ruby-openai 4.1.0 → 4.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: '06199aaabd11e965f6d07f3948323b5226fdda82f09326c065cda4b5b2cc9237'
-  data.tar.gz: 59cce00dfeb08270e11b2c33b23af4558dfc53796c87ebb6cf64b1cb76739790
+  metadata.gz: 666cf605fbc981b59131ef5005ec32fd0eabd604f924d907ae0ee0d707b739bb
+  data.tar.gz: fe938931bad97952bd8829ab1ec336896c12ed247c18bc62f3df116917919498
 SHA512:
-  metadata.gz: 1d9b9409e915f49284f8acdf4be10cde81d7065fadb254dc135aeaad5572c2278c3bb6115752e8c43619d4ea60d696bc55a8128af8981ec544db2320c2d4b89a
-  data.tar.gz: a202ca506f515e8933f00e0302dcd8a59b8d15f6b11c13263499ac140b9b045162089141f27cab5dda2dbde3d5b960c05c8081415a721b29cbdffcd3d375ddd0
+  metadata.gz: 2799064a7bbfc79dc47ea4168b0a7755e53aad89e3f3d55a79defba569592141aca70bdfd86747d1690b4ab72acf0d542844d6dd7f1fc8e235c6e3bf7f911854
+  data.tar.gz: d81441ee5b5a1b4070c438ae02f363b95f133d571971c9876bd1cc239225cbd193955c4ce23efbba0c45af6d2726d06bd6d27b418a2a682edcf9de5c1c701b7f

data/.gitignore

@@ -1,16 +1,74 @@
-/.bundle/
-/.yardoc
-/_yardoc/
+### Ruby ###
+*.gem
+*.rbc
+/.config
 /coverage/
-/doc/
+/InstalledFiles
 /pkg/
 /spec/reports/
+/spec/examples.txt
+/test/tmp/
+/test/version_tmp/
 /tmp/
+/.bundle/
+/.yardoc
+/_yardoc/
+/doc/
+
+
+# Used by dotenv library to load environment variables.
+.env
+
+# Ignore Byebug command history file.
+.byebug_history
+
+## Specific to RubyMotion:
+.dat*
+.repl_history
+build/
+*.bridgesupport
+build-iPhoneOS/
+build-iPhoneSimulator/
+
+## Specific to RubyMotion (use of CocoaPods):
+#
+# We recommend against adding the Pods directory to your .gitignore. However
+# you should judge for yourself, the pros and cons are mentioned at:
+# https://guides.cocoapods.org/using/using-cocoapods.html#should-i-check-the-pods-directory-into-source-control
+# vendor/Pods/
+
+## Documentation cache and generated files:
+/.yardoc/
+/_yardoc/
+/doc/
+/rdoc/
+
+## Environment normalization:
+/.bundle/
+/vendor/bundle
+/lib/bundler/man/
+
+# for a library or gem, you might want to ignore these files since the code is
+# intended to run in multiple environments; otherwise, check them in:
+# Gemfile.lock
+# .ruby-version
+# .ruby-gemset
+
+# unless supporting rvm < 1.11.0 or doing something fancy, ignore this:
+.rvmrc
+
+# Used by RuboCop. Remote config files pulled in from inherit_from directive.
+# .rubocop-https?--*
 
 # rspec failure tracking
 .rspec_status
 
-.byebug_history
-.env
+# IDE
+.idea
+.idea/
+.idea/*
+.vscode
+.vs/
 
-*.gem
+# Mac
+.DS_Store

data/CHANGELOG.md

@@ -5,6 +5,18 @@ 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).
 
+## [4.3.0] - 2023-06-20
+
+### Added
+
+- Add extra-headers to config to allow setting openai-caching-proxy-worker TTL, Helicone Auth and anything else ya need. Ty to [@deltaguita](https://github.com/deltaguita) and [@marckohlbrugge](https://github.com/marckohlbrugge) for the PR!
+
+## [4.2.0] - 2023-06-20
+
+### Added
+
+- Add Azure OpenAI Service support. Thanks to [@rmachielse](https://github.com/rmachielse) and [@steffansluis](https://github.com/steffansluis) for the PR and to everyone who requested this feature!
+
 ## [4.1.0] - 2023-05-15
 
 ### Added

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    ruby-openai (4.1.0)
+    ruby-openai (4.3.0)
       faraday (>= 1)
       faraday-multipart (>= 1)
 
@@ -16,7 +16,7 @@ GEM
       rexml
     diff-lcs (1.5.0)
     dotenv (2.8.1)
-    faraday (2.7.4)
+    faraday (2.7.10)
       faraday-net_http (>= 2.0, < 3.1)
       ruby2_keywords (>= 0.0.4)
     faraday-multipart (1.0.4)

data/README.md

@@ -70,13 +70,18 @@ client = OpenAI::Client.new
 
 #### 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
+    }
 )
 ```
 
@@ -88,9 +93,29 @@ 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
 ```
 
+#### 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`
+
 ### Models
 
 There are different models that can be used to generate text. For a full list and to retrieve information about a single model:
@@ -149,6 +174,68 @@ 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).
+
+### 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 🌞"
+```
+
 ### Completions
 
 Hit the OpenAI API for a completion using other GPT-3 models:
@@ -185,12 +272,15 @@ 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

data/lib/openai/client.rb

@@ -2,11 +2,13 @@ module OpenAI
   class Client
     extend OpenAI::HTTP
 
-    def initialize(access_token: nil, organization_id: nil, uri_base: nil, request_timeout: nil)
+    def initialize(access_token: nil, organization_id: nil, uri_base: nil, request_timeout: nil,
+                   extra_headers: {})
       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
+      OpenAI.configuration.extra_headers = extra_headers
     end
 
     def chat(parameters: {})

data/lib/openai/http.rb

@@ -70,14 +70,28 @@ module OpenAI
     end
 
     def uri(path:)
-      OpenAI.configuration.uri_base + OpenAI.configuration.api_version + path
+      if OpenAI.configuration.api_type == :azure
+        base = File.join(OpenAI.configuration.uri_base, path)
+        "#{base}?api-version=#{OpenAI.configuration.api_version}"
+      else
+        File.join(OpenAI.configuration.uri_base, OpenAI.configuration.api_version, path)
+      end
     end
 
     def headers
+      return azure_headers if OpenAI.configuration.api_type == :azure
+
       {
         "Content-Type" => "application/json",
         "Authorization" => "Bearer #{OpenAI.configuration.access_token}",
         "OpenAI-Organization" => OpenAI.configuration.organization_id
+      }.merge(OpenAI.configuration.extra_headers)
+    end
+
+    def azure_headers
+      {
+        "Content-Type" => "application/json",
+        "api-key" => OpenAI.configuration.access_token
       }
     end
 

data/lib/openai/version.rb

@@ -1,3 +1,3 @@
 module OpenAI
-  VERSION = "4.1.0".freeze
+  VERSION = "4.3.0".freeze
 end

data/lib/openai.rb

@@ -15,7 +15,8 @@ module OpenAI
 
   class Configuration
     attr_writer :access_token
-    attr_accessor :api_version, :organization_id, :uri_base, :request_timeout
+    attr_accessor :api_type, :api_version, :organization_id, :uri_base, :request_timeout,
+                  :extra_headers
 
     DEFAULT_API_VERSION = "v1".freeze
     DEFAULT_URI_BASE = "https://api.openai.com/".freeze
@@ -23,6 +24,7 @@ module OpenAI
 
     def initialize
       @access_token = nil
+      @api_type = nil
       @api_version = DEFAULT_API_VERSION
       @organization_id = nil
       @uri_base = DEFAULT_URI_BASE

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: ruby-openai
 version: !ruby/object:Gem::Version
-  version: 4.1.0
+  version: 4.3.0
 platform: ruby
 authors:
 - Alex
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2023-05-15 00:00:00.000000000 Z
+date: 2023-08-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: faraday