aia 0.5.12 → 0.5.14

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 8fa0d67e36209d8ac1840c94820ce58e0b6c08a6b01e47e579dfe90f04b94420
-  data.tar.gz: 382d34ab554077b0e81d3a724362b41463e5ccc88f888dbba00b1ad65ff0c528
+  metadata.gz: 9a4bc8019b9ad41da7d884ad4d86b3489afd2487b8ce7be78dd10ca8e963f454
+  data.tar.gz: d374c91f50ea29bb1dd0d9fab5c924ab7741676c45cf75de6999f3f965c1d8a1
 SHA512:
-  metadata.gz: 109f27eb85889450bd19bb78a123d02ba789bd99708cf7be20528a8da8c090a7ef68655e60f7fda31a0da12a506a38f3fcdf8c9d2b4a2ea9096006ab81c5d494
-  data.tar.gz: 4b46125f0937d74ea4fe446c343b474f7c3b7d0443def5fea9782a5eea9a7c7bf4997e866871723dc2e4fe2d4fd9db07fe7384f9a95655891efbbfac5711a40f
+  metadata.gz: 4a2a194377c2b871a13e951a423bd1cede4b06be631ba0a3986cd8b3bddb80bb3cdd0c831207df08da7cabbdcb697d290bef6c083c54054d550c942909dbdd16
+  data.tar.gz: 79921b2f9899a2a86a86a18ae4cf2d9fe988a94e2bb70ae4dcd1998c3f721661b9a4587f4585219666b2d942d6ef500015fe9f4cfd60cae3982cb143b62bc366

data/.semver

@@ -1,6 +1,6 @@
 ---
 :major: 0
 :minor: 5
-:patch: 12
+:patch: 14
 :special: ''
 :metadata: ''

data/CHANGELOG.md

@@ -1,5 +1,13 @@
 ## [Unreleased]
 
+## [0.5.14] 2024-03-09
+- Directly access OpenAI to do text to speech when using the `--speak` option
+- Added --voice to specify which voice to use
+- Added --speech_model to specify which TTS model to use
+
+## [0.5.13] 2024-03-03
+- Added CLI-utility `llm` as a backend processor
+
 ## [0.5.12] 2024-02-24
 - Happy Birthday Ruby!
 - Added --next CLI option

data/README.md

@@ -6,16 +6,15 @@ It leverages the `prompt_manager` gem to manage prompts for the `mods` and `sgpt
 
 **Most Recent Change**: Refer to the [Changelog](CHANGELOG.md)
 
-> v0.5.12
-> - Supports Prompt Sequencing
-> - Added --next option
-> - Added --pipeline option
+> v0.5.14
+> - Directly access OpenAI to do text to speech when using the `--speak` option
+> - Added --voice to specify which voice to use
+> - Added --speech_model to specify which TTS model to use
 >
-> v0.5.11
-> - Allow directives to prepend content into the prompt text
-> - Added //include  path_to_file
-> - Added //shell    shell_command
-> - Added //ruby     ruby code
+> v0.5.13
+> - Added an initial integration for CLI-tool `llm` as a backend processor
+>   Its primary feature is its **ability to use local LLMs and APIs to keep all processing within your local workstation.**
+> 
 
 <!-- Tocer[start]: Auto-generated, don't remove. -->
 
@@ -48,6 +47,10 @@ It leverages the `prompt_manager` gem to manage prompts for the `mods` and `sgpt
     - [The --role Option](#the---role-option)
     - [Other Ways to Insert Roles into Prompts](#other-ways-to-insert-roles-into-prompts)
   - [External CLI Tools Used](#external-cli-tools-used)
+    - [Optional External CLI-tools](#optional-external-cli-tools)
+      - [Backend Processor `llm`](#backend-processor-llm)
+      - [Backend Processor `sgpt`](#backend-processor-sgpt)
+      - [Occassionally Useful Tool `plz`](#occassionally-useful-tool-plz)
   - [Shell Completion](#shell-completion)
   - [My Most Powerful Prompt](#my-most-powerful-prompt)
   - [My Configuration](#my-configuration)
@@ -103,9 +106,12 @@ The `aia` configuration defaults can be over-ridden by system environment variab
 | log_file      | ~/.prompts/_prompts.log | AIA_LOG_FILE |
 | markdown      | true          | AIA_MARKDOWN |
 | model         | gpt-4-1106-preview | AIA_MODEL |
-| out_file       | STDOUT        | AIA_OUT_FILE |
+| out_file      | STDOUT        | AIA_OUT_FILE |
 | prompts_dir   | ~/.prompts    | AIA_PROMPTS_DIR |
-| VERBOSE       | FALSE         | AIA_VERBOSE |
+| speech_model. | tts-1         | AIA_SPEECH_MODEL |
+| verbose       | FALSE         | AIA_VERBOSE |
+| voice         | alloy         | AIA_VOICE |
+
 
 
 See the `@options` hash in the `cli.rb` file for a complete list.  There are some config items that do not necessarily make sense for use as an envar over-ride.  For example if you set `export AIA_DUMP_FILE=config.yaml` then `aia` would dump the current configuration config.yaml and exit every time it is ran until you finally `unset AIA_DUMP_FILE`
@@ -431,7 +437,28 @@ system environment variable 'EDITOR' like this:
 
   export EDITOR="subl -w"
 
+### Optional External CLI-tools
+
+#### Backend Processor `llm`
+
+```
+llm  Access large language models from the command-line
+     |   brew install llm
+     |__ https://llm.datasette.io/
+```
+
+As of `aia v0.5.13` the `llm` backend processor is available in a limited integration.  It is a very powerful python-based implementation that has its own prompt templating system.  The reason that it is be included within the `aia` environment is for its ability to make use of local LLM models.
+
+
+#### Backend Processor `sgpt`
+
+`shell-gpt` aka `sgpt` is also a python implementation of a CLI-tool that processes prompts through OpenAI.  It has less features than both `mods` and `llm` and is less flexible.
+
+#### Occassionally Useful Tool `plz`
+
+`plz-cli` aka `plz` is not integrated with `aia` however, it gets an honorable mention for its ability to except a prompt that tailored to doing something on the command line.  Its response is a CLI command (sometimes a piped sequence) that accomplishes the task set forth in the prompt.  It will return the commands to be executed agaist the data files you specified with a query to execute the command.
 
+- brew install plz-cli
 
 ## Shell Completion
 

data/lib/aia/cli.rb

@@ -155,6 +155,8 @@ class AIA::Cli
       extra:      [''],   # 
       #
       model:      ["gpt-4-1106-preview",  "--llm --model"],
+      speech_model: ["tts-1", "--sm --spech_model"],
+      voice:        ["alloy", "--voice"],
       #
       dump_file:  [nil,       "--dump"],
       completion: [nil,       "--completion"],

data/lib/aia/main.rb

@@ -53,17 +53,6 @@ class AIA::Main
   end
 
 
-  def speak(what)
-    return false unless AIA.config.speak?
-    # TODO: Consider putting this into a thread
-    #       so that it can speak at the same time
-    #       the output is going to the screen
-    # MacOS uses the say command
-    system "say #{Shellwords.escape(what)}"
-    true
-  end
-
-
   # Function to setup the Reline history with a maximum depth
   def setup_reline_history(max_history_size=5)
     Reline::HISTORY.clear
@@ -123,7 +112,7 @@ class AIA::Main
 
     if AIA.config.chat?
       setup_reline_history
-      speak result
+      AIA.speak result
       lets_chat 
     end
 
@@ -227,14 +216,14 @@ class AIA::Main
           result          = get_and_display_result(the_prompt_text)
 
           log_the_follow_up(the_prompt_text, result)
-          speak result
+          AIA.speak result
         end
       else
         the_prompt_text = insert_terse_phrase(the_prompt_text)
         result          = get_and_display_result(the_prompt_text)
 
         log_the_follow_up(the_prompt_text, result)
-        speak result
+        AIA.speak result
       end
 
       the_prompt_text = ask_question_with_reline("\nFollow Up: ")

data/lib/aia/tools/llm.rb

@@ -0,0 +1,77 @@
+# lib/aia/tools/llm.rb
+
+require_relative 'backend_common'
+
+class AIA::Llm < AIA::Tools
+  include AIA::BackendCommon
+
+  meta(
+    name:     'llm',
+    role:     :backend,
+    desc:     "llm on the command line using local and remote models",
+    url:      "https://llm.datasette.io/",
+    install:  "brew install llm",
+  )
+
+
+  DEFAULT_PARAMETERS = [
+    # "--verbose",          # enable verbose logging (if applicable)
+    # Add default parameters here
+  ].join(' ').freeze
+
+  DIRECTIVES = %w[
+    api_key
+    frequency_penalty
+    max_tokens
+    model
+    presence_penalty
+    stop_sequence
+    temperature
+    top_p
+  ]
+end
+
+__END__
+
+#########################################################
+
+llm, version 0.13.1
+
+Usage: llm [OPTIONS] COMMAND [ARGS]...
+
+  Access large language models from the command-line
+
+  Documentation: https://llm.datasette.io/
+
+  To get started, obtain an OpenAI key and set it like this:
+
+      $ llm keys set openai
+      Enter key: ...
+
+  Then execute a prompt like this:
+
+      llm 'Five outrageous names for a pet pelican'
+
+Options:
+  --version  Show the version and exit.
+  --help     Show this message and exit.
+
+Commands:
+  prompt*       Execute a prompt
+  aliases       Manage model aliases
+  chat          Hold an ongoing chat with a model.
+  collections   View and manage collections of embeddings
+  embed         Embed text and store or return the result
+  embed-models  Manage available embedding models
+  embed-multi   Store embeddings for multiple strings at once
+  install       Install packages from PyPI into the same environment as LLM
+  keys          Manage stored API keys for different models
+  logs          Tools for exploring logged prompts and responses
+  models        Manage available models
+  openai        Commands for working directly with the OpenAI API
+  plugins       List installed plugins
+  similar       Return top N similar IDs from a collection
+  templates     Manage stored prompt templates
+  uninstall     Uninstall Python packages from the LLM environment
+
+  

data/lib/aia/tools/mods.rb

@@ -8,7 +8,7 @@ class AIA::Mods < AIA::Tools
   meta(
     name:     'mods',
     role:     :backend,
-    desc:     'AI on the command-line',
+    desc:     'GPT on the command line. Built for pipelines.',
     url:      'https://github.com/charmbracelet/mods',
     install:  'brew install mods',
   )
@@ -16,25 +16,35 @@ class AIA::Mods < AIA::Tools
   
   DEFAULT_PARAMETERS = [
     # "--no-cache",           # do not save prompt and response
-    "--no-limit"              # no limit on input context
+    "--no-limit",             # no limit on input context
+    "--quiet",                # Quiet mode (hide the spinner while loading and stderr messages for success).
   ].join(' ').freeze
 
 
   DIRECTIVES = %w[
-    api        
-    fanciness  
-    http-proxy 
+    api
+    ask-model
+    continue
+    continue-last
+    fanciness
+    format-as
+    http-proxy
     max-retries
+    max-retries
+    max-tokens
     max-tokens 
     model
     no-cache
     no-limit  
-    quiet      
-    raw        
+    prompt
+    prompt-args
+    quiet
+    raw
     status-text
-    temp       
-    title      
-    topp       
+    temp
+    title
+    topp
+    word-wrap
   ]
 end
 
@@ -43,6 +53,8 @@ __END__
 
 ##########################################################
 
+mods version 1.2.1 (Homebre)
+
 GPT on the command line. Built for pipelines.
 
 Usage:
@@ -50,9 +62,11 @@ Usage:
 
 Options:
   -m, --model           Default model (gpt-3.5-turbo, gpt-4, ggml-gpt4all-j...).
+  -M, --ask-model       Ask which model to use with an interactive prompt.
   -a, --api             OpenAI compatible REST API (openai, localai).
   -x, --http-proxy      HTTP proxy to use for API requests.
   -f, --format          Ask for the response to be formatted as markdown unless otherwise set.
+  --format-as
   -r, --raw             Render output as raw text when connected to a TTY.
   -P, --prompt          Include the prompt from the arguments and stdin, truncate stdin to specified number of lines.
   -p, --prompt-args     Include the prompt from the arguments in the response.
@@ -61,14 +75,16 @@ Options:
   -l, --list            Lists saved conversations.
   -t, --title           Saves the current conversation with the given title.
   -d, --delete          Deletes a saved conversation with the given title or ID.
+  --delete-older-than   Deletes all saved conversations older than the specified duration. Valid units are: ns, us, µs, μs, ms, s, m, h, d, w, mo, and y.
   -s, --show            Show a saved conversation with the given title or ID.
-  -S, --show-last       Show a the last saved conversation.
+  -S, --show-last       Show the last saved conversation.
   -q, --quiet           Quiet mode (hide the spinner while loading and stderr messages for success).
   -h, --help            Show help and exit.
   -v, --version         Show version and exit.
   --max-retries         Maximum number of times to retry API calls.
   --no-limit            Turn off the client-side limit on the size of the input into the model.
   --max-tokens          Maximum number of tokens in response.
+  --word-wrap           Wrap formatted output at specific width (default is 80)
   --temp                Temperature (randomness) of results, from 0.0 to 2.0.
   --topp                TopP, an alternative to temperature that narrows response, from 0.0 to 1.0.
   --fanciness           Your desired level of fanciness.
@@ -81,3 +97,4 @@ Options:
 Example:
   # Editorialize your video files
   ls ~/vids | mods -f "summarize each of these titles, group them by decade" | glow
+

data/lib/aia.rb

@@ -20,11 +20,12 @@ tramp_require('debug_me') {
 }
 
 require 'hashie'
+require 'openai'
 require 'os'
 require 'pathname'
 require 'reline'
 require 'shellwords'
-require 'tempfile'    # SMELL: is this still being used?
+require 'tempfile'
 
 require 'tty-spinner'
 
@@ -45,8 +46,15 @@ require_relative "core_ext/string_wrap"
 module AIA
   class << self
     attr_accessor :config
+    attr_accessor :client
 
     def run(args=ARGV)
+      begin
+        @client = OpenAI::Client.new(access_token: ENV["OPENAI_API_KEY"])
+      rescue OpenAI::ConfigurationError
+        @client = nil
+      end
+
       args = args.split(' ') if args.is_a?(String)
 
       # TODO: Currently this is a one and done architecture.
@@ -59,8 +67,47 @@ module AIA
 
 
     def speak(what)
-      return unless AIA.config.speak?
-      system "say #{Shellwords.escape(what)}" if OS.osx?
+      return unless config.speak?
+
+      if OS.osx? && 'siri' == config.voice.downcase
+        system "say #{Shellwords.escape(what)}"
+      else
+        use_openai_tts(what)
+      end
+    end
+
+
+    def use_openai_tts(what)
+      if client.nil?
+        puts "\nWARNING: OpenAI's text to speech capability is not available at this time."
+        return
+      end
+
+      player = if OS.osx?
+                  'afplay'
+                elsif OS.linux?
+                  'mpg123'
+                elsif OS.windows?
+                  'cmdmp3'
+                else
+                  puts "\nWARNING: There is no MP3 player available"
+                  return
+                end
+
+      response = client.audio.speech(
+        parameters: {
+          model: config.speech_model,
+          input: what,
+          voice: config.voice
+        }
+      )
+
+      Tempfile.create(['speech', '.mp3']) do |f|
+        f.binmode
+        f.write(response)
+        f.close
+        `#{player} #{f.path}`
+      end
     end
   end
 end

data/man/aia.1

@@ -1,6 +1,6 @@
 .\" Generated by kramdown-man 1.0.1
 .\" https://github.com/postmodern/kramdown-man#readme
-.TH aia 1 "v0.5.12" AIA "User Manuals"
+.TH aia 1 "v0.5.14" AIA "User Manuals"
 .SH NAME
 .PP
 aia \- command\-line interface for an AI assistant
@@ -98,6 +98,12 @@ A role ID is the same as a prompt ID\.  A \[lq]role\[rq] is a specialized prompt
 .TP
 \fB\-v\fR, \fB\-\-verbose\fR
 Be Verbose \- default is false
+.TP
+\fB\-\-voice\fR
+The voice to use when the option \fB\-\-speak\fR is used\.  If you are on a Mac, then setting voice to \[lq]siri\[rq] will use your Mac\[cq]s default siri voice and not access OpenAI \- default is \[lq]alloy\[rq] from OpenAI
+.TP
+\fB\-\-sm\fR, \fB\-\-speech\[ru]model\fR
+The OpenAI speech model to use when converting text into speech \- default is \[lq]tts\-1\[rq]
 .SH CONFIGURATION HIERARCHY
 .PP
 System Environment Variables (envars) that are all uppercase and begin with \[lq]AIA\[ru]\[rq] can be used to over\-ride the default configuration settings\.  For example setting \[lq]export AIA\[ru]PROMPTS\[ru]DIR\[eq]\[ti]\[sl]Documents\[sl]prompts\[rq] will over\-ride the default configuration; however, a config value provided by a command line options will over\-ride an envar setting\.
@@ -180,6 +186,11 @@ OpenAI Platform Documentation
 .UE
  and working with OpenAI models\.
 .IP \(bu 2
+llm
+.UR https:\[sl]\[sl]llm\.datasette\.io\[sl]
+.UE
+ for more information on \fBllm\fR \- A CLI utility and Python library for interacting with Large Language Models, both via remote APIs and models that can be installed and run on your own machine\.
+.IP \(bu 2
 mods
 .UR https:\[sl]\[sl]github\.com\[sl]charmbracelet\[sl]mods
 .UE

data/man/aia.1.md

@@ -1,4 +1,4 @@
-# aia 1 "v0.5.12" AIA "User Manuals"
+# aia 1 "v0.5.14" AIA "User Manuals"
 
 ## NAME
 
@@ -103,6 +103,11 @@ The aia command-line tool is an interface for interacting with an AI model backe
 `-v`, `--verbose`
 : Be Verbose - default is false
 
+`--voice`
+: The voice to use when the option `--speak` is used.  If you are on a Mac, then setting voice to "siri" will use your Mac's default siri voice and not access OpenAI - default is "alloy" from OpenAI
+
+`--sm`, `--speech_model`
+: The OpenAI speech model to use when converting text into speech - default is "tts-1"
 
 ## CONFIGURATION HIERARCHY
 
@@ -176,6 +181,8 @@ if you want to specify them one at a time.
 
 - [OpenAI Platform Documentation](https://platform.openai.com/docs/overview) for more information on [obtaining access tokens](https://platform.openai.com/account/api-keys) and working with OpenAI models.
 
+- [llm](https://llm.datasette.io/) for more information on `llm` - A CLI utility and Python library for interacting with Large Language Models, both via remote APIs and models that can be installed and run on your own machine.
+
 - [mods](https://github.com/charmbracelet/mods) for more information on `mods` - AI for the command line, built for pipelines.  LLM based AI is really good at interpreting the output of commands and returning the results in CLI friendly text formats like Markdown. Mods is a simple tool that makes it super easy to use AI on the command line and in your pipelines. Mods works with [OpenAI](https://platform.openai.com/account/api-keys) and [LocalAI](https://github.com/go-skynet/LocalAI)
 
 - [sgpt](https://github.com/tbckr/sgpt) (aka shell-gpt) is a powerful command-line interface (CLI) tool designed for seamless interaction with OpenAI models directly from your terminal. Effortlessly run queries, generate shell commands or code, create images from text, and more, using simple commands. Streamline your workflow and enhance productivity with this powerful and user-friendly CLI tool.

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: aia
 version: !ruby/object:Gem::Version
-  version: 0.5.12
+  version: 0.5.14
 platform: ruby
 authors:
 - Dewayne VanHoozer
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-02-25 00:00:00.000000000 Z
+date: 2024-03-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: hashie
@@ -66,6 +66,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: ruby-openai
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: semver2
   requirement: !ruby/object:Gem::Requirement
@@ -220,18 +234,17 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-description: |
-  A command-line AI Assistante (aia) that provides pre-compositional
-  template prompt management to various backend gen-AI processes.
-  Complete shell integration allows a prompt to access system
-  environment variables and execut shell commands as part of the
-  prompt content.  In addition full embedded Ruby support is provided
-  given even more dynamic prompt conditional content.  It is a
-  generalized power house that rivals specialized gen-AI tools.  aia
-  currently supports "mods" and "sgpt" CLI tools.  aia uses "ripgrep"
-  and "fzf" CLI utilities to search for and select prompt files to
-  send to the backend gen-AI tool along with supported context
-  files.
+description: A command-line AI Assistante (aia) that provides pre-compositional template
+  prompt management to various backend gen-AI processes such as llm, mods and sgpt
+  support processing of prompts both via remote API calls as well as keeping everything
+  local through the use of locally managed models and the LocalAI API. Complete shell
+  integration allows a prompt to access system environment variables and execut shell
+  commands as part of the prompt content.  In addition full embedded Ruby support
+  is provided given even more dynamic prompt conditional content.  It is a generalized
+  power house that rivals specialized gen-AI tools.  aia currently supports "mods"
+  and "sgpt" CLI tools.  aia uses "ripgrep" and "fzf" CLI utilities to search for
+  and select prompt files to send to the backend gen-AI tool along with supported
+  context files.
 email:
 - dvanhoozer@gmail.com
 executables:
@@ -268,6 +281,7 @@ files:
 - lib/aia/tools/editor.rb
 - lib/aia/tools/fzf.rb
 - lib/aia/tools/glow.rb
+- lib/aia/tools/llm.rb
 - lib/aia/tools/mods.rb
 - lib/aia/tools/sgpt.rb
 - lib/aia/tools/subl.rb