ruby-openai 4.0.0 → 6.3.1

data/README.md

@@ -1,14 +1,14 @@
 # Ruby OpenAI
 
-[![Gem Version](https://badge.fury.io/rb/ruby-openai.svg)](https://badge.fury.io/rb/ruby-openai)
+[![Gem Version](https://img.shields.io/gem/v/ruby-openai.svg)](https://rubygems.org/gems/ruby-openai)
 [![GitHub license](https://img.shields.io/badge/license-MIT-blue.svg)](https://github.com/alexrudall/ruby-openai/blob/main/LICENSE.txt)
 [![CircleCI Build Status](https://circleci.com/gh/alexrudall/ruby-openai.svg?style=shield)](https://circleci.com/gh/alexrudall/ruby-openai)
 
-Use the [OpenAI API](https://openai.com/blog/openai-api/) with Ruby! 🤖❤️
+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)
+[🚢 Hire me](https://peaceterms.com?utm_source=ruby-openai&utm_medium=readme&utm_id=26072023) | [🎮 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
 
@@ -20,13 +20,17 @@ gem "ruby-openai"
 
 And then execute:
 
+```bash
 $ bundle install
+```
 
 ### Gem install
 
 Or install with:
 
+```bash
 $ gem install ruby-openai
+```
 
 and require with:
 
@@ -36,8 +40,8 @@ require "openai"
 
 ## Usage
 
-- Get your API key from [https://beta.openai.com/account/api-keys](https://beta.openai.com/account/api-keys)
-- If you belong to multiple organizations, you can get your Organization ID from [https://beta.openai.com/account/org-settings](https://beta.openai.com/account/org-settings)
+- Get your API key from [https://platform.openai.com/account/api-keys](https://platform.openai.com/account/api-keys)
+- If you belong to multiple organizations, you can get your Organization ID from [https://platform.openai.com/account/org-settings](https://platform.openai.com/account/org-settings)
 
 ### Quickstart
 
@@ -64,15 +68,27 @@ Then you can create a client like this:
 client = OpenAI::Client.new
 ```
 
+You can still override the config defaults when making new clients; any options not included will fall back to any global config set with OpenAI.configure. e.g. in this example the organization_id, request_timeout, etc. will fallback to any set globally using OpenAI.configure, with only the access_token overridden:
+
+```ruby
+client = OpenAI::Client.new(access_token: "access_token_goes_here")
+```
+
 #### Custom timeout or base URI
 
-The default timeout for any request using this library is 120 seconds. You can change that by passing a number of seconds to the `request_timeout` when initializing the client. You can also change the base URI used for all requests, eg. to use observability tools like [Helicone](https://docs.helicone.ai/quickstart/integrate-in-one-line-of-code):
+The default timeout for any request using this library is 120 seconds. You can change that by passing a number of seconds to the `request_timeout` when initializing the client. You can also change the base URI used for all requests, eg. to use observability tools like [Helicone](https://docs.helicone.ai/quickstart/integrate-in-one-line-of-code), and add arbitrary other headers e.g. for [openai-caching-proxy-worker](https://github.com/6/openai-caching-proxy-worker):
 
 ```ruby
 client = OpenAI::Client.new(
     access_token: "access_token_goes_here",
     uri_base: "https://oai.hconeai.com/",
-    request_timeout: 240
+    request_timeout: 240,
+    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-stream-force-format" => "true", # Use this with Helicone otherwise streaming drops chunks # https://github.com/alexrudall/ruby-openai/issues/251
+    }
 )
 ```
 
@@ -84,9 +100,51 @@ OpenAI.configure do |config|
     config.organization_id = ENV.fetch("OPENAI_ORGANIZATION_ID") # Optional
     config.uri_base = "https://oai.hconeai.com/" # Optional
     config.request_timeout = 240 # Optional
+    config.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
+    } # Optional
 end
 ```
 
+#### Verbose Logging
+
+You can pass [Faraday middleware](https://lostisland.github.io/faraday/#/middleware/index) to the client in a block, eg. to enable verbose logging with Ruby's [Logger](https://ruby-doc.org/3.2.2/stdlibs/logger/Logger.html):
+
+```ruby
+  client = OpenAI::Client.new do |f|
+    f.response :logger, Logger.new($stdout), bodies: true
+  end
+```
+
+#### Azure
+
+To use the [Azure OpenAI Service](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/) API, you can configure the gem like this:
+
+```ruby
+    OpenAI.configure do |config|
+        config.access_token = ENV.fetch("AZURE_OPENAI_API_KEY")
+        config.uri_base = ENV.fetch("AZURE_OPENAI_URI")
+        config.api_type = :azure
+        config.api_version = "2023-03-15-preview"
+    end
+```
+
+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:
@@ -99,7 +157,7 @@ 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)
@@ -111,9 +169,9 @@ 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(
@@ -126,9 +184,11 @@ puts response.dig("choices", 0, "message", "content")
 # => "Hello! How may I assist you today?"
 ```
 
-### Streaming ChatGPT
+#### Streaming Chat
+
+[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) 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(
@@ -143,19 +203,139 @@ client.chat(
 # => "Anna is a young woman in her mid-twenties, with wavy chestnut hair that falls to her shoulders..."
 ```
 
-### Completions
+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.
 
-Hit the OpenAI API for a completion using other GPT-3 models:
+#### Vision
+
+You can use the GPT-4 Vision model to generate a description of an image:
 
 ```ruby
-response = client.completions(
+messages = [
+  { "type": "text", "text": "What’s in this image?"},
+  { "type": "image_url",
+    "image_url": {
+      "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
+    },
+  }
+]
+response = client.chat(
     parameters: {
-        model: "text-davinci-001",
-        prompt: "Once upon a time",
-        max_tokens: 5
+        model: "gpt-4-vision-preview", # Required.
+        messages: [{ role: "user", content: messages}], # Required.
     })
-puts response["choices"].map { |c| c["text"] }
-# => [", there lived a great"]
+puts response.dig("choices", 0, "message", "content")
+# => "The image depicts a serene natural landscape featuring a long wooden boardwalk extending straight ahead"
+```
+
+#### JSON Mode
+
+You can set the response_format to ask for responses in JSON (at least for `gpt-3.5-turbo-1106`):
+
+```ruby
+  response = client.chat(
+    parameters: {
+        model: "gpt-3.5-turbo-1106",
+        response_format: { type: "json_object" },
+        messages: [{ role: "user", content: "Hello! Give me some JSON please."}],
+        temperature: 0.7,
+    })
+    puts response.dig("choices", 0, "message", "content")
+    {
+      "name": "John",
+      "age": 30,
+      "city": "New York",
+      "hobbies": ["reading", "traveling", "hiking"],
+      "isStudent": false
+    }
+```
+
+You can stream it as well!
+
+```ruby
+  response = client.chat(
+    parameters: {
+      model: "gpt-3.5-turbo-1106",
+      messages: [{ role: "user", content: "Can I have some JSON please?"}],
+        response_format: { type: "json_object" },
+        stream: proc do |chunk, _bytesize|
+          print chunk.dig("choices", 0, "delta", "content")
+        end
+  })
+  {
+    "message": "Sure, please let me know what specific JSON data you are looking for.",
+    "JSON_data": {
+      "example_1": {
+        "key_1": "value_1",
+        "key_2": "value_2",
+        "key_3": "value_3"
+      },
+      "example_2": {
+        "key_4": "value_4",
+        "key_5": "value_5",
+        "key_6": "value_6"
+      }
+    }
+  }
+```
+
+### Functions
+
+You can describe and pass in functions and the model will intelligently choose to output a JSON object containing arguments to call those them. For example, if you want the model to use your method `get_current_weather` to get the current weather in a given location:
+
+```ruby
+def get_current_weather(location:, unit: "fahrenheit")
+  # use a weather api to fetch weather
+end
+
+response =
+  client.chat(
+    parameters: {
+      model: "gpt-3.5-turbo-0613",
+      messages: [
+        {
+          "role": "user",
+          "content": "What is the weather like in San Francisco?",
+        },
+      ],
+      functions: [
+        {
+          name: "get_current_weather",
+          description: "Get the current weather in a given location",
+          parameters: {
+            type: :object,
+            properties: {
+              location: {
+                type: :string,
+                description: "The city and state, e.g. San Francisco, CA",
+              },
+              unit: {
+                type: "string",
+                enum: %w[celsius fahrenheit],
+              },
+            },
+            required: ["location"],
+          },
+        },
+      ],
+    },
+  )
+
+message = response.dig("choices", 0, "message")
+
+if message["role"] == "assistant" && message["function_call"]
+  function_name = message.dig("function_call", "name")
+  args =
+    JSON.parse(
+      message.dig("function_call", "arguments"),
+      { symbolize_names: true },
+    )
+
+  case function_name
+  when "get_current_weather"
+    get_current_weather(**args)
+  end
+end
+# => "The weather is nice 🌞"
 ```
 
 ### Edits
@@ -179,12 +359,15 @@ puts response.dig("choices", 0, "text")
 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(
+response = client.embeddings(
     parameters: {
-        model: "babbage-similarity",
+        model: "text-embedding-ada-002",
         input: "The food was delicious and the waiter..."
     }
 )
+
+puts response.dig("data", 0, "embedding")
+# => Vector representation of your embedding
 ```
 
 ### Files
@@ -206,22 +389,22 @@ 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"]
 ```
@@ -252,10 +435,10 @@ 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
@@ -315,7 +498,7 @@ Whisper is a speech to text model that can be used to generate text based on aud
 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(
+response = client.audio.translate(
     parameters: {
         model: "whisper-1",
         file: File.open("path_to_file", "rb"),
@@ -329,7 +512,7 @@ puts response["text"]
 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(
+response = client.audio.transcribe(
     parameters: {
         model: "whisper-1",
         file: File.open("path_to_file", "rb"),
@@ -338,6 +521,34 @@ puts response["text"]
 # => "Transcription of the text"
 ```
 
+#### Speech
+
+The speech API takes as input the text and a voice and returns the content of an audio file you can listen to.
+
+```ruby
+response = client.audio.speech(
+  parameters: {
+    model: "tts-1",
+    input: "This is a speech test!",
+    voice: "alloy"
+  }
+)
+File.binwrite('demo.mp3', response)
+# => mp3 file that plays: "This is a speech test!"
+```
+
+### 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/assistants.rb

@@ -0,0 +1,27 @@
+module OpenAI
+  class Assistants
+    def initialize(client:)
+      @client = client.beta(assistants: "v1")
+    end
+
+    def list
+      @client.get(path: "/assistants")
+    end
+
+    def retrieve(id:)
+      @client.get(path: "/assistants/#{id}")
+    end
+
+    def create(parameters: {})
+      @client.json_post(path: "/assistants", parameters: parameters)
+    end
+
+    def modify(id:, parameters: {})
+      @client.json_post(path: "/assistants/#{id}", parameters: parameters)
+    end
+
+    def delete(id:)
+      @client.delete(path: "/assistants/#{id}")
+    end
+  end
+end

data/lib/openai/audio.rb

@@ -0,0 +1,19 @@
+module OpenAI
+  class Audio
+    def initialize(client:)
+      @client = client
+    end
+
+    def transcribe(parameters: {})
+      @client.multipart_post(path: "/audio/transcriptions", parameters: parameters)
+    end
+
+    def translate(parameters: {})
+      @client.multipart_post(path: "/audio/translations", parameters: parameters)
+    end
+
+    def speech(parameters: {})
+      @client.json_post(path: "/audio/speech", parameters: parameters)
+    end
+  end
+end

data/lib/openai/client.rb

@@ -1,56 +1,91 @@
 module OpenAI
   class Client
-    extend OpenAI::HTTP
+    include OpenAI::HTTP
 
-    def initialize(access_token: nil, organization_id: nil, uri_base: nil, request_timeout: nil)
-      OpenAI.configuration.access_token = access_token if access_token
-      OpenAI.configuration.organization_id = organization_id if organization_id
-      OpenAI.configuration.uri_base = uri_base if uri_base
-      OpenAI.configuration.request_timeout = request_timeout if request_timeout
-    end
+    CONFIG_KEYS = %i[
+      api_type
+      api_version
+      access_token
+      organization_id
+      uri_base
+      request_timeout
+      extra_headers
+    ].freeze
+    attr_reader *CONFIG_KEYS, :faraday_middleware
 
-    def chat(parameters: {})
-      OpenAI::Client.json_post(path: "/chat/completions", parameters: parameters)
+    def initialize(config = {}, &faraday_middleware)
+      CONFIG_KEYS.each do |key|
+        # Set instance variables like api_type & access_token. Fall back to global config
+        # if not present.
+        instance_variable_set("@#{key}", config[key] || OpenAI.configuration.send(key))
+      end
+      @faraday_middleware = faraday_middleware
     end
 
-    def completions(parameters: {})
-      OpenAI::Client.json_post(path: "/completions", parameters: parameters)
+    def chat(parameters: {})
+      json_post(path: "/chat/completions", parameters: parameters)
     end
 
     def edits(parameters: {})
-      OpenAI::Client.json_post(path: "/edits", parameters: parameters)
+      json_post(path: "/edits", parameters: parameters)
     end
 
     def embeddings(parameters: {})
-      OpenAI::Client.json_post(path: "/embeddings", parameters: parameters)
+      json_post(path: "/embeddings", parameters: parameters)
+    end
+
+    def audio
+      @audio ||= OpenAI::Audio.new(client: self)
     end
 
     def files
-      @files ||= OpenAI::Files.new
+      @files ||= OpenAI::Files.new(client: self)
     end
 
     def finetunes
-      @finetunes ||= OpenAI::Finetunes.new
+      @finetunes ||= OpenAI::Finetunes.new(client: self)
     end
 
     def images
-      @images ||= OpenAI::Images.new
+      @images ||= OpenAI::Images.new(client: self)
     end
 
     def models
-      @models ||= OpenAI::Models.new
+      @models ||= OpenAI::Models.new(client: self)
+    end
+
+    def assistants
+      @assistants ||= OpenAI::Assistants.new(client: self)
+    end
+
+    def threads
+      @threads ||= OpenAI::Threads.new(client: self)
+    end
+
+    def messages
+      @messages ||= OpenAI::Messages.new(client: self)
+    end
+
+    def runs
+      @runs ||= OpenAI::Runs.new(client: self)
+    end
+
+    def run_steps
+      @run_steps ||= OpenAI::RunSteps.new(client: self)
     end
 
     def moderations(parameters: {})
-      OpenAI::Client.json_post(path: "/moderations", parameters: parameters)
+      json_post(path: "/moderations", parameters: parameters)
     end
 
-    def transcribe(parameters: {})
-      OpenAI::Client.multipart_post(path: "/audio/transcriptions", parameters: parameters)
+    def azure?
+      @api_type&.to_sym == :azure
     end
 
-    def translate(parameters: {})
-      OpenAI::Client.multipart_post(path: "/audio/translations", parameters: parameters)
+    def beta(apis)
+      dup.tap do |client|
+        client.add_headers("OpenAI-Beta": apis.map { |k, v| "#{k}=#{v}" }.join(";"))
+      end
     end
   end
 end

data/lib/openai/compatibility.rb

@@ -5,5 +5,6 @@ module Ruby
     Error = ::OpenAI::Error
     ConfigurationError = ::OpenAI::ConfigurationError
     Configuration = ::OpenAI::Configuration
+    MiddlewareErrors = ::OpenAI::MiddlewareErrors
   end
 end

data/lib/openai/files.rb

@@ -1,33 +1,32 @@
 module OpenAI
   class Files
-    def initialize(access_token: nil, organization_id: nil)
-      OpenAI.configuration.access_token = access_token if access_token
-      OpenAI.configuration.organization_id = organization_id if organization_id
+    def initialize(client:)
+      @client = client
     end
 
     def list
-      OpenAI::Client.get(path: "/files")
+      @client.get(path: "/files")
     end
 
     def upload(parameters: {})
-      validate(file: parameters[:file])
+      validate(file: parameters[:file]) if parameters[:file].include?(".jsonl")
 
-      OpenAI::Client.multipart_post(
+      @client.multipart_post(
         path: "/files",
         parameters: parameters.merge(file: File.open(parameters[:file]))
       )
     end
 
     def retrieve(id:)
-      OpenAI::Client.get(path: "/files/#{id}")
+      @client.get(path: "/files/#{id}")
     end
 
     def content(id:)
-      OpenAI::Client.get(path: "/files/#{id}/content")
+      @client.get(path: "/files/#{id}/content")
     end
 
     def delete(id:)
-      OpenAI::Client.delete(path: "/files/#{id}")
+      @client.delete(path: "/files/#{id}")
     end
 
     private

data/lib/openai/finetunes.rb

@@ -1,36 +1,27 @@
 module OpenAI
   class Finetunes
-    def initialize(access_token: nil, organization_id: nil)
-      OpenAI.configuration.access_token = access_token if access_token
-      OpenAI.configuration.organization_id = organization_id if organization_id
+    def initialize(client:)
+      @client = client
     end
 
     def list
-      OpenAI::Client.get(path: "/fine-tunes")
+      @client.get(path: "/fine_tuning/jobs")
     end
 
     def create(parameters: {})
-      OpenAI::Client.json_post(path: "/fine-tunes", parameters: parameters)
+      @client.json_post(path: "/fine_tuning/jobs", parameters: parameters)
     end
 
     def retrieve(id:)
-      OpenAI::Client.get(path: "/fine-tunes/#{id}")
+      @client.get(path: "/fine_tuning/jobs/#{id}")
     end
 
     def cancel(id:)
-      OpenAI::Client.multipart_post(path: "/fine-tunes/#{id}/cancel")
+      @client.json_post(path: "/fine_tuning/jobs/#{id}/cancel", parameters: {})
     end
 
-    def events(id:)
-      OpenAI::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
-
-      OpenAI::Client.delete(path: "/models/#{fine_tuned_model}")
+    def list_events(id:)
+      @client.get(path: "/fine_tuning/jobs/#{id}/events")
     end
   end
 end