-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
feat: Core implementation of ChatGPT Ruby SDK
- Implemented ChatGPT client with configuration management - Added support for completions and chat APIs - Added streaming support - Implemented robust error handling - Added comprehensive test suite with 100% coverage
- Loading branch information
Showing
20 changed files
with
695 additions
and
239 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,135 +1,242 @@ | ||
| # ChatGPT Ruby | ||
|
|
||
| [](https://badge.fury.io/rb/chatgpt-ruby) [](https://opensource.org/licenses/MIT) [](https://codeclimate.com/github/nagstler/chatgpt-ruby/maintainability) [](https://codeclimate.com/github/nagstler/chatgpt-ruby/test_coverage) [](https://github.com/nagstler/chatgpt-ruby/actions/workflows/ci.yml) | ||
|
|
||
| The `chatgpt-ruby` is a Ruby SDK for the OpenAI API, providing methods for generating text and completing prompts using the ChatGPT model. | ||
| [](https://badge.fury.io/rb/chatgpt-ruby) | ||
| [](https://opensource.org/licenses/MIT) | ||
| [](https://codeclimate.com/github/nagstler/chatgpt-ruby/maintainability) | ||
| [](https://codeclimate.com/github/nagstler/chatgpt-ruby/test_coverage) | ||
| [](https://github.com/nagstler/chatgpt-ruby/actions/workflows/ci.yml) | ||
|
|
||
| A comprehensive Ruby SDK for OpenAI's GPT APIs, providing a robust, feature-rich interface for AI-powered applications. | ||
|
|
||
| ## Features | ||
|
|
||
| - 🚀 Full support for GPT-3.5-Turbo and GPT-4 models | ||
| - 📡 Streaming responses support | ||
| - 🔧 Function calling and JSON mode | ||
| - 🎨 DALL-E image generation | ||
| - 🔄 Fine-tuning capabilities | ||
| - 📊 Token counting and validation | ||
| - ⚡ Async operations support | ||
| - 🛡️ Built-in rate limiting and retries | ||
| - 🎯 Type-safe responses | ||
| - 📝 Comprehensive logging | ||
|
|
||
| ## Table of Contents | ||
|
|
||
| - [Features](#features) | ||
| - [Installation](#installation) | ||
| - [Quick Start](#quick-start) | ||
| - [Configuration](#configuration) | ||
| - [Core Features](#core-features) | ||
| - [Chat Completions](#chat-completions) | ||
| - [Function Calling](#function-calling) | ||
| - [Image Generation (DALL-E)](#image-generation-dall-e) | ||
| - [Fine-tuning](#fine-tuning) | ||
| - [Token Management](#token-management) | ||
| - [Error Handling](#error-handling) | ||
| - [Advanced Usage](#advanced-usage) | ||
| - [Async Operations](#async-operations) | ||
| - [Batch Operations](#batch-operations) | ||
| - [Response Objects](#response-objects) | ||
| - [Development](#development) | ||
| - [Contributing](#contributing) | ||
| - [License](#license) | ||
|
|
||
| ## Installation | ||
|
|
||
| Add this line to your application's Gemfile: | ||
| Add to your Gemfile: | ||
|
|
||
| ```ruby | ||
| gem 'chatgpt-ruby' | ||
| ``` | ||
|
|
||
| And then execute: | ||
| Or install directly: | ||
|
|
||
| ```ruby | ||
| $ bundle install | ||
| ```bash | ||
| $ gem install chatgpt-ruby | ||
| ``` | ||
|
|
||
| Or install it yourself as: | ||
| ## Quick Start | ||
|
|
||
| ```ruby | ||
| $ gem install chatgpt-ruby | ||
| ``` | ||
| require 'chatgpt' | ||
|
|
||
| # Initialize with API key | ||
| client = ChatGPT::Client.new(api_key: 'your-api-key') | ||
|
|
||
| ## Usage | ||
| # Simple chat completion | ||
| response = client.chat(messages: [ | ||
| { role: "user", content: "What is Ruby?" } | ||
| ]) | ||
|
|
||
| To use the ChatGPT API SDK, you will need an API key from OpenAI. You can obtain an API key by signing up for the [OpenAI API beta program](https://beta.openai.com/signup/) . | ||
| puts response.content | ||
| ``` | ||
|
|
||
| Once you have an API key, you can create a new `ChatGPT::Client` instance with your API key: | ||
| ## Configuration | ||
|
|
||
| ```ruby | ||
| require 'chatgpt/client' | ||
|
|
||
| api_key = 'your-api-key' | ||
| client = ChatGPT::Client.new(api_key) | ||
| ChatGPT.configure do |config| | ||
| config.api_key = 'your-api-key' | ||
| config.default_model = 'gpt-4' | ||
| config.timeout = 30 | ||
| config.max_retries = 3 | ||
| config.api_version = '2024-01' | ||
| end | ||
| ``` | ||
|
|
||
| ## Completions | ||
| ## Core Features | ||
|
|
||
| To generate completions given a prompt, you can use the `completions` method: | ||
| ### Chat Completions | ||
|
|
||
| ```ruby | ||
| prompt = 'Hello, my name is' | ||
| completions = client.completions(prompt) | ||
| # Basic chat | ||
| client.chat(messages: [ | ||
| { role: "system", content: "You are a helpful assistant." }, | ||
| { role: "user", content: "Hello!" } | ||
| ]) | ||
|
|
||
| # With streaming | ||
| client.chat_stream(messages: [...]) do |chunk| | ||
| print chunk.content | ||
| end | ||
| ``` | ||
|
|
||
| ### Function Calling | ||
|
|
||
| ```ruby | ||
| functions = [ | ||
| { | ||
| name: "get_weather", | ||
| description: "Get current weather", | ||
| parameters: { | ||
| type: "object", | ||
| properties: { | ||
| location: { type: "string" }, | ||
| unit: { type: "string", enum: ["celsius", "fahrenheit"] } | ||
| } | ||
| } | ||
| } | ||
| ] | ||
|
|
||
| # Output: an array of completion strings | ||
| response = client.chat( | ||
| messages: [{ role: "user", content: "What's the weather in London?" }], | ||
| functions: functions, | ||
| function_call: "auto" | ||
| ) | ||
| ``` | ||
|
|
||
| You can customize the generation process by passing in additional parameters as a hash: | ||
| ### Image Generation (DALL-E) | ||
|
|
||
| ```ruby | ||
| params = { | ||
| engine: 'text-davinci-002', | ||
| max_tokens: 50, | ||
| temperature: 0.7 | ||
| } | ||
| completions = client.completions(prompt, params) | ||
|
|
||
| puts completions["choices"].map { |c| c["text"] } | ||
| # Output: an array of completion strings | ||
| # Generate image | ||
| image = client.images.generate( | ||
| prompt: "A sunset over mountains", | ||
| size: "1024x1024", | ||
| quality: "hd" | ||
| ) | ||
|
|
||
| # Create variations | ||
| variation = client.images.create_variation( | ||
| image: File.read("input.png"), | ||
| n: 1 | ||
| ) | ||
| ``` | ||
|
|
||
| ## Chat | ||
| ### Fine-tuning | ||
|
|
||
| The `chat` method allows for a dynamic conversation with the GPT model. It requires an array of messages where each message is a hash with two properties: `role` and `content`. | ||
| ```ruby | ||
| # Create fine-tuning job | ||
| job = client.fine_tunes.create( | ||
| training_file: "file-abc123", | ||
| model: "gpt-3.5-turbo" | ||
| ) | ||
|
|
||
| `role` can be: | ||
| - `'system'`: Used for instructions that guide the conversation. | ||
| - `'user'`: Represents the user's input. | ||
| - `'assistant'`: Represents the model's output. | ||
| # List fine-tuning jobs | ||
| jobs = client.fine_tunes.list | ||
|
|
||
| `content` contains the text message from the corresponding role. | ||
| # Get job status | ||
| status = client.fine_tunes.retrieve(job.id) | ||
| ``` | ||
|
|
||
| Here is how you would start a chat: | ||
| ### Token Management | ||
|
|
||
| ```ruby | ||
| # Count tokens | ||
| count = client.tokens.count("Your text here", model: "gpt-4") | ||
|
|
||
| # Define the conversation messages | ||
| messages = [ | ||
| { | ||
| role: "system", | ||
| content: "You are a helpful assistant." | ||
| }, | ||
| { | ||
| role: "user", | ||
| content: "Who won the world series in 2020?" | ||
| } | ||
| ] | ||
|
|
||
| # Start a chat | ||
| response = client.chat(messages) | ||
| # Validate token limits | ||
| client.tokens.validate_messages(messages, max_tokens: 4000) | ||
| ``` | ||
|
|
||
| The response will be a hash containing the model's message(s). You can extract the assistant's message like this: | ||
| ### Error Handling | ||
|
|
||
| ```ruby | ||
|
|
||
| puts response['choices'][0]['message']['content'] # Outputs the assistant's message | ||
| begin | ||
| response = client.chat(messages: [...]) | ||
| rescue ChatGPT::RateLimitError => e | ||
| puts "Rate limit hit: #{e.message}" | ||
| rescue ChatGPT::APIError => e | ||
| puts "API error: #{e.message}" | ||
| rescue ChatGPT::TokenLimitError => e | ||
| puts "Token limit exceeded: #{e.message}" | ||
| end | ||
| ``` | ||
|
|
||
| The conversation can be continued by extending the `messages` array and calling the `chat` method again: | ||
| ## Advanced Usage | ||
|
|
||
| ### Async Operations | ||
|
|
||
| ```ruby | ||
| client.async do | ||
| response1 = client.chat(messages: [...]) | ||
| response2 = client.chat(messages: [...]) | ||
| [response1, response2] | ||
| end | ||
| ``` | ||
|
|
||
| messages << {role: "user", content: "Tell me more about it."} | ||
| ### Batch Operations | ||
|
|
||
| response = client.chat(messages) | ||
| puts response['choices'][0]['message']['content'] # Outputs the assistant's new message | ||
| ```ruby | ||
| responses = client.batch do |batch| | ||
| batch.add_chat(messages: [...]) | ||
| batch.add_chat(messages: [...]) | ||
| end | ||
| ``` | ||
|
|
||
| With this method, you can build an ongoing conversation with the model. | ||
| ### Response Objects | ||
|
|
||
| ## Changelog | ||
| ```ruby | ||
| response = client.chat(messages: [...]) | ||
|
|
||
| For a detailed list of changes for each version of this project, please see the [CHANGELOG](CHANGELOG.md). | ||
| response.content # Main response content | ||
| response.usage # Token usage information | ||
| response.finish_reason # Why the response ended | ||
| response.model # Model used | ||
| ``` | ||
|
|
||
| ## Development | ||
|
|
||
| After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake test` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment. | ||
| ```bash | ||
| # Run tests | ||
| bundle exec rake test | ||
|
|
||
| To install this gem onto your local machine, run `bundle exec rake install`. | ||
| # Run linter | ||
| bundle exec rubocop | ||
|
|
||
| # Generate documentation | ||
| bundle exec yard doc | ||
| ``` | ||
|
|
||
| ## Contributing | ||
|
|
||
| Bug reports and pull requests are welcome on GitHub at https://github.com/nagstler/chatgpt-ruby. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [code of conduct](https://github.com/nagstler/chatgpt-ruby/blob/main/CODE_OF_CONDUCT.md). | ||
| 1. Fork it | ||
| 2. Create your feature branch (`git checkout -b feature/my-new-feature`) | ||
| 3. Add tests for your feature | ||
| 4. Make your changes | ||
| 5. Commit your changes (`git commit -am 'Add some feature'`) | ||
| 6. Push to the branch (`git push origin feature/my-new-feature`) | ||
| 7. Create a new Pull Request | ||
|
|
||
| ## License | ||
|
|
||
| The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT). | ||
|
|
||
| ## Code of Conduct | ||
|
|
||
| Everyone interacting in the Chatgpt::Ruby project's codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/nagstler/chatgpt-ruby/blob/main/CODE_OF_CONDUCT.md). | ||
| Released under the MIT License. See [LICENSE](LICENSE.txt) for details. |
Oops, something went wrong.