llm.rb 0.9.0 → 0.10.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: eb2885c3c77d0ac7555b59fd57ccbf15ed5c72e2b385f5f4d83f8ea906b34171
-  data.tar.gz: 0cf0fa38bec61167de57441f11c389f13a1f86ea9dd04caf597698363fa53c71
+  metadata.gz: 15ddbff68b600d6a8926e872ed687edaff585ed075136415c8b8921438c5d32f
+  data.tar.gz: bf498f154df07de201f1529253559db03e850182afdf84eb6b99efb527920a2f
 SHA512:
-  metadata.gz: 280bccde2d4d730485845440986b27ce7b753cdde7f080bc3c7e2f1381a3e924fa1aebe48fe734d9d6d58c5d0d5ff7e182a5d7bba5b3e390c79c4c2738bbd8c2
-  data.tar.gz: dba89769f1fe6f35ac98e7ad6fce9e90775e8b61e47ee3215e8fb8df555d9787f9d289206bd3cdc60b3b1bdee4a5217e8e69b1d3aa33f29e0e193ba90f0e33f8
+  metadata.gz: 6256cf08682c5f9bf5aff9a6065aec57e23e8f68bc54acd302eee4f6c08628feddf438043e58898611be6ffa0d61c07f437da3c6cd16007d256c6fd4adee4218
+  data.tar.gz: a7c0510691a9aa08447dc65146a763a37ca1aefb59de9ee10c2eca691d725a971d9dcdc35dc1316ff473b3ff002ef1b5c2963601a8044ec70b2c2302132e4627

data/README.md

@@ -1,17 +1,16 @@
 ## About
 
 llm.rb is a zero-dependency Ruby toolkit for Large Language Models that
-includes OpenAI, Gemini, Anthropic, DeepSeek, Ollama, and LlamaCpp.
-It's fast, simple and composable – with full support for chat,
-streaming, tool calling, audio, images, files, and JSON Schema
-generation.
+includes OpenAI, Gemini, Anthropic, DeepSeek, Ollama, and LlamaCpp. The
+toolkit includes full support for chat, streaming, tool calling, audio,
+images, files, and JSON Schema generation.
 
 ## Features
 
 #### General
 - ✅ A single unified interface for multiple providers
 - 📦 Zero dependencies outside Ruby's standard library
-- 🚀 Optimized for performance and low memory usage
+- 🚀 Efficient API design that minimizes the request count
 
 #### Chat, Agents
 - 🧠 Stateless and stateful chat via completions and responses API
@@ -31,6 +30,12 @@ generation.
 
 ## Demos
 
+> The
+> [llmrb/llm-shell](https://github.com/llmrb/llm-shell)
+> project is built with llm.rb and its demos have been
+> included to provide a better idea of what llm.rb
+> is capable of.
+
 <details>
   <summary><b>1. Tools: "system" function</b></summary>
   <img src="https://github.com/llmrb/llm/raw/main/share/llm-shell/examples/toolcalls.gif">
@@ -115,13 +120,13 @@ msgs.each { print "[#{_1.role}] ", _1.content, "\n" }
 > There Is More Than One Way To Do It (TIMTOWTDI) when you are
 > using llm.rb &ndash; and this is especially true when it
 > comes to streaming. See the streaming documentation in
-> [docs/](docs/STREAMING.md#flexibility) for more details.
+> [docs/](docs/STREAMING.md#scopes) for more details.
 
 The following example streams the messages in a conversation
 as they are generated in real-time. This feature can be useful
-in case you want to see the contents of a message as it is
-generated, or in case you want to avoid potential read timeouts
-during the generation of a response.
+when you want to stream a conversation in real time, or when you
+want to avoid potential read timeouts during the generation of a
+response.
 
 The `stream` option can be set to an IO object, or the value `true`
 to enable streaming &ndash; and at the end of the request, `bot.chat`
@@ -497,22 +502,10 @@ else there's the API reference. It covers classes and methods that the README gl
 over or doesn't cover at all. The API reference is available at
 [0x1eef.github.io/x/llm.rb](https://0x1eef.github.io/x/llm.rb).
 
-
 ### Guides
 
 The [docs/](docs/) directory contains some additional documentation that
-didn't quite make it into the README. It covers the design guidelines that
-the library follows, some strategies for memory management, and other
-provider-specific features.
-
-## See also
-
-**[llmrb/llm-shell](https://github.com/llmrb/llm-shell)**
-
-An extensible, developer-oriented command line utility that is powered by
-llm.rb and serves as a demonstration of the library's capabilities. The
-[demo](https://github.com/llmrb/llm-shell#demos) section has a number of GIF
-previews might be especially interesting.
+didn't quite make it into the README.
 
 ## Install
 

data/lib/llm/bot/conversable.rb

@@ -25,7 +25,5 @@ class LLM::Bot
       role = params.delete(:role)
       @messages.push [LLM::Message.new(role, prompt), @params.merge(params), :complete]
     end
-
-    include LLM
   end
 end

data/lib/llm/buffer.rb

@@ -2,7 +2,6 @@
 
 module LLM
   ##
-  # @private
   # {LLM::Buffer LLM::Buffer} provides an Enumerable object that
   # yields each message in a conversation on-demand, and only sends
   # a request to the LLM when a response is needed.
@@ -23,9 +22,13 @@ module LLM
     #  Yields each message in the conversation thread
     # @raise (see LLM::Provider#complete)
     # @return [void]
-    def each
-      empty! unless @pending.empty?
-      @completed.each { yield(_1) }
+    def each(...)
+      if block_given?
+        empty! unless @pending.empty?
+        @completed.each { yield(_1) }
+      else
+        enum_for(:each, ...)
+      end
     end
 
     ##
@@ -54,6 +57,15 @@ module LLM
     end
     alias_method :push, :<<
 
+    ##
+    # @param [Integer, #to_i] index
+    #  The message index
+    # @return [LLM::Message, nil]
+    #  Returns a message, or nil
+    def [](index)
+      @completed[index.to_i] || to_a[index.to_i]
+    end
+
     ##
     # @return [String]
     def inspect

data/lib/llm/providers/anthropic.rb

@@ -76,10 +76,10 @@ module LLM
 
     ##
     # Returns the default model for chat completions
-    # @see https://docs.anthropic.com/en/docs/about-claude/models/all-models#model-comparison-table claude-3-5-sonnet-20240620
+    # @see https://docs.anthropic.com/en/docs/about-claude/models/all-models#model-comparison-table claude-sonnet-4-20250514
     # @return [String]
     def default_model
-      "claude-3-5-sonnet-20240620"
+      "claude-sonnet-4-20250514"
     end
 
     private

data/lib/llm/providers/gemini/images.rb

@@ -43,7 +43,7 @@ class LLM::Gemini
     def create(prompt:, model: "gemini-2.0-flash-exp-image-generation", **params)
       req  = Net::HTTP::Post.new("/v1beta/models/#{model}:generateContent?key=#{key}", headers)
       body = JSON.dump({
-        contents: [{parts: {text: prompt}}],
+        contents: [{parts: [{text: create_prompt}, {text: prompt}]}],
         generationConfig: {responseModalities: ["TEXT", "IMAGE"]}
       }.merge!(params))
       req.body = body
@@ -93,6 +93,15 @@ class LLM::Gemini
       @provider.instance_variable_get(:@key)
     end
 
+    def create_prompt
+      <<~PROMPT
+        Your task is to generate one or more image(s) from
+        text I will provide to you. Your response *MUST* include
+        at least one image, and your response *MUST NOT* include
+        any text or other content.
+      PROMPT
+    end
+
     [:response_parser, :headers, :execute, :set_body_stream].each do |m|
       define_method(m) { |*args, **kwargs, &b| @provider.send(m, *args, **kwargs, &b) }
     end

data/lib/llm/providers/gemini.rb

@@ -126,10 +126,10 @@ module LLM
 
     ##
     # Returns the default model for chat completions
-    # @see https://ai.google.dev/gemini-api/docs/models#gemini-1.5-flash gemini-1.5-flash
+    # @see https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash gemini-2.5-flash
     # @return [String]
     def default_model
-      "gemini-1.5-flash"
+      "gemini-2.5-flash"
     end
 
     private

data/lib/llm/providers/openai.rb

@@ -121,10 +121,10 @@ module LLM
 
     ##
     # Returns the default model for chat completions
-    # @see https://platform.openai.com/docs/models/gpt-4o-mini gpt-4o-mini
+    # @see https://platform.openai.com/docs/models/gpt-4.1 gpt-4.1
     # @return [String]
     def default_model
-      "gpt-4o-mini"
+      "gpt-4.1"
     end
 
     private

data/lib/llm/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module LLM
-  VERSION = "0.9.0"
+  VERSION = "0.10.0"
 end

data/llm.gemspec

@@ -8,11 +8,13 @@ Gem::Specification.new do |spec|
   spec.authors = ["Antar Azri", "0x1eef"]
   spec.email = ["azantar@proton.me", "0x1eef@proton.me"]
 
-  spec.summary = "llm.rb is a zero-dependency Ruby toolkit for " \
-                 "Large Language Models that includes OpenAI, Gemini, " \
-                 "Anthropic, DeepSeek, Ollama, and LlamaCpp. It’s fast, simple " \
-                 "and composable – with full support for chat, streaming, tool calling, audio, " \
-                 "images, files, and JSON Schema generation."
+  spec.summary = <<~SUMMARY
+  llm.rb is a zero-dependency Ruby toolkit for Large Language Models that
+  includes OpenAI, Gemini, Anthropic, DeepSeek, Ollama, and LlamaCpp. The
+  toolkit includes full support for chat, streaming, tool calling, audio,
+  images, files, and JSON Schema generation.
+  SUMMARY
+
   spec.description = spec.summary
   spec.homepage = "https://github.com/llmrb/llm"
   spec.license = "0BSDL"

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: llm.rb
 version: !ruby/object:Gem::Version
-  version: 0.9.0
+  version: 0.10.0
 platform: ruby
 authors:
 - Antar Azri
@@ -151,9 +151,9 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '2.8'
 description: llm.rb is a zero-dependency Ruby toolkit for Large Language Models that
-  includes OpenAI, Gemini, Anthropic, DeepSeek, Ollama, and LlamaCpp. It’s fast, simple
-  and composable – with full support for chat, streaming, tool calling, audio, images,
-  files, and JSON Schema generation.
+  includes OpenAI, Gemini, Anthropic, DeepSeek, Ollama, and LlamaCpp. The toolkit
+  includes full support for chat, streaming, tool calling, audio, images, files, and
+  JSON Schema generation.
 email:
 - azantar@proton.me
 - 0x1eef@proton.me
@@ -282,10 +282,10 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.6.8
+rubygems_version: 3.7.1
 specification_version: 4
 summary: llm.rb is a zero-dependency Ruby toolkit for Large Language Models that includes
-  OpenAI, Gemini, Anthropic, DeepSeek, Ollama, and LlamaCpp. It’s fast, simple and
-  composable – with full support for chat, streaming, tool calling, audio, images,
-  files, and JSON Schema generation.
+  OpenAI, Gemini, Anthropic, DeepSeek, Ollama, and LlamaCpp. The toolkit includes
+  full support for chat, streaming, tool calling, audio, images, files, and JSON Schema
+  generation.
 test_files: []