openai 0.3.0 → 0.4.1

data/README.md

@@ -1,57 +1,321 @@
-# OpenAI API client library to access GPT-3 in Ruby
+# OpenAI Ruby API library
 
-This is a wrapper for calling OpenAI and GPT-3's HTTP APIs. API docs are available here: https://beta.openai.com/api-docs
+The OpenAI Ruby library provides convenient access to the OpenAI REST API from any Ruby 3.2.0+ application. It ships with comprehensive types & docstrings in Yard, RBS, and RBI – [see below](https://github.com/openai/openai-ruby#Sorbet) for usage with Sorbet. The standard library's `net/http` is used as the HTTP transport, with connection pooling via the `connection_pool` gem.
+
+## Documentation
+
+Documentation for releases of this gem can be found [on RubyDoc](https://gemdocs.org/gems/openai).
+
+The REST API documentation can be found on [platform.openai.com](https://platform.openai.com/docs).
 
 ## Installation
 
-Add this line to your application's Gemfile:
+To use this gem, install via Bundler by adding the following to your application's `Gemfile`:
+
+<!-- x-release-please-start-version -->
 
 ```ruby
-gem 'openai'
+gem "openai", "~> 0.4.1"
 ```
 
-And then execute:
+<!-- x-release-please-end -->
 
-    $ bundle
+## Usage
 
-Or install it yourself as:
+```ruby
+require "bundler/setup"
+require "openai"
 
-    $ gem install openai
+openai = OpenAI::Client.new(
+  api_key: ENV["OPENAI_API_KEY"] # This is the default and can be omitted
+)
 
-## Usage
+chat_completion = openai.chat.completions.create(
+  messages: [{role: "user", content: "Say this is a test"}],
+  model: :"gpt-4.1"
+)
+
+puts(chat_completion)
+```
+
+### Streaming
+
+We provide support for streaming responses using Server-Sent Events (SSE).
+
+**coming soon:** `openai.chat.completions.stream` will soon come with Python SDK-style higher-level streaming responses support.
 
 ```ruby
-require "openai"
+stream = openai.chat.completions.stream_raw(
+  messages: [{role: "user", content: "Say this is a test"}],
+  model: :"gpt-4.1"
+)
+
+stream.each do |completion|
+  puts(completion)
+end
+```
 
-openai_client = OpenAI::Client.new(api_key: ENV.fetch("OPENAI_API_KEY"), default_engine: "ada")
+### Pagination
 
-# List Engines
-openai_client.engines
+List methods in the OpenAI API are paginated.
 
-# Retrieve Engine
-openai_client.engine("babbage")
+This library provides auto-paginating iterators with each list response, so you do not have to request successive pages manually:
 
-# Search
-openai_client.search(documents: ["White House", "hospital", "school"], query: "the president")
+```ruby
+page = openai.fine_tuning.jobs.list(limit: 20)
 
-# Create Completion
-openai_client.completions(prompt: "Once upon a time", max_tokens: 5)
+# Fetch single item from page.
+job = page.data[0]
+puts(job.id)
+
+# Automatically fetches more pages as needed.
+page.auto_paging_each do |job|
+  puts(job.id)
+end
 ```
 
-## TODO
+Alternatively, you can use the `#next_page?` and `#next_page` methods for more granular control working with pages.
 
-* Stream Completion
+```ruby
+if page.next_page?
+  new_page = page.next_page
+  puts(new_page.data[0].id)
+end
+```
 
-## Development
+### File uploads
 
-After checking out the repo, run `bin/setup` to install dependencies. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+Request parameters that correspond to file uploads can be passed as raw contents, a [`Pathname`](https://rubyapi.org/3.2/o/pathname) instance, [`StringIO`](https://rubyapi.org/3.2/o/stringio), or more.
 
-To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+```ruby
+require "pathname"
 
-## Contributing
+# Use `Pathname` to send the filename and/or avoid paging a large file into memory:
+file_object = openai.files.create(file: Pathname("input.jsonl"), purpose: "fine-tune")
+
+# Alternatively, pass file contents or a `StringIO` directly:
+file_object = openai.files.create(file: File.read("input.jsonl"), purpose: "fine-tune")
+
+# Or, to control the filename and/or content type:
+file = OpenAI::FilePart.new(File.read("input.jsonl"), filename: "input.jsonl", content_type: "…")
+file_object = openai.files.create(file: file, purpose: "fine-tune")
+
+puts(file_object.id)
+```
+
+Note that you can also pass a raw `IO` descriptor, but this disables retries, as the library can't be sure if the descriptor is a file or pipe (which cannot be rewound).
+
+### Handling errors
+
+When the library is unable to connect to the API, or if the API returns a non-success status code (i.e., 4xx or 5xx response), a subclass of `OpenAI::Errors::APIError` will be thrown:
+
+```ruby
+begin
+  job = openai.fine_tuning.jobs.create(model: :"babbage-002", training_file: "file-abc123")
+rescue OpenAI::Errors::APIConnectionError => e
+  puts("The server could not be reached")
+  puts(e.cause)  # an underlying Exception, likely raised within `net/http`
+rescue OpenAI::Errors::RateLimitError => e
+  puts("A 429 status code was received; we should back off a bit.")
+rescue OpenAI::Errors::APIStatusError => e
+  puts("Another non-200-range status code was received")
+  puts(e.status)
+end
+```
+
+Error codes are as follows:
+
+| Cause            | Error Type                 |
+| ---------------- | -------------------------- |
+| HTTP 400         | `BadRequestError`          |
+| HTTP 401         | `AuthenticationError`      |
+| HTTP 403         | `PermissionDeniedError`    |
+| HTTP 404         | `NotFoundError`            |
+| HTTP 409         | `ConflictError`            |
+| HTTP 422         | `UnprocessableEntityError` |
+| HTTP 429         | `RateLimitError`           |
+| HTTP >= 500      | `InternalServerError`      |
+| Other HTTP error | `APIStatusError`           |
+| Timeout          | `APITimeoutError`          |
+| Network error    | `APIConnectionError`       |
+
+### Retries
+
+Certain errors will be automatically retried 2 times by default, with a short exponential backoff.
+
+Connection errors (for example, due to a network connectivity problem), 408 Request Timeout, 409 Conflict, 429 Rate Limit, >=500 Internal errors, and timeouts will all be retried by default.
+
+You can use the `max_retries` option to configure or disable this:
+
+```ruby
+# Configure the default for all requests:
+openai = OpenAI::Client.new(
+  max_retries: 0 # default is 2
+)
+
+# Or, configure per-request:
+openai.chat.completions.create(
+  messages: [{role: "user", content: "How can I get the name of the current day in JavaScript?"}],
+  model: :"gpt-4.1",
+  request_options: {max_retries: 5}
+)
+```
+
+### Timeouts
+
+By default, requests will time out after 600 seconds. You can use the timeout option to configure or disable this:
+
+```ruby
+# Configure the default for all requests:
+openai = OpenAI::Client.new(
+  timeout: nil # default is 600
+)
+
+# Or, configure per-request:
+openai.chat.completions.create(
+  messages: [{role: "user", content: "How can I list all files in a directory using Python?"}],
+  model: :"gpt-4.1",
+  request_options: {timeout: 5}
+)
+```
+
+On timeout, `OpenAI::Errors::APITimeoutError` is raised.
+
+Note that requests that time out are retried by default.
+
+## Advanced concepts
+
+### BaseModel
 
-Bug reports and pull requests are welcome on GitHub at https://github.com/nileshtrivedi/openai.
+All parameter and response objects inherit from `OpenAI::Internal::Type::BaseModel`, which provides several conveniences, including:
 
-## License
+1. All fields, including unknown ones, are accessible with `obj[:prop]` syntax, and can be destructured with `obj => {prop: prop}` or pattern-matching syntax.
+
+2. Structural equivalence for equality; if two API calls return the same values, comparing the responses with == will return true.
+
+3. Both instances and the classes themselves can be pretty-printed.
+
+4. Helpers such as `#to_h`, `#deep_to_h`, `#to_json`, and `#to_yaml`.
+
+### Making custom or undocumented requests
+
+#### Undocumented properties
+
+You can send undocumented parameters to any endpoint, and read undocumented response properties, like so:
+
+Note: the `extra_` parameters of the same name overrides the documented parameters.
+
+```ruby
+chat_completion =
+  openai.chat.completions.create(
+    messages: [{role: "user", content: "How can I get the name of the current day in JavaScript?"}],
+    model: :"gpt-4.1",
+    request_options: {
+      extra_query: {my_query_parameter: value},
+      extra_body: {my_body_parameter: value},
+      extra_headers: {"my-header": value}
+    }
+  )
+
+puts(chat_completion[:my_undocumented_property])
+```
+
+#### Undocumented request params
+
+If you want to explicitly send an extra param, you can do so with the `extra_query`, `extra_body`, and `extra_headers` under the `request_options:` parameter when making a request, as seen in the examples above.
+
+#### Undocumented endpoints
+
+To make requests to undocumented endpoints while retaining the benefit of auth, retries, and so on, you can make requests using `client.request`, like so:
+
+```ruby
+response = client.request(
+  method: :post,
+  path: '/undocumented/endpoint',
+  query: {"dog": "woof"},
+  headers: {"useful-header": "interesting-value"},
+  body: {"hello": "world"}
+)
+```
+
+### Concurrency & connection pooling
+
+The `OpenAI::Client` instances are threadsafe, but are only fork-safe when there are no in-flight HTTP requests.
+
+Each instance of `OpenAI::Client` has its own HTTP connection pool with a default size of 99. As such, we recommend instantiating the client once per application in most settings.
+
+When all available connections from the pool are checked out, requests wait for a new connection to become available, with queue time counting towards the request timeout.
+
+Unless otherwise specified, other classes in the SDK do not have locks protecting their underlying data structure.
+
+## Sorbet
+
+This library provides comprehensive [RBI](https://sorbet.org/docs/rbi) definitions and has no dependency on sorbet-runtime.
+
+You can provide typesafe request parameters like so:
+
+```ruby
+openai.chat.completions.create(
+  messages: [OpenAI::Chat::ChatCompletionUserMessageParam.new(role: "user", content: "Say this is a test")],
+  model: :"gpt-4.1"
+)
+```
+
+Or, equivalently:
+
+```ruby
+# Hashes work, but are not typesafe:
+openai.chat.completions.create(
+  messages: [{role: "user", content: "Say this is a test"}],
+  model: :"gpt-4.1"
+)
+
+# You can also splat a full Params class:
+params = OpenAI::Chat::CompletionCreateParams.new(
+  messages: [OpenAI::Chat::ChatCompletionUserMessageParam.new(role: "user", content: "Say this is a test")],
+  model: :"gpt-4.1"
+)
+openai.chat.completions.create(**params)
+```
+
+### Enums
+
+Since this library does not depend on `sorbet-runtime`, it cannot provide [`T::Enum`](https://sorbet.org/docs/tenum) instances. Instead, we provide "tagged symbols" instead, which is always a primitive at runtime:
+
+```ruby
+# :low
+puts(OpenAI::ReasoningEffort::LOW)
+
+# Revealed type: `T.all(OpenAI::ReasoningEffort, Symbol)`
+T.reveal_type(OpenAI::ReasoningEffort::LOW)
+```
+
+Enum parameters have a "relaxed" type, so you can either pass in enum constants or their literal value:
+
+```ruby
+# Using the enum constants preserves the tagged type information:
+openai.chat.completions.create(
+  reasoning_effort: OpenAI::ReasoningEffort::LOW,
+  # …
+)
+
+# Literal values are also permissible:
+openai.chat.completions.create(
+  reasoning_effort: :low,
+  # …
+)
+```
+
+## Versioning
+
+This package follows [SemVer](https://semver.org/spec/v2.0.0.html) conventions. As the library is in initial development and has a major version of `0`, APIs may change at any time.
+
+This package considers improvements to the (non-runtime) `*.rbi` and `*.rbs` type definitions to be non-breaking changes.
+
+## Requirements
+
+Ruby 3.2.0 or higher.
+
+## Contributing
 
-The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
+See [the contributing documentation](https://github.com/openai/openai-ruby/tree/main/CONTRIBUTING.md).

data/SECURITY.md

@@ -0,0 +1,29 @@
+# Security Policy
+
+## Reporting Security Issues
+
+This SDK is generated by [Stainless Software Inc](http://stainless.com). Stainless takes security seriously and encourages you to report any security vulnerability promptly so that appropriate action can be taken.
+
+To report a security issue, please contact the Stainless team at security@stainless.com.
+
+## Responsible Disclosure
+
+We appreciate the efforts of security researchers and individuals who help us maintain the security of
+SDKs we generate. If you believe you have found a security vulnerability, please adhere to responsible
+disclosure practices by allowing us a reasonable amount of time to investigate and address the issue
+before making any information public.
+
+## Reporting Non-SDK Related Security Issues
+
+If you encounter security issues that are not directly related to SDKs but pertain to the services
+or products provided by OpenAI, please follow the respective company's security reporting guidelines.
+
+### OpenAI Terms and Policies
+
+Our Security Policy can be found at [Security Policy URL](https://openai.com/policies/coordinated-vulnerability-disclosure-policy).
+
+Please contact disclosure@openai.com for any questions or concerns regarding the security of our services.
+
+---
+
+Thank you for helping us keep the SDKs and systems they interact with secure.

data/lib/openai/client.rb

@@ -1,140 +1,156 @@
-require "json"
-require "net/http"
-require "time"
-require "uri"
+# frozen_string_literal: true
 
 module OpenAI
-  class Client
-    class Error < RuntimeError
-    end
+  class Client < OpenAI::Internal::Transport::BaseClient
+    # Default max number of retries to attempt after a failed retryable request.
+    DEFAULT_MAX_RETRIES = 2
 
-    LastResponse = Struct.new(:date, :organization, :processing_ms, :request_id, :status_code, :status_message, keyword_init: true)
+    # Default per-request timeout.
+    DEFAULT_TIMEOUT_IN_SECONDS = 600.0
 
-    attr_reader :last_response
-    attr_writer :api_key
-    attr_accessor :default_engine
+    # Default initial retry delay in seconds.
+    # Overall delay is calculated using exponential backoff + jitter.
+    DEFAULT_INITIAL_RETRY_DELAY = 0.5
 
-    def initialize(api_key:, default_engine: "davinci")
-      @api_key = api_key
-      @default_engine = default_engine
-    end
+    # Default max retry delay in seconds.
+    DEFAULT_MAX_RETRY_DELAY = 8.0
 
-    def engine(id = default_engine)
-      engine = get("/v1/engines/#{id}")
-      Engine.new(**engine)
-    end
+    # @return [String]
+    attr_reader :api_key
 
-    def engines
-      engines = get("/v1/engines")
-      engines[:data].map do |engine|
-        Engine.new(**engine)
-      end
-    end
+    # @return [String, nil]
+    attr_reader :organization
 
-    def completions(prompt: nil, max_tokens: nil, temperature: nil, top_p: nil, n: nil, logprobs: nil, echo: nil, stop: nil, presence_penalty: nil, frequency_penalty: nil, best_of: nil, engine: default_engine)
-      body = {
-        "prompt"            => prompt,
-        "max_tokens"        => max_tokens,
-        "temperature"       => temperature,
-        "top_p"             => top_p,
-        "n"                 => n,
-        "logprobs"          => logprobs,
-        "echo"              => echo,
-        "stop"              => stop,
-        "presence_penalty"  => presence_penalty,
-        "frequency_penalty" => frequency_penalty,
-        "best_of"           => best_of,
-      }.compact
-
-      completion = post("/v1/engines/#{engine}/completions", body: body)
-
-      choices = completion[:choices]&.map do |choice|
-        Choice.new(
-          finish_reason: choice[:finish_reason],
-          index: choice[:index],
-          text: choice[:text],
-          logprobs: choice[:logprobs]&.tap do |logprob|
-            Logprobs.new(
-              text_offset: logprob[:text_offset],
-              token_logprobs: logprob[:token_logprobs],
-              tokens: logprob[:tokens],
-              top_logprobs: logprob[:top_logprobs]
-            )
-          end
-        )
-      end
+    # @return [String, nil]
+    attr_reader :project
 
-      Completion.new(
-        choices: choices,
-        created: completion[:created],
-        id: completion[:id],
-        model: completion[:model],
-        object: completion[:object]
-      )
-    end
+    # @return [OpenAI::Resources::Completions]
+    attr_reader :completions
 
-    def search(documents:, query:, engine: default_engine)
-      body = {
-        "documents" => documents,
-        "query"     => query,
-      }.compact
-
-      search_results = post("/v1/engines/#{engine}/search", body: body)
-      search_results[:data].map.with_index do |datum, index|
-        SearchResult.new(**datum).tap do |result|
-          result.text = documents[index]
-        end
-      end
-    end
+    # @return [OpenAI::Resources::Chat]
+    attr_reader :chat
 
-    private def get(path)
-      uri = URI.parse("https://api.openai.com#{path}")
-      req = Net::HTTP::Get.new(uri)
-      headers.each do |name, value|
-        req[name] = value
-      end
-      response = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) do |http|
-        http.request(req)
-      end
-      handle_response(response)
-    end
+    # @return [OpenAI::Resources::Embeddings]
+    attr_reader :embeddings
 
-    private def post(path, body: nil)
-      uri = URI.parse("https://api.openai.com#{path}")
-      req = Net::HTTP::Post.new(uri)
-      req.body = body.to_json
-      headers.each do |name, value|
-        req[name] = value
-      end
-      response = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) do |http|
-        http.request(req)
-      end
-      handle_response(response)
+    # @return [OpenAI::Resources::Files]
+    attr_reader :files
+
+    # @return [OpenAI::Resources::Images]
+    attr_reader :images
+
+    # @return [OpenAI::Resources::Audio]
+    attr_reader :audio
+
+    # @return [OpenAI::Resources::Moderations]
+    attr_reader :moderations
+
+    # @return [OpenAI::Resources::Models]
+    attr_reader :models
+
+    # @return [OpenAI::Resources::FineTuning]
+    attr_reader :fine_tuning
+
+    # @return [OpenAI::Resources::Graders]
+    attr_reader :graders
+
+    # @return [OpenAI::Resources::VectorStores]
+    attr_reader :vector_stores
+
+    # @return [OpenAI::Resources::Beta]
+    attr_reader :beta
+
+    # @return [OpenAI::Resources::Batches]
+    attr_reader :batches
+
+    # @return [OpenAI::Resources::Uploads]
+    attr_reader :uploads
+
+    # @return [OpenAI::Resources::Responses]
+    attr_reader :responses
+
+    # @return [OpenAI::Resources::Evals]
+    attr_reader :evals
+
+    # @return [OpenAI::Resources::Containers]
+    attr_reader :containers
+
+    # @api private
+    #
+    # @return [Hash{String=>String}]
+    private def auth_headers
+      return {} if @api_key.nil?
+
+      {"authorization" => "Bearer #{@api_key}"}
     end
 
-    private def handle_response(response)
-      date = Time.httpdate(response["date"]) if response["date"]
-      organization = response["openai-organization"]
-      processing_ms = response["openai-processing-ms"]&.to_i
-      request_id = response["x-request-id"]
-      status_code = response.code&.to_i
-      status_message = response.message
-      @last_response = LastResponse.new(date: date, organization: organization, processing_ms: processing_ms, request_id: request_id, status_code: status_code, status_message: status_message)
-
-      response_body = JSON.parse(response.body, symbolize_names: true)
-      case response
-      when Net::HTTPSuccess
-        response_body
-      else
-        raise Error, response_body[:error][:message].to_s
+    # Creates and returns a new client for interacting with the API.
+    #
+    # @param api_key [String, nil] Defaults to `ENV["OPENAI_API_KEY"]`
+    #
+    # @param organization [String, nil] Defaults to `ENV["OPENAI_ORG_ID"]`
+    #
+    # @param project [String, nil] Defaults to `ENV["OPENAI_PROJECT_ID"]`
+    #
+    # @param base_url [String, nil] Override the default base URL for the API, e.g.,
+    # `"https://api.example.com/v2/"`. Defaults to `ENV["OPENAI_BASE_URL"]`
+    #
+    # @param max_retries [Integer] Max number of retries to attempt after a failed retryable request.
+    #
+    # @param timeout [Float]
+    #
+    # @param initial_retry_delay [Float]
+    #
+    # @param max_retry_delay [Float]
+    def initialize(
+      api_key: ENV["OPENAI_API_KEY"],
+      organization: ENV["OPENAI_ORG_ID"],
+      project: ENV["OPENAI_PROJECT_ID"],
+      base_url: ENV["OPENAI_BASE_URL"],
+      max_retries: self.class::DEFAULT_MAX_RETRIES,
+      timeout: self.class::DEFAULT_TIMEOUT_IN_SECONDS,
+      initial_retry_delay: self.class::DEFAULT_INITIAL_RETRY_DELAY,
+      max_retry_delay: self.class::DEFAULT_MAX_RETRY_DELAY
+    )
+      base_url ||= "https://api.openai.com/v1"
+
+      if api_key.nil?
+        raise ArgumentError.new("api_key is required, and can be set via environ: \"OPENAI_API_KEY\"")
       end
-    end
 
-    private def headers
-      @headers ||= {
-        "Authorization" => "Bearer #{@api_key}",
-        "Content-Type"  => "application/json",
+      headers = {
+        "openai-organization" => (@organization = organization&.to_s),
+        "openai-project" => (@project = project&.to_s)
       }
+
+      @api_key = api_key.to_s
+
+      super(
+        base_url: base_url,
+        timeout: timeout,
+        max_retries: max_retries,
+        initial_retry_delay: initial_retry_delay,
+        max_retry_delay: max_retry_delay,
+        headers: headers
+      )
+
+      @completions = OpenAI::Resources::Completions.new(client: self)
+      @chat = OpenAI::Resources::Chat.new(client: self)
+      @embeddings = OpenAI::Resources::Embeddings.new(client: self)
+      @files = OpenAI::Resources::Files.new(client: self)
+      @images = OpenAI::Resources::Images.new(client: self)
+      @audio = OpenAI::Resources::Audio.new(client: self)
+      @moderations = OpenAI::Resources::Moderations.new(client: self)
+      @models = OpenAI::Resources::Models.new(client: self)
+      @fine_tuning = OpenAI::Resources::FineTuning.new(client: self)
+      @graders = OpenAI::Resources::Graders.new(client: self)
+      @vector_stores = OpenAI::Resources::VectorStores.new(client: self)
+      @beta = OpenAI::Resources::Beta.new(client: self)
+      @batches = OpenAI::Resources::Batches.new(client: self)
+      @uploads = OpenAI::Resources::Uploads.new(client: self)
+      @responses = OpenAI::Resources::Responses.new(client: self)
+      @evals = OpenAI::Resources::Evals.new(client: self)
+      @containers = OpenAI::Resources::Containers.new(client: self)
     end
   end
 end