ruby-openai 5.0.0 → 5.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 4f487bd64d6f7a7c4f0ccc3198d9bec592b199792763b6885b12b21f267ff80a
-  data.tar.gz: 566af61bb906edbb2315ee343aae62f82e6837aa318dfb505d67d73497fcb27a
+  metadata.gz: 996d39cd32c3c05c73efea0177c12d0751b5dda208b2855aaac440af7b2702d8
+  data.tar.gz: 65471a670e34f537fe4878322c87978f1c2beaf93336a7f2104baaa86b018c60
 SHA512:
-  metadata.gz: 7e500ce6b1cff92bdb78b4cf455aac251cb229e43e52c4c863a98f44a351ac1ef4abd9692dde13f822f458b7373ee063e34dc0670b72dc67e02827533e316b13
-  data.tar.gz: 5d90d4ae80e14da163655a29d598c09834cfd0cad728bebe18f09b015aff7fa0881e736408360b228aa4921497de3f41b6122ee0a5e7a6011001b32403f70b41
+  metadata.gz: deab41c7c7f4ee21b4ed1a17f289b147b2e4960b33fd12ce863d5bdb8c835a955215d01438890c1ab8d9a1c7026faba0e5b8359c1fe3d9139082f8de58dce616
+  data.tar.gz: 3309d1c3a68736816c4f3bd1d465021ee3f162b5f5c3dbb7915ed5ce6f3a8d7014f9f1c4b07cf630f3f90201bdbe0ec308f1dc00fb6b075f45546fe519afb553

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 +5,20 @@ 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).
 
+## [5.2.0] - 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
+
+- Added rough_token_count to estimate tokens in a string according to OpenAI's "rules of thumb". Thank you to [@jamiemccarthy](https://github.com/jamiemccarthy) for the idea and implementation!
+
 ## [5.0.0] - 2023-08-14
 
 ### Added

data/Gemfile.lock

@@ -1,7 +1,8 @@
 PATH
   remote: .
   specs:
-    ruby-openai (5.0.0)
+    ruby-openai (5.2.0)
+      event_stream_parser (>= 0.3.0, < 1.0.0)
       faraday (>= 1)
       faraday-multipart (>= 1)
 
@@ -16,6 +17,7 @@ GEM
       rexml
     diff-lcs (1.5.0)
     dotenv (2.8.1)
+    event_stream_parser (0.3.0)
     faraday (2.7.10)
       faraday-net_http (>= 2.0, < 3.1)
       ruby2_keywords (>= 0.0.4)

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
 
@@ -24,13 +22,17 @@ gem "ruby-openai"
 
 And then execute:
 
+```bash
 $ bundle install
+```
 
 ### Gem install
 
 Or install with:
 
+```bash
 $ gem install ruby-openai
+```
 
 and require with:
 
@@ -86,7 +88,8 @@ client = OpenAI::Client.new(
     extra_headers: {
       "X-Proxy-TTL" => "43200", # For https://github.com/6/openai-caching-proxy-worker#specifying-a-cache-ttl
       "X-Proxy-Refresh": "true", # For https://github.com/6/openai-caching-proxy-worker#refreshing-the-cache
-      "Helicone-Auth": "Bearer HELICONE_API_KEY" # For https://docs.helicone.ai/getting-started/integration-method/openai-proxy
+      "Helicone-Auth": "Bearer HELICONE_API_KEY", # For https://docs.helicone.ai/getting-started/integration-method/openai-proxy
+      "helicone-stream-force-format" => "true", # Use this with Helicone otherwise streaming drops chunks # https://github.com/alexrudall/ruby-openai/issues/251
     }
 )
 ```
@@ -122,6 +125,18 @@ To use the [Azure OpenAI Service](https://learn.microsoft.com/en-us/azure/cognit
 
 where `AZURE_OPENAI_URI` is e.g. `https://custom-domain.openai.azure.com/openai/deployments/gpt-35-turbo`
 
+### Counting Tokens
+
+OpenAI parses prompt text into [tokens](https://help.openai.com/en/articles/4936856-what-are-tokens-and-how-to-count-them), which are words or portions of words. (These tokens are unrelated to your API access_token.) Counting tokens can help you estimate your [costs](https://openai.com/pricing). It can also help you ensure your prompt text size is within the max-token limits of your model's context window, and choose an appropriate [`max_tokens`](https://platform.openai.com/docs/api-reference/chat/create#chat/create-max_tokens) completion parameter so your response will fit as well.
+
+To estimate the token-count of your text:
+
+```ruby
+OpenAI.rough_token_count("Your text")
+```
+
+If you need a more accurate count, try [tiktoken_ruby](https://github.com/IAPark/tiktoken_ruby).
+
 ### Models
 
 There are different models that can be used to generate text. For a full list and to retrieve information about a single model:
@@ -180,7 +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. If you need to work out how many tokens are being used while streaming, try [tiktoken_ruby](https://github.com/IAPark/tiktoken_ruby).
+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).
 
 ### Functions
 

data/lib/openai/http.rb

@@ -1,3 +1,5 @@
+require "event_stream_parser"
+
 module OpenAI
   module HTTP
     def get(path:)
@@ -53,15 +55,25 @@ module OpenAI
     # @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
+          emit_json(json: chunk, user_proc: user_proc)
+        else
+          parser.feed(chunk) do |_type, data|
+            emit_json(json: data, user_proc: user_proc) unless data == "[DONE]"
+          end
         end
       end
     end
 
+    def emit_json(json:, user_proc:)
+      user_proc.call(JSON.parse(json))
+    rescue JSON::ParserError
+      # Ignore invalid JSON.
+    end
+
     def conn(multipart: false)
       Faraday.new do |f|
         f.options[:timeout] = @request_timeout

data/lib/openai/version.rb

@@ -1,3 +1,3 @@
 module OpenAI
-  VERSION = "5.0.0".freeze
+  VERSION = "5.2.0".freeze
 end

data/lib/openai.rb

@@ -52,4 +52,16 @@ module OpenAI
   def self.configure
     yield(configuration)
   end
+
+  # Estimate the number of tokens in a string, using the rules of thumb from OpenAI:
+  # https://help.openai.com/en/articles/4936856-what-are-tokens-and-how-to-count-them
+  def self.rough_token_count(content = "")
+    raise ArgumentError, "rough_token_count requires a string" unless content.is_a? String
+    return 0 if content.empty?
+
+    count_by_chars = content.size / 4.0
+    count_by_words = content.split.size * 4.0 / 3
+    estimate = ((count_by_chars + count_by_words) / 2.0).round
+    [1, estimate].max
+  end
 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: 5.0.0
+  version: 5.2.0
 platform: ruby
 authors:
 - Alex
-autorequire:
+autorequire: 
 bindir: exe
 cert_chain: []
-date: 2023-08-14 00:00:00.000000000 Z
+date: 2023-10-30 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: []