raix 0.7 → 0.7.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f6783ed9671864edec5d734f8003822accee2dd7b89d0453a2c6973d35ecf2bf
-  data.tar.gz: 90eac19ba012daaeed4ce898a2be3476d1dac9c6df2cbb66fbe88a5620b971c6
+  metadata.gz: 5f8ebb64b9a241bce3f7865030ecdf00f5d640df62b754e5d2cbde4768502d3b
+  data.tar.gz: ce540f67cda77e6697c2387a3fbc399da5559e0bf7a6e51e9db5eb0e50671d74
 SHA512:
-  metadata.gz: 6753d494dd65e960373308189d7324e973c347f627ed82463b9ae3d7079446a87b7e012949c5a69adf734a1e9f37e8684b51a04f3a7b39b6b9772b501908949a
-  data.tar.gz: 07f8d142ca423979013c17da2f8758a7113fc583fc2ee47b10cf64072a7be12aa7b53447821340239033866e8c108b1bea76ffc202fcd24e02cf814607df5989
+  metadata.gz: f62b2bc73bbb7a4ed5d45a1b59a6ae1de7ff75a2e2b078bd4918f8c6af7eb5b80bbe77052f916d5709158802a241cd6dd074fa4ebcc79e2596ae837c7dc7889e
+  data.tar.gz: d3805d4059eba9ad536ae34fa0132a6eb0b608cc92c4d32c5fcf6840cabb5f58b85954f64ef3852459c63159b963a5e6e75e3c94d99eaf84da2046430478a11f

data/CHANGELOG.md

@@ -16,7 +16,6 @@
 - adds support for `execute_ai_request` in `PromptDeclarations` to handle API calls
 - adds support for `chat_completion_from_superclass` in `PromptDeclarations` to handle superclass calls
 - adds support for `model`, `temperature`, and `max_tokens` in `PromptDeclarations` to access prompt parameters
-- fixes function return values in `FunctionDispatch` to properly return results from tool calls (thanks @ttilberg)
 - Make automatic JSON parsing available to non-OpenAI providers that don't support the response_format parameter by scanning for json XML tags
 
 ## [0.6.0] - 2024-11-12

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    raix (0.7)
+    raix (0.7.2)
       activesupport (>= 6.0)
       open_router (~> 0.2)
       ruby-openai (~> 7.0)

data/README.md

@@ -4,7 +4,7 @@
 
 Raix (pronounced "ray" because the x is silent) is a library that gives you everything you need to add discrete large-language model (LLM) AI components to your Ruby applications. Raix consists of proven code that has been extracted from [Olympia](https://olympia.chat), the world's leading virtual AI team platform, and probably one of the biggest and most successful AI chat projects written completely in Ruby.
 
-Understanding the how to use discrete AI components in otherwise normal code is key to productively leveraging Raix, and the subject of a book written by Raix's author Obie Fernandez, titled [Patterns of Application Development Using AI](https://leanpub.com/patterns-of-application-development-using-ai). You can easily support the ongoing development of this project by buying the book at Leanpub.
+Understanding how to use discrete AI components in otherwise normal code is key to productively leveraging Raix, and the subject of a book written by Raix's author Obie Fernandez, titled [Patterns of Application Development Using AI](https://leanpub.com/patterns-of-application-development-using-ai). You can easily support the ongoing development of this project by buying the book at Leanpub.
 
 At the moment, Raix natively supports use of either OpenAI or OpenRouter as its underlying AI provider. Eventually you will be able to specify your AI provider via an adapter, kind of like ActiveRecord maps to databases. Note that you can also use Raix to add AI capabilities to non-Rails applications as long as you include ActiveSupport as a dependency. Extracting the base code to its own standalone library without Rails dependencies is on the roadmap, but not a high priority.
 
@@ -23,6 +23,7 @@ end
 
 => "The question of the meaning of life is one of the most profound and enduring inquiries in philosophy, religion, and science.
     Different perspectives offer various answers..."
+```
 
 By default, Raix will automatically add the AI's response to the transcript. This behavior can be controlled with the `save_response` parameter, which defaults to `true`. You may want to set it to `false` when making multiple chat completion calls during the lifecycle of a single object (whether sequentially or in parallel) and want to manage the transcript updates yourself:
 
@@ -32,7 +33,7 @@ By default, Raix will automatically add the AI's response to the transcript. Thi
 
 #### Transcript Format
 
-The transcript accepts both abbreviated and standard OpenAI message hash formats. The abbreviated format, suitable for system, assistant, and user messages is simply a mapping of `role => content`, as show in the example above.
+The transcript accepts both abbreviated and standard OpenAI message hash formats. The abbreviated format, suitable for system, assistant, and user messages is simply a mapping of `role => content`, as shown in the example above.
 
 ```ruby
 transcript << { user: "What is the meaning of life?" }
@@ -56,7 +57,7 @@ Raix supports [Predicted Outputs](https://platform.openai.com/docs/guides/latenc
 
 ### Prompt Caching
 
-Raix supports [Anthropic-style prompt caching](https://openrouter.ai/docs/prompt-caching#anthropic-claude) when using Anthropic's Claud family of models. You can specify a `cache_at` parameter when doing a chat completion. If the character count for the content of a particular message is longer than the cache_at parameter, it will be sent to Anthropic as a multipart message with a cache control "breakpoint" set to "ephemeral".
+Raix supports [Anthropic-style prompt caching](https://openrouter.ai/docs/prompt-caching#anthropic-claude) when using Anthropic's Claude family of models. You can specify a `cache_at` parameter when doing a chat completion. If the character count for the content of a particular message is longer than the cache_at parameter, it will be sent to Anthropic as a multipart message with a cache control "breakpoint" set to "ephemeral".
 
 Note that there is a limit of four breakpoints, and the cache will expire within five minutes. Therefore, it is recommended to reserve the cache breakpoints for large bodies of text, such as character cards, CSV data, RAG data, book chapters, etc. Raix does not enforce a limit on the number of breakpoints, which means that you might get an error if you try to cache too many messages.
 
@@ -78,6 +79,26 @@ Note that there is a limit of four breakpoints, and the cache will expire within
     },
 ```
 
+### JSON Mode
+
+Raix supports JSON mode for chat completions, which ensures that the AI model's response is valid JSON. This is particularly useful when you need structured data from the model.
+
+When using JSON mode with OpenAI models, Raix will automatically set the `response_format` parameter on requests accordingly, and attempt to parse the entire response body as JSON.
+When using JSON mode with other models (e.g. Anthropic) that don't support `response_format`, Raix will look for JSON content inside of &lt;json&gt; XML tags in the response, before
+falling back to parsing the entire response body. Make sure you tell the AI to reply with JSON inside of XML tags.
+
+```ruby
+>> my_class.chat_completion(json: true)
+=> { "key": "value" }
+```
+
+When using JSON mode with non-OpenAI providers, Raix automatically sets the `require_parameters` flag to ensure proper JSON formatting. You can also combine JSON mode with other parameters:
+
+```ruby
+>> my_class.chat_completion(json: true, openai: "gpt-4o")
+=> { "key": "value" }
+```
+
 ### Use of Tools/Functions
 
 The second (optional) module that you can add to your Ruby classes after `ChatCompletion` is `FunctionDispatch`. It lets you declare and implement functions to be called at the AI's discretion as part of a chat completion "loop" in a declarative, Rails-like "DSL" fashion.
@@ -109,44 +130,39 @@ Note that for security reasons, dispatching functions only works with functions
 
 #### Multiple Tool Calls
 
-Some AI models (like GPT-4) can make multiple tool calls in a single response. When this happens, Raix will automatically handle all the function calls sequentially and return an array of their results. Here's an example:
+Some AI models (like GPT-4) can make multiple tool calls in a single response. When this happens, Raix will automatically handle all the function calls sequentially.
+If you need to capture the arguments to the function calls, do so in the block passed to `function`. The response from `chat_completion` is always the final text
+response from the assistant, and is not affected by function calls.
 
 ```ruby
 class MultipleToolExample
   include Raix::ChatCompletion
   include Raix::FunctionDispatch
 
+  attr_reader :invocations
+
   function :first_tool do |arguments|
+    @invocations << :first
     "Result from first tool"
   end
 
   function :second_tool do |arguments|
+    @invocations << :second
     "Result from second tool"
   end
+
+  def initialize
+    @invocations = []
+  end
 end
 
 example = MultipleToolExample.new
 example.transcript << { user: "Please use both tools" }
-results = example.chat_completion(openai: "gpt-4o")
-# => ["Result from first tool", "Result from second tool"]
-```
-
-Note that as of version 0.6.1, function return values are properly returned from tool calls, whether in single or multiple tool call scenarios. This means you can use the return values from your functions in your application logic.
-
-```ruby
-class DiceRoller
-  include Raix::ChatCompletion
-  include Raix::FunctionDispatch
-
-  function :roll_dice, "Roll a die with specified number of faces", faces: { type: :integer } do |arguments|
-    rand(1..arguments[:faces])
-  end
-end
+example.chat_completion(openai: "gpt-4o")
+# => "I used both tools, as requested"
 
-roller = DiceRoller.new
-roller.transcript << { user: "Roll a d20 twice" }
-results = roller.chat_completion(openai: "gpt-4o")
-# => [15, 7] # Actual random dice roll results
+example.invocations
+# => [:first, :second]
 ```
 
 #### Manually Stopping a Loop
@@ -224,7 +240,7 @@ class PromptSubscriber
 
   attr_accessor :conversation, :bot_message, :user_message
 
-  # many other declarations ommitted...
+  # many other declarations omitted...
 
   prompt call: FetchUrlCheck
 
@@ -548,13 +564,13 @@ You will also need to configure the OpenRouter API access token as per the instr
 
 After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
 
-Specs require `OR_ACCESS_TOKEN` and `OAI_ACCESS_TOKEN` environment variables, for access to OpenRouter and OpenAI, respectively. You can add those keys to a local unversionsed `.env` file and they will be picked up by the `dotenv` gem.
+Specs require `OR_ACCESS_TOKEN` and `OAI_ACCESS_TOKEN` environment variables, for access to OpenRouter and OpenAI, respectively. You can add those keys to a local unversioned `.env` file and they will be picked up by the `dotenv` gem.
 
 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 the created tag, and push the `.gem` file to [rubygems.org](https://rubygems.org).
 
 ## Contributing
 
-Bug reports and pull requests are welcome on GitHub at https://github.com/[OlympiaAI]/raix. 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/[OlympiaAI]/raix/blob/main/CODE_OF_CONDUCT.md).
+Bug reports and pull requests are welcome on GitHub at https://github.com/OlympiaAI/raix. 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/OlympiaAI/raix/blob/main/CODE_OF_CONDUCT.md).
 
 ## License
 
@@ -562,4 +578,4 @@ The gem is available as open source under the terms of the [MIT License](https:/
 
 ## Code of Conduct
 
-Everyone interacting in the Raix project's codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/[OlympiaAI]/raix/blob/main/CODE_OF_CONDUCT.md).
+Everyone interacting in the Raix project's codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/OlympiaAI/raix/blob/main/CODE_OF_CONDUCT.md).

data/lib/raix/chat_completion.rb

@@ -43,8 +43,9 @@ module Raix
     # @option params [Boolean] :json (false) Whether to return the parse the response as a JSON object. Will search for <json> tags in the response first, then fall back to the default JSON parsing of the entire response.
     # @option params [Boolean] :openai (false) Whether to use OpenAI's API instead of OpenRouter's.
     # @option params [Boolean] :raw (false) Whether to return the raw response or dig the text content.
+    # @option params [Array] :messages (nil) An array of messages to use instead of the transcript.
     # @return [String|Hash] The completed chat response.
-    def chat_completion(params: {}, loop: false, json: false, raw: false, openai: false, save_response: true)
+    def chat_completion(params: {}, loop: false, json: false, raw: false, openai: false, save_response: true, messages: nil)
       # set params to default values if not provided
       params[:cache_at] ||= cache_at.presence
       params[:frequency_penalty] ||= frequency_penalty.presence
@@ -68,13 +69,17 @@ module Raix
       params[:top_logprobs] ||= top_logprobs.presence
       params[:top_p] ||= top_p.presence
 
+      json = true if params[:response_format].is_a?(Raix::ResponseFormat)
+
       if json
         unless openai
           params[:provider] ||= {}
           params[:provider][:require_parameters] = true
         end
-        params[:response_format] ||= {}
-        params[:response_format][:type] = "json_object"
+        if params[:response_format].blank?
+          params[:response_format] ||= {}
+          params[:response_format][:type] = "json_object"
+        end
       end
 
       # used by FunctionDispatch
@@ -87,7 +92,9 @@ module Raix
 
       # duplicate the transcript to avoid race conditions in situations where
       # chat_completion is called multiple times in parallel
-      messages = transcript.flatten.compact.map { |msg| adapter.transform(msg) }.dup
+      # TODO: Defensive programming, ensure messages is an array
+      messages ||= transcript.flatten.compact
+      messages = messages.map { |msg| adapter.transform(msg) }.dup
       raise "Can't complete an empty transcript" if messages.blank?
 
       begin

data/lib/raix/function_dispatch.rb

@@ -70,7 +70,7 @@ module Raix
               }
             ]
           }
-          result = instance_exec(arguments, &block).tap do |content|
+          instance_exec(arguments, &block).tap do |content|
             transcript << {
               role: "tool",
               tool_call_id: id,
@@ -81,10 +81,6 @@ module Raix
           end
 
           chat_completion(**chat_completion_args) if loop
-
-          # Return the result of the function call in case that's what the caller wants
-          # https://github.com/OlympiaAI/raix/issues/16
-          result
         end
       end
     end

data/lib/raix/response_format.rb

@@ -50,16 +50,20 @@ module Raix
       {}.tap do |response|
         case input
         when Array
-          properties = {}
-          input.each { |item| properties.merge!(decode(item)) }
-
           response[:type] = "array"
-          response[:items] = {
-            type: "object",
-            properties:,
-            required: properties.keys.select { |key| properties[key].delete(:required) },
-            additionalProperties: false
-          }
+
+          if input.size == 1 && input.first.is_a?(String)
+            response[:items] = { type: input.first }
+          else
+            properties = {}
+            input.each { |item| properties.merge!(decode(item)) }
+            response[:items] = {
+              type: "object",
+              properties:,
+              required: properties.keys.select { |key| properties[key].delete(:required) },
+              additionalProperties: false
+            }
+          end
         when Hash
           input.each do |key, value|
             response[key] = if value.is_a?(Hash) && value.key?(:type)

data/lib/raix/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Raix
-  VERSION = "0.7"
+  VERSION = "0.7.2"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: raix
 version: !ruby/object:Gem::Version
-  version: '0.7'
+  version: 0.7.2
 platform: ruby
 authors:
 - Obie Fernandez
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2025-04-13 00:00:00.000000000 Z
+date: 2025-04-18 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activesupport