://twitter.com/alexrudall) | [🧠 Anthropic Gem](https://github.com/alexrudall/anthropic) | [🚂 Midjourney Gem](https://github.com/alexrudall/midjourney)
 
 ### Bundler
 
@@ -151,7 +149,7 @@ client.models.retrieve(id: "text-ada-001")
 #### Examples
 
 - [GPT-4 (limited beta)](https://platform.openai.com/docs/models/gpt-4)
-  - gpt-4
+  - gpt-4 (uses current version)
   - gpt-4-0314
   - gpt-4-32k
 - [GPT-3.5](https://platform.openai.com/docs/models/gpt-3-5)
@@ -163,9 +161,9 @@ client.models.retrieve(id: "text-ada-001")
   - text-babbage-001
   - text-curie-001
 
-### ChatGPT
+### Chat
 
-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):
+GPT 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(
@@ -178,11 +176,11 @@ puts response.dig("choices", 0, "message", "content")
 # => "Hello! How may I assist you today?"
 ```
 
-### Streaming ChatGPT
+### Streaming Chat
 
-[Quick guide to streaming ChatGPT with Rails 7 and Hotwire](https://gist.github.com/alexrudall/cb5ee1e109353ef358adb4e66631799d)
+[Quick guide to streaming Chat with Rails 7 and Hotwire](https://gist.github.com/alexrudall/cb5ee1e109353ef358adb4e66631799d)
 
-You can stream from the API in realtime, which can be much faster and used to create a more engaging user experience. Pass a [Proc](https://ruby-doc.org/core-2.6/Proc.html) (or any object with a `#call` method) to the `stream` parameter to receive the stream of text chunks as they are generated. Each time one or more chunks is received, the proc will be called once with each chunk, parsed as a Hash. If OpenAI returns an error, `ruby-openai` will pass that to your proc as a Hash.
+You can stream from the API in realtime, which can be much faster and used to create a more engaging user experience. Pass a [Proc](https://ruby-doc.org/core-2.6/Proc.html) (or any object with a `#call` method) to the `stream` parameter to receive the stream of completion chunks as they are generated. Each time one or more chunks is received, the proc will be called once with each chunk, parsed as a Hash. If OpenAI returns an error, `ruby-openai` will raise a Faraday error.
 
 ```ruby
 client.chat(
@@ -197,7 +195,7 @@ client.chat(
 # => "Anna is a young woman in her mid-twenties, with wavy chestnut hair that falls to her shoulders..."
 ```
 
-Note: the API docs state that token usage is included in the streamed chat chunk objects, but this doesn't currently appear to be the case. To count tokens while streaming, try `OpenAI.rough_token_count` or [tiktoken_ruby](https://github.com/IAPark/tiktoken_ruby).
+Note: OpenAPI currently does not report token usage for streaming responses. To count tokens while streaming, try `OpenAI.rough_token_count` or [tiktoken_ruby](https://github.com/IAPark/tiktoken_ruby). We think that each call to the stream proc corresponds to a single token, so you can also try counting the number of calls to the proc to get the completion token count.
 
 ### Functions
 
@@ -259,21 +257,6 @@ end
 # => "The weather is nice 🌞"
 ```
 
-### Completions
-
-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"]
-```
-
 ### Edits
 
 Send a string and some instructions for what to do to the string:
@@ -325,22 +308,22 @@ client.files.content(id: "file-123")
 client.files.delete(id: "file-123")
 ```
 
-### Fine-tunes
+### Finetunes
 
 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" })
+response = client.files.upload(parameters: { file: "path/to/sarcasm.jsonl", purpose: "fine-tune" })
 file_id = JSON.parse(response.body)["id"]
 ```
 
-You can then use this file ID to create a fine-tune model:
+You can then use this file ID to create a fine tuning job:
 
 ```ruby
 response = client.finetunes.create(
     parameters: {
     training_file: file_id,
-    model: "ada"
+    model: "gpt-3.5-turbo-0613"
 })
 fine_tune_id = response["id"]
 ```
@@ -371,10 +354,10 @@ response = client.completions(
 response.dig("choices", 0, "text")
 ```
 
-You can delete the fine-tuned model when you are done with it:
+You can also capture the events for a job:
 
-```ruby
-client.finetunes.delete(fine_tuned_model: fine_tuned_model)
+```
+client.finetunes.list_events(id: fine_tune_id)
 ```
 
 ### Image Generation
@@ -457,6 +440,18 @@ puts response["text"]
 # => "Transcription of the text"
 ```
 
+#### Errors
+
+HTTP errors can be caught like this:
+
+```
+  begin
+    OpenAI::Client.new.models.retrieve(id: "text-ada-001")
+  rescue Faraday::Error => e
+    raise "Got a Faraday error: #{e}"
+  end
+```
+
 ## Development
 
 After checking out the repo, run `bin/setup` to install dependencies. You can run `bin/console` for an interactive prompt that will allow you to experiment.

data/lib/openai/client.rb

@@ -25,10 +25,6 @@ module OpenAI
       json_post(path: "/chat/completions", parameters: parameters)
     end
 
-    def completions(parameters: {})
-      json_post(path: "/completions", parameters: parameters)
-    end
-
     def edits(parameters: {})
       json_post(path: "/edits", parameters: parameters)
     end

data/lib/openai/finetunes.rb

@@ -5,31 +5,23 @@ module OpenAI
     end
 
     def list
-      @client.get(path: "/fine-tunes")
+      @client.get(path: "/fine_tuning/jobs")
     end
 
     def create(parameters: {})
-      @client.json_post(path: "/fine-tunes", parameters: parameters)
+      @client.json_post(path: "/fine_tuning/jobs", parameters: parameters)
     end
 
     def retrieve(id:)
-      @client.get(path: "/fine-tunes/#{id}")
+      @client.get(path: "/fine_tuning/jobs/#{id}")
     end
 
     def cancel(id:)
-      @client.multipart_post(path: "/fine-tunes/#{id}/cancel")
+      @client.json_post(path: "/fine_tuning/jobs/#{id}/cancel", parameters: {})
     end
 
-    def events(id:)
-      @client.get(path: "/fine-tunes/#{id}/events")
-    end
-
-    def delete(fine_tuned_model:)
-      if fine_tuned_model.start_with?("ft-")
-        raise ArgumentError, "Please give a fine_tuned_model name, not a fine-tune ID"
-      end
-
-      @client.delete(path: "/models/#{fine_tuned_model}")
+    def list_events(id:)
+      @client.get(path: "/fine_tuning/jobs/#{id}/events")
     end
   end
 end

data/lib/openai/http.rb

@@ -1,63 +1,61 @@
+require "event_stream_parser"
+
 module OpenAI
   module HTTP
     def get(path:)
-      to_json(conn.get(uri(path: path)) do |req|
+      parse_jsonl(conn.get(uri(path: path)) do |req|
         req.headers = headers
       end&.body)
     end
 
     def json_post(path:, parameters:)
-      to_json(conn.post(uri(path: path)) do |req|
-        if parameters[:stream].respond_to?(:call)
-          req.options.on_data = to_json_stream(user_proc: parameters[:stream])
-          parameters[:stream] = true # Necessary to tell OpenAI to stream.
-        elsif parameters[:stream]
-          raise ArgumentError, "The stream parameter must be a Proc or have a #call method"
-        end
-
-        req.headers = headers
-        req.body = parameters.to_json
-      end&.body)
+      conn.post(uri(path: path)) do |req|
+        configure_json_post_request(req, parameters)
+      end&.body
     end
 
     def multipart_post(path:, parameters: nil)
-      to_json(conn(multipart: true).post(uri(path: path)) do |req|
+      conn(multipart: true).post(uri(path: path)) do |req|
         req.headers = headers.merge({ "Content-Type" => "multipart/form-data" })
         req.body = multipart_parameters(parameters)
-      end&.body)
+      end&.body
     end
 
     def delete(path:)
-      to_json(conn.delete(uri(path: path)) do |req|
+      conn.delete(uri(path: path)) do |req|
         req.headers = headers
-      end&.body)
+      end&.body
     end
 
     private
 
-    def to_json(string)
-      return unless string
+    def parse_jsonl(response)
+      return unless response
+      return response unless response.is_a?(String)
 
-      JSON.parse(string)
-    rescue JSON::ParserError
       # Convert a multiline string of JSON objects to a JSON array.
-      JSON.parse(string.gsub("}\n{", "},{").prepend("[").concat("]"))
+      response = response.gsub("}\n{", "},{").prepend("[").concat("]")
+
+      JSON.parse(response)
     end
 
     # Given a proc, returns an outer proc that can be used to iterate over a JSON stream of chunks.
     # For each chunk, the inner user_proc is called giving it the JSON object. The JSON object could
     # be a data object or an error object as described in the OpenAI API documentation.
     #
-    # If the JSON object for a given data or error message is invalid, it is ignored.
-    #
     # @param user_proc [Proc] The inner proc to call for each JSON object in the chunk.
     # @return [Proc] An outer proc that iterates over a raw stream, converting it to JSON.
     def to_json_stream(user_proc:)
-      proc do |chunk, _|
-        chunk.scan(/(?:data|error): (\{.*\})/i).flatten.each do |data|
-          user_proc.call(JSON.parse(data))
-        rescue JSON::ParserError
-          # Ignore invalid JSON.
+      parser = EventStreamParser::Parser.new
+
+      proc do |chunk, _bytes, env|
+        if env && env.status != 200
+          raise_error = Faraday::Response::RaiseError.new
+          raise_error.on_complete(env.merge(body: JSON.parse(chunk)))
+        end
+
+        parser.feed(chunk) do |_type, data|
+          user_proc.call(JSON.parse(data)) unless data == "[DONE]"
         end
       end
     end
@@ -66,6 +64,8 @@ module OpenAI
       Faraday.new do |f|
         f.options[:timeout] = @request_timeout
         f.request(:multipart) if multipart
+        f.response :raise_error
+        f.response :json
       end
     end
 
@@ -111,5 +111,19 @@ module OpenAI
         Faraday::UploadIO.new(value, "", value.path)
       end
     end
+
+    def configure_json_post_request(req, parameters)
+      req_parameters = parameters.dup
+
+      if parameters[:stream].respond_to?(:call)
+        req.options.on_data = to_json_stream(user_proc: parameters[:stream])
+        req_parameters[:stream] = true # Necessary to tell OpenAI to stream.
+      elsif parameters[:stream]
+        raise ArgumentError, "The stream parameter must be a Proc or have a #call method"
+      end
+
+      req.headers = headers
+      req.body = req_parameters.to_json
+    end
   end
 end

data/lib/openai/version.rb

@@ -1,3 +1,3 @@
 module OpenAI
-  VERSION = "5.1.0".freeze
+  VERSION = "6.0.0".freeze
 end

data/ruby-openai.gemspec

@@ -25,6 +25,7 @@ Gem::Specification.new do |spec|
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
   spec.require_paths = ["lib"]
 
+  spec.add_dependency "event_stream_parser", ">= 0.3.0", "< 1.0.0"
   spec.add_dependency "faraday", ">= 1"
   spec.add_dependency "faraday-multipart", ">= 1"
 end

metadata

@@ -1,15 +1,35 @@
 --- !ruby/object:Gem::Specification
 name: ruby-openai
 version: !ruby/object:Gem::Version
-  version: 5.1.0
+  version: 6.0.0
 platform: ruby
 authors:
 - Alex
-autorequire:
+autorequire: 
 bindir: exe
 cert_chain: []
-date: 2023-08-20 00:00:00.000000000 Z
+date: 2023-11-06 00:00:00.000000000 Z
 dependencies:
+- !ruby/object:Gem::Dependency
+  name: event_stream_parser
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.3.0
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: 1.0.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.3.0
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: 1.0.0
 - !ruby/object:Gem::Dependency
   name: faraday
   requirement: !ruby/object:Gem::Requirement
@@ -38,7 +58,7 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '1'
-description:
+description: 
 email:
 - alexrudall@users.noreply.github.com
 executables: []
@@ -46,6 +66,10 @@ extensions: []
 extra_rdoc_files: []
 files:
 - ".circleci/config.yml"
+- ".devcontainer/Dockerfile"
+- ".devcontainer/devcontainer.json"
+- ".devcontainer/docker-compose.yml"
+- ".github/FUNDING.yml"
 - ".github/ISSUE_TEMPLATE/bug_report.md"
 - ".github/ISSUE_TEMPLATE/feature_request.md"
 - ".github/dependabot.yml"
@@ -83,7 +107,7 @@ metadata:
   source_code_uri: https://github.com/alexrudall/ruby-openai
   changelog_uri: https://github.com/alexrudall/ruby-openai/blob/main/CHANGELOG.md
   rubygems_mfa_required: 'true'
-post_install_message:
+post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
@@ -98,8 +122,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.4.12
-signing_key:
+rubygems_version: 3.4.10
+signing_key: 
 specification_version: 4
 summary: "OpenAI API + Ruby! \U0001F916❤️"
 test_files: []