7.0.0

.circleci/config.yml

@@ -8,7 +8,7 @@ jobs:
   rubocop:
     parallelism: 1
     docker:
-      - image: cimg/ruby:3.1-node
+      - image: cimg/ruby:3.2-node
     steps:
       - checkout
       - ruby/install-deps
@@ -43,3 +43,4 @@ workflows:
                 - cimg/ruby:3.0-node
                 - cimg/ruby:3.1-node
                 - cimg/ruby:3.2-node
+                - cimg/ruby:3.3-node

CHANGELOG.md

@@ -5,6 +5,35 @@ 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).
 
+## [7.0.0] - 2024-04-27
+
+### Added
+
+- Add support for Batches, thanks to [@simonx1](https://github.com/simonx1) for the PR!
+- Allow use of local LLMs like Ollama! Thanks to [@ThomasSevestre](https://github.com/ThomasSevestre)
+- Update to v2 of the Assistants beta & add documentation on streaming from an Assistant.
+- Add Assistants endpoint to create and run a thread in one go, thank you [@quocphien90](https://github.com/
+  quocphien90)
+- Add missing parameters (order, limit, etc) to Runs, RunSteps and Messages - thanks to [@shalecraig](https://github.com/shalecraig) and [@coezbek](https://github.com/coezbek)
+- Add missing Messages#list spec - thanks [@adammeghji](https://github.com/adammeghji)
+- Add Messages#modify to README - thanks to [@nas887](https://github.com/nas887)
+- Don't add the api_version (`/v1/`) to base_uris that already include it - thanks to [@kaiwren](https://github.com/kaiwren) for raising this issue
+- Allow passing a `StringIO` to Files#upload - thanks again to [@simonx1](https://github.com/simonx1)
+- Add Ruby 3.3 to CI
+
+### Security
+
+- [BREAKING] ruby-openai will no longer log out API errors by default - you can reenable by passing `log_errors: true` to your client. This will help to prevent leaking secrets to logs. Thanks to [@lalunamel](https://github.com/lalunamel) for this PR.
+
+### Removed
+
+- [BREAKING] Remove deprecated edits endpoint.
+
+### Fixed
+
+- Fix README DALL·E 3 error - thanks to [@clayton](https://github.com/clayton)
+- Fix README tool_calls error and add missing tool_choice info - thanks to [@Jbrito6492](https://github.com/Jbrito6492)
+
 ## [6.5.0] - 2024-03-31
 
 ### Added
@@ -67,13 +96,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [BREAKING] Switch from legacy Finetunes to the new Fine-tune-jobs endpoints. Implemented by [@lancecarlson](https://github.com/lancecarlson)
 - [BREAKING] Remove deprecated Completions endpoints - use Chat instead.
 
-### Fix
+### Fixed
 
 - [BREAKING] Fix issue where :stream parameters were replaced by a boolean in the client application. Thanks to [@martinjaimem](https://github.com/martinjaimem), [@vickymadrid03](https://github.com/vickymadrid03) and [@nicastelo](https://github.com/nicastelo) for spotting and fixing this issue.
 
 ## [5.2.0] - 2023-10-30
 
-### Fix
+### Fixed
 
 - 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

Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    ruby-openai (6.5.0)
+    ruby-openai (7.0.0)
       event_stream_parser (>= 0.3.0, < 2.0.0)
       faraday (>= 1)
       faraday-multipart (>= 1)

README.md

@@ -29,7 +29,6 @@ Stream text with GPT-4, transcribe and translate audio with Whisper, or create i
       - [Ollama](#ollama)
     - [Counting Tokens](#counting-tokens)
     - [Models](#models)
-      - [Examples](#examples)
     - [Chat](#chat)
       - [Streaming Chat](#streaming-chat)
       - [Vision](#vision)
@@ -258,24 +257,9 @@ There are different models that can be used to generate text. For a full list an
 
 ```ruby
 client.models.list
-client.models.retrieve(id: "text-ada-001")
+client.models.retrieve(id: "gpt-3.5-turbo")
 ```
 
-#### Examples
-
-- [GPT-4 (limited beta)](https://platform.openai.com/docs/models/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)
-  - gpt-3.5-turbo
-  - gpt-3.5-turbo-0301
-  - text-davinci-003
-- [GPT-3](https://platform.openai.com/docs/models/gpt-3)
-  - text-ada-001
-  - text-babbage-001
-  - text-curie-001
-
 ### Chat
 
 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):
@@ -387,7 +371,7 @@ You can stream it as well!
 
 ### 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, see the example below. Note that tool_choice is optional, but if you exclude it, the model will choose whether to use the function or not ([see this for more details](https://github.com/openai/openai-cookbook/blob/main/examples/How_to_call_functions_with_chat_models.ipynb)).
+You can describe and pass in functions and the model will intelligently choose to output a JSON object containing arguments to call them - eg., to use your method `get_current_weather` to get the weather in a given location. Note that tool_choice is optional, but if you exclude it, the model will choose whether to use the function or not ([see here](https://platform.openai.com/docs/api-reference/chat/create#chat-create-tool_choice)).
 
 ```ruby
 
@@ -398,7 +382,7 @@ end
 response =
   client.chat(
     parameters: {
-      model: "gpt-3.5-turbo-0613",
+      model: "gpt-3.5-turbo",
       messages: [
         {
           "role": "user",
@@ -462,30 +446,14 @@ Hit the OpenAI API for a completion using other GPT-3 models:
 ```ruby
 response = client.completions(
     parameters: {
-        model: "text-davinci-001",
+        model: "gpt-3.5-turbo",
         prompt: "Once upon a time",
         max_tokens: 5
     })
 puts response["choices"].map { |c| c["text"] }
 # => [", there lived a great"]
 ```
 
-### Edits
-
-Send a string and some instructions for what to do to the string:
-
-```ruby
-response = client.edits(
-    parameters: {
-        model: "text-davinci-edit-001",
-        input: "What day of the wek is it?",
-        instruction: "Fix the spelling mistakes"
-    }
-)
-puts response.dig("choices", 0, "text")
-# => What day of the week is it?
-```
-
 ### Embeddings
 
 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.
@@ -624,7 +592,7 @@ You can then use this file ID to create a fine tuning job:
 response = client.finetunes.create(
     parameters: {
     training_file: file_id,
-    model: "gpt-3.5-turbo-0613"
+    model: "gpt-3.5-turbo"
 })
 fine_tune_id = response["id"]
 ```
@@ -1030,7 +998,7 @@ HTTP errors can be caught like this:
 
 ```
   begin
-    OpenAI::Client.new.models.retrieve(id: "text-ada-001")
+    OpenAI::Client.new.models.retrieve(id: "gpt-3.5-turbo")
   rescue Faraday::Error => e
     raise "Got a Faraday error: #{e}"
   end

lib/openai/client.rb

@@ -30,10 +30,6 @@ def chat(parameters: {})
       json_post(path: "/chat/completions", parameters: parameters)
     end
 
-    def edits(parameters: {})
-      json_post(path: "/edits", parameters: parameters)
-    end
-
     def embeddings(parameters: {})
       json_post(path: "/embeddings", parameters: parameters)
     end

lib/openai/version.rb

@@ -1,3 +1,3 @@
 module OpenAI
-  VERSION = "6.5.0".freeze
+  VERSION = "7.0.0".freeze
 end