omniai 2.7.0 → 2.8.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 488be723c0a59ca0095eb3a1f64081cceff14ae982208e598da5058ee0ea0c4b
-  data.tar.gz: 47805f82344429912eaa2e0f00299cc95868d35d04a6d424f698b719bf9d0fe8
+  metadata.gz: a9cab46e52805a61d08bf4638ef7ed9ab46549c016ada8740abb7471f3ee5d07
+  data.tar.gz: 3a34ea68b515d8759a76d689f2474648c7e55d51b42a93ee022c18df271e049e
 SHA512:
-  metadata.gz: 1c0d66e74c7a0e1eb0296e371b0339d44cedbb7a747c2beeb7cb0547303140d0a6550fd8d7fc6629c09804c57cfcf780dec38f01f6c8aac49004ab28e9968872
-  data.tar.gz: aeb129f452a6ea0a9c2e33a25afbe5f8be1e7b27445fb58399556e7bdd0475b0840b36465c6b33edbdf857c6d943c10824b0cc21b7e6a917d161829e4ca033a6
+  metadata.gz: b241dca1c95f27efd023c09cb6ed9e8193f94e2487490b376a816e5c50d8a6a42e6cb0bc54e47ec3aeba0b12f23de7b3a258d9ca29d222ce6bf414469e2ad777
+  data.tar.gz: b74ba2a9950c821b7ca6bd5d1348165daab7dea3b7372db702d40cdda8d2669c057b32913cf5713b6d75cf3d97a234acf25c1f11af3357cc465740b18ec5990e

data/README.md

@@ -228,24 +228,27 @@ puts format.parse(response.text)
 }
 ```
 
-### Example #7: [Chat w/ CLI](https://github.com/ksylvest/omniai/blob/main/examples/chat_with_cli)
+### Example #7: [CLI](https://github.com/ksylvest/omniai/blob/main/examples/cli)
 
 The `OmniAI` gem also ships with a CLI to simplify quick tests.
 
 ```bash
+# Chat
+
 omniai chat "Who designed the Ruby programming language?"
-```
+omniai chat --provider="google" --model="gemini-2.0-flash" "Who are you?"
 
-```
-The Ruby programming language was created by Yukihiro Matsumoto, often known as "Matz."
-```
+## Speech to Text
 
-```bash
-omniai chat --provider="google" --model="gemini-2.0-flash" "Who are you?"
-```
+omniai speak "Salley sells sea shells by the sea shore." > ./files/audio.wav
 
-```
-I am a large language model, trained by Google.
+# Text to Speech
+
+omniai transcribe "./files/audio.wav"
+
+# Embed
+
+omniai embed "What is the capital of France?"
 ```
 
 ### Example #8: [Text-to-Speech](https://github.com/ksylvest/omniai/blob/main/examples/text_to_speech)
@@ -650,6 +653,18 @@ The capital of Spain is **Madrid**.
 ...
 ```
 
+#### Text-to-Speech
+
+```bash
+omniai speak "Sally sells sea shells on the sea shore." > audio.aac
+```
+
+#### Speech-to-Text
+
+```bash
+omniai transcribe ./audio.aac
+```
+
 ### MCP
 
 [MCP](https://modelcontextprotocol.io/introduction) is an open protocol designed to standardize giving context to LLMs. The OmniAI implementation supports building an MCP server that operates via the [stdio](https://modelcontextprotocol.io/docs/concepts/transports) transport.

data/lib/omniai/cli/base_handler.rb

@@ -31,7 +31,7 @@ module OmniAI
 
       # @return [OmniAI::Client]
       def client
-        @client ||= OmniAI::Client.find(provider: @provider)
+        @client ||= OmniAI.client(provider: @provider)
       end
     end
   end

data/lib/omniai/cli/speak_handler.rb

@@ -0,0 +1,59 @@
+# frozen_string_literal: true
+
+module OmniAI
+  class CLI
+    # Used by CLI to process commands like:
+    #
+    #    omniai speak "Sally sells seashells by the seashore." > ./audio.aac
+    class SpeakHandler < BaseHandler
+      # @param argv [Array<String>]
+      def handle!(argv:)
+        parser.parse!(argv)
+
+        speak(argv.join(" "))
+      end
+
+    private
+
+      # @param input [String]
+      def speak(input)
+        client.speak(input, **@args) do |chunk|
+          @stdout.write(chunk)
+        end
+        @stdout.flush
+      end
+
+      # @return [OptionParser]
+      def parser
+        OptionParser.new do |options|
+          options.banner = 'usage: omniai speak [options] "<prompt>"'
+
+          options.on("-h", "--help", "help") do
+            @stdout.puts(options)
+            exit
+          end
+
+          options.on("-p", "--provider=PROVIDER", "provider") do |provider|
+            @provider = provider
+          end
+
+          options.on("-m", "--model=MODEL", "model") do |model|
+            @args[:model] = model
+          end
+
+          options.on("-v", "--voice=VOICE", "voice") do |voice|
+            @args[:voice] = voice
+          end
+
+          options.on("-s", "--speed=SPEED", Float, "speed") do |speed|
+            @args[:speed] = speed
+          end
+
+          options.on("-f", "--format=FORMAT", "format") do |format|
+            @args[:format] = format
+          end
+        end
+      end
+    end
+  end
+end

data/lib/omniai/cli/transcribe_handler.rb

@@ -0,0 +1,56 @@
+# frozen_string_literal: true
+
+module OmniAI
+  class CLI
+    # Used by CLI to process commands like:
+    #
+    #    omniai transcribe ./audio.wav
+    class TranscribeHandler < BaseHandler
+      # @param argv [Array<String>]
+      def handle!(argv:)
+        parser.parse!(argv)
+
+        argv.each do |path|
+          transcribe(path)
+        end
+      end
+
+    private
+
+      # @param input [String]
+      def transcribe(input)
+        File.open(input, "rb") do |file|
+          @stdout.puts(client.transcribe(file, **@args).text)
+        end
+      end
+
+      # @return [OptionParser]
+      def parser
+        OptionParser.new do |options|
+          options.banner = 'usage: omniai chat [options] "<prompt>"'
+
+          options.on("-h", "--help", "help") do
+            @stdout.puts(options)
+            exit
+          end
+
+          options.on("-p", "--provider=PROVIDER", "provider") do |provider|
+            @provider = provider
+          end
+
+          options.on("-m", "--model=MODEL", "model") do |model|
+            @args[:model] = model
+          end
+
+          options.on("-l", "--language=LANGUAGE", "language") do |language|
+            @args[:language] = language
+          end
+
+          options.on("-f", "--format=FORMAT", "format") do |format|
+            @args[:format] = format
+          end
+        end
+      end
+    end
+  end
+end

data/lib/omniai/cli.rb

@@ -13,7 +13,7 @@ module OmniAI
     # @param stdin [IO] a stream
     # @param stdout [IO] a stream
     # @param provider [String] a provider
-    def initialize(stdin: $stdin, stdout: $stdout, provider: "openai")
+    def initialize(stdin: $stdin, stdout: $stdout, provider: nil)
       @stdin = stdin
       @stdout = stdout
       @provider = provider
@@ -30,6 +30,8 @@ module OmniAI
         case command
         when "chat" then ChatHandler
         when "embed" then EmbedHandler
+        when "speak" then SpeakHandler
+        when "transcribe" then TranscribeHandler
         else raise Error, "unsupported command=#{command.inspect}"
         end
 
@@ -60,6 +62,9 @@ module OmniAI
         options.separator <<~COMMANDS
           commands:
             chat
+            embed
+            speak
+            transcribe
         COMMANDS
       end
     end

data/lib/omniai/speak.rb

@@ -23,7 +23,11 @@ module OmniAI
   #     end
   #   end
   #
-  #   client.transcribe(File.open("..."), model: "...", format: :json)
+  #   File.open('audio.wav', 'wb') do |file|
+  #     client.speak('Sally sells seashells by the seashore.', format: OmniAI::Speak::Format::WAV) do |chunk|
+  #       file << chunk
+  #     end
+  #   end
   class Speak
     module Format
       AAC = "aac"
@@ -34,6 +38,8 @@ module OmniAI
       WAV = "wav"
     end
 
+    DEFAULT_FORMAT = Format::AAC
+
     # @raise [HTTPError]
     #
     # @param client [OmniAI::Client] required
@@ -52,7 +58,7 @@ module OmniAI
     # @yield [chunk]
     #
     # @return [Tempfile]
-    def self.process!(input, client:, model:, voice:, speed: nil, format: nil, &)
+    def self.process!(input, client:, model:, voice:, speed: nil, format: DEFAULT_FORMAT, &)
       new(input, client:, model:, voice:, speed:, format:).process!(&)
     end
 
@@ -68,7 +74,7 @@ module OmniAI
     #   - "opus"
     #   - "pcm"
     #   - "wav"
-    def initialize(input, client:, model:, voice:, speed: nil, format: nil)
+    def initialize(input, client:, model:, voice:, speed: nil, format: DEFAULT_FORMAT)
       @input = input
       @client = client
       @model = model

data/lib/omniai/transcribe.rb

@@ -23,7 +23,9 @@ module OmniAI
   #     end
   #   end
   #
-  #   client.transcribe(File.open("..."), model: "...", format: :json)
+  #   File.open('audio.wav', 'rb') do |file|
+  #     client.transcribe(file, model: "...", format: :json)
+  #   end
   class Transcribe
     module Language
       AFRIKAANS = "af"

data/lib/omniai/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module OmniAI
-  VERSION = "2.7.0"
+  VERSION = "2.8.0"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: omniai
 version: !ruby/object:Gem::Version
-  version: 2.7.0
+  version: 2.8.0
 platform: ruby
 authors:
 - Kevin Sylvestre
@@ -103,6 +103,8 @@ files:
 - lib/omniai/cli/base_handler.rb
 - lib/omniai/cli/chat_handler.rb
 - lib/omniai/cli/embed_handler.rb
+- lib/omniai/cli/speak_handler.rb
+- lib/omniai/cli/transcribe_handler.rb
 - lib/omniai/client.rb
 - lib/omniai/config.rb
 - lib/omniai/context.rb