ollama-ruby 0.8.0 → 0.9.1

data/bin/ollama_chat

@@ -52,6 +52,7 @@ class OllamaChatConfig
       list: <%= `say -v ? 2>/dev/null`.lines.map { _1[/^(.+?)\s+[a-z]{2}_[a-zA-Z0-9]{2,}/, 1] }.uniq.sort.to_s.force_encoding('ASCII-8BIT') %>
     markdown: true
     stream: true
+    document_policy: importing
     embedding:
       enabled: true
       model:
@@ -107,7 +108,7 @@ class OllamaChatConfig
 end
 
 class FollowChat
-  include Ollama::Handlers::Concern
+  include Handlers::Concern
   include Term::ANSIColor
 
   def initialize(messages:, markdown: false, voice: nil, output: $stdout)
@@ -163,114 +164,142 @@ class FollowChat
   end
 end
 
-module CheckSwitch
-  extend Tins::Concern
+module Switches
+  module CheckSwitch
+    extend Tins::Concern
 
-  included do
-    alias_method :on?, :value
-  end
+    included do
+      alias_method :on?, :value
+    end
 
-  def off?
-    !on?
-  end
+    def off?
+      !on?
+    end
 
-  def show
-    puts @msg[value]
+    def show
+      puts @msg[value]
+    end
   end
-end
 
-class Switch
-  def initialize(name, msg:, config: $config)
-    @value = [ false, true ].include?(config) ? config : !!config.send("#{name}?")
-    @msg   = msg
-  end
+  class Switch
+    def initialize(name, msg:, config: $config)
+      @value = [ false, true ].include?(config) ? config : !!config.send("#{name}?")
+      @msg   = msg
+    end
 
-  attr_reader :value
+    attr_reader :value
 
-  def set(value, show: false)
-    @value = !!value
-    show && self.show
-  end
+    def set(value, show: false)
+      @value = !!value
+      show && self.show
+    end
 
-  def toggle(show: true)
-    @value = !@value
-    show && self.show
+    def toggle(show: true)
+      @value = !@value
+      show && self.show
+    end
+
+    include CheckSwitch
   end
 
-  include CheckSwitch
-end
+  class CombinedSwitch
+    def initialize(value:, msg:)
+      @value = value
+      @msg   = msg
+    end
 
-class CombinedSwitch
-  def initialize(value:, msg:)
-    @value = value
-    @msg   = msg
-  end
+    def value
+      @value.()
+    end
 
-  def value
-    @value.()
+    include CheckSwitch
   end
 
-  include CheckSwitch
-end
+  def setup_switches
+    $markdown = Switch.new(
+      :markdown,
+      msg: {
+        true  => "Using #{italic{'ANSI'}} markdown to output content.",
+        false => "Using plaintext for outputting content.",
+      }
+    )
 
-def setup_switches
-  $markdown = Switch.new(
-    :markdown,
-    msg: {
-      true  => "Using #{italic{'ANSI'}} markdown to output content.",
-      false => "Using plaintext for outputting content.",
-    }
-  )
+    $stream = Switch.new(
+      :stream,
+      msg: {
+        true  => "Streaming enabled.",
+        false => "Streaming disabled.",
+      }
+    )
 
-  $stream = Switch.new(
-    :stream,
-    msg: {
-      true  => "Streaming enabled.",
-      false => "Streaming disabled.",
-    }
-  )
+    $voice = Switch.new(
+      :stream,
+      msg: {
+        true  => "Voice output enabled.",
+        false => "Voice output disabled.",
+      },
+      config: $config.voice
+    )
 
-  $voice = Switch.new(
-    :stream,
-    msg: {
-      true  => "Voice output enabled.",
-      false => "Voice output disabled.",
-    },
-    config: $config.voice
-  )
+    $embedding_enabled = Switch.new(
+      :embedding_enabled,
+      msg: {
+        true  => "Embedding enabled.",
+        false => "Embedding disabled.",
+      }
+    )
 
-  $embedding_enabled = Switch.new(
-    :embedding_enabled,
-    msg: {
-      true  => "Embedding enabled.",
-      false => "Embedding disabled.",
-    }
-  )
+    $embedding_paused = Switch.new(
+      :embedding_paused,
+      msg: {
+        true  => "Embedding paused.",
+        false => "Embedding resumed.",
+      }
+    )
 
-  $embedding_paused = Switch.new(
-    :embedding_paused,
-    msg: {
-      true  => "Embedding paused.",
-      false => "Embedding resumed.",
-    }
-  )
+    $embedding = CombinedSwitch.new(
+      value: -> { $embedding_enabled.on? && $embedding_paused.off? },
+      msg: {
+        true  => "Embedding is currently performed.",
+        false => "Embedding is currently not performed.",
+      }
+    )
 
-  $embedding = CombinedSwitch.new(
-    value: -> { $embedding_enabled.on? && $embedding_paused.off? },
-    msg: {
-      true  => "Embedding is currently performed.",
-      false => "Embedding is currently not performed.",
-    }
-  )
+    $location = Switch.new(
+      :location,
+      msg: {
+        true  => "Location and localtime enabled.",
+        false => "Location and localtime disabled.",
+      },
+      config: $config.location.enabled
+    )
+  end
+end
+include Switches
 
-  $location = Switch.new(
-    :location,
-    msg: {
-      true  => "Location and localtime enabled.",
-      false => "Location and localtime disabled.",
-    },
-    config: $config.location.enabled
-  )
+def pull_model_unless_present(model, options, retried = false)
+  ollama.show(name: model) { |response|
+    puts "Model #{bold{model}} with architecture "\
+      "#{response.model_info['general.architecture']} found."
+    if system = response.system
+      puts "Configured model system prompt is:\n#{italic { system }}"
+      return system
+    else
+      return
+    end
+  }
+rescue Errors::NotFoundError
+  puts "Model #{bold{model}} not found locally, attempting to pull it from remote now…"
+  ollama.pull(name: model)
+  if retried
+    exit 1
+  else
+    retried = true
+    retry
+  end
+rescue Errors::Error => e
+  warn "Caught #{e.class} while pulling model: #{e} => Exiting."
+  exit 1
 end
 
 def search_web(query, n = nil)
@@ -281,7 +310,7 @@ def search_web(query, n = nil)
   n < 1 and n = 1
   query = URI.encode_uri_component(query)
   url = "https://www.duckduckgo.com/html/?q=#{query}"
-  Ollama::Utils::Fetcher.get(url, debug: $config.debug) do |tmp|
+  Utils::Fetcher.get(url, debug: $config.debug) do |tmp|
     result = []
     doc = Nokogiri::HTML(tmp)
     doc.css('.results_links').each do |link|
@@ -302,38 +331,13 @@ def search_web(query, n = nil)
   end
 end
 
-def pull_model_unless_present(model, options, retried = false)
-  ollama.show(name: model) { |response|
-    puts "Model #{bold{model}} with architecture "\
-      "#{response.model_info['general.architecture']} found."
-    if system = response.system
-      puts "Configured model system prompt is:\n#{italic { system }}"
-      return system
-    else
-      return
-    end
-  }
-rescue Errors::NotFoundError
-  puts "Model #{bold{model}} not found locally, attempting to pull it from remote now…"
-  ollama.pull(name: model)
-  if retried
-    exit 1
-  else
-    retried = true
-    retry
-  end
-rescue Errors::Error => e
-  warn "Caught #{e.class} while pulling model: #{e} => Exiting."
-  exit 1
-end
-
 def load_conversation(filename)
   unless File.exist?(filename)
     puts "File #{filename} doesn't exist. Choose another filename."
     return
   end
   File.open(filename, 'r') do |output|
-    return JSON(output.read).map { Ollama::Message.from_hash(_1) }
+    return JSON(output.read).map { Message.from_hash(_1) }
   end
 end
 
@@ -479,59 +483,6 @@ def parse_source(source_io)
   end
 end
 
-def embed_source(source_io, source, count: nil)
-  $embedding.on? or return parse_source(source_io)
-  m = "Embedding #{italic { source_io&.content_type }} document #{source.to_s.inspect}."
-  if count
-    puts '%u. %s' % [ count, m ]
-  else
-    puts m
-  end
-  text = parse_source(source_io) or return
-  text.downcase!
-  splitter_config = $config.embedding.splitter
-  inputs = nil
-  case splitter_config.name
-  when 'Character'
-    splitter = Ollama::Documents::Splitters::Character.new(
-      chunk_size: splitter_config.chunk_size,
-    )
-    inputs = splitter.split(text)
-  when 'RecursiveCharacter'
-    splitter = Ollama::Documents::Splitters::RecursiveCharacter.new(
-      chunk_size: splitter_config.chunk_size,
-    )
-    inputs = splitter.split(text)
-  when 'Semantic'
-    splitter = Ollama::Documents::Splitters::Semantic.new(
-      ollama:, model: $config.embedding.model.name,
-      chunk_size: splitter_config.chunk_size,
-    )
-    inputs = splitter.split(
-      text,
-      breakpoint: splitter_config.breakpoint.to_sym,
-      percentage: splitter_config.percentage?,
-      percentile: splitter_config.percentile?,
-    )
-    inputs = splitter.split(text)
-  end
-  inputs or return
-  source = source.to_s
-  if source.start_with?(?!)
-    source = Ollama::Utils::Width.truncate(
-      source[1..-1].gsub(/\W+/, ?_),
-      length: 10
-    )
-  end
-  $documents.add(inputs, source:, batch_size: $config.embedding.batch_size?)
-end
-
-def add_image(images, source_io, source)
-  STDERR.puts "Adding #{source_io&.content_type} image #{source.to_s.inspect}."
-  image = Image.for_io(source_io, path: source.to_s)
-  (images << image).uniq!
-end
-
 def http_options(url)
   options = {}
   if ssl_no_verify = $config.ssl_no_verify?
@@ -556,7 +507,7 @@ def fetch_source(source, &block)
       source,
       cache:        $cache,
       debug:        $config.debug,
-      http_options: http_options(source)
+      http_options: http_options(Utils::Fetcher.normalize_url(source))
     ) do |tmp|
       block.(tmp)
     end
@@ -570,33 +521,94 @@ def fetch_source(source, &block)
     raise "invalid source"
   end
 rescue => e
-  STDERR.puts "Cannot fetch source #{source.to_s.inspect}: #{e}\n#{e.backtrace * ?\n}"
+  STDERR.puts "Cannot fetch source #{source.to_s.inspect}: #{e.class} #{e}\n#{e.backtrace * ?\n}"
+end
+
+def add_image(images, source_io, source)
+  STDERR.puts "Adding #{source_io&.content_type} image #{source.to_s.inspect}."
+  image = Image.for_io(source_io, path: source.to_s)
+  (images << image).uniq!
+end
+
+def import_source(source_io, source)
+  source = source.to_s
+  puts "Importing #{italic { source_io&.content_type }} document #{source.inspect} now."
+	source_content = parse_source(source_io)
+  "Imported #{source.inspect}:\n#{source_content}\n\n"
 end
 
 def import(source)
-  puts "Now importing #{source.to_s.inspect}."
   fetch_source(source) do |source_io|
-    content = parse_source(source_io)
-    content.present? or return
+    content = import_source(source_io, source) or return
     source_io.rewind
     content
   end
 end
 
-def summarize(source, words: nil)
+def summarize_source(source_io, source, words: nil)
+  puts "Summarizing #{italic { source_io&.content_type }} document #{source.inspect} now."
   words = words.to_i
   words < 1 and words = 100
-  puts "Now summarizing #{source.to_s.inspect}."
-  source_content =
-    fetch_source(source) do |source_io|
-      content = parse_source(source_io)
-      content.present? or return
-      source_io.rewind
-      content
-    end
+  source_content = parse_source(source_io)
+  source_content.present? or return
   $config.prompts.summarize % { source_content:, words: }
 end
 
+def summarize(source, words: nil)
+  fetch_source(source) do |source_io|
+    content = summarize_source(source_io, source, words:) or return
+    source_io.rewind
+    content
+  end
+end
+
+def embed_source(source_io, source, count: nil)
+  $embedding.on? or return parse_source(source_io)
+  m = "Embedding #{italic { source_io&.content_type }} document #{source.to_s.inspect}."
+  if count
+    puts '%u. %s' % [ count, m ]
+  else
+    puts m
+  end
+  text = parse_source(source_io) or return
+  text.downcase!
+  splitter_config = $config.embedding.splitter
+  inputs = nil
+  case splitter_config.name
+  when 'Character'
+    splitter = Documents::Splitters::Character.new(
+      chunk_size: splitter_config.chunk_size,
+    )
+    inputs = splitter.split(text)
+  when 'RecursiveCharacter'
+    splitter = Documents::Splitters::RecursiveCharacter.new(
+      chunk_size: splitter_config.chunk_size,
+    )
+    inputs = splitter.split(text)
+  when 'Semantic'
+    splitter = Documents::Splitters::Semantic.new(
+      ollama:, model: $config.embedding.model.name,
+      chunk_size: splitter_config.chunk_size,
+    )
+    inputs = splitter.split(
+      text,
+      breakpoint: splitter_config.breakpoint.to_sym,
+      percentage: splitter_config.percentage?,
+      percentile: splitter_config.percentile?,
+    )
+    inputs = splitter.split(text)
+  end
+  inputs or return
+  source = source.to_s
+  if source.start_with?(?!)
+    source = Utils::Width.truncate(
+      source[1..-1].gsub(/\W+/, ?_),
+      length: 10
+    )
+  end
+  $documents.add(inputs, source:, batch_size: $config.embedding.batch_size?)
+end
+
 def embed(source)
   if $embedding.on?
     puts "Now embedding #{source.to_s.inspect}."
@@ -618,6 +630,7 @@ def parse_content(content, images)
   images.clear
   tags = Utils::Tags.new
 
+  contents = [ content ]
   content.scan(%r((?:\.\.|[.~])?/\S+|https?://\S+|#\S+)).each do |source|
     case source
     when /\A#(\S+)/
@@ -628,8 +641,15 @@ def parse_content(content, images)
         case source_io&.content_type&.media_type
         when 'image'
           add_image(images, source_io, source)
-        when 'text', 'application'
-          embed_source(source_io, source)
+        when 'text', 'application', nil
+          case $document_policy
+          when 'importing'
+            contents << import_source(source_io, source)
+          when 'embedding'
+            embed_source(source_io, source)
+          when 'summarizing'
+            contents << summarize_source(source_io, source)
+          end
         else
           STDERR.puts(
             "Cannot fetch #{source.to_s.inspect} with content type "\
@@ -639,14 +659,14 @@ def parse_content(content, images)
       end
     end
   end
-
-  return content, (tags unless tags.empty?)
+  new_content = contents.select(&:present?).compact * "\n\n"
+  return new_content, (tags unless tags.empty?)
 end
 
 def choose_model(cli_model, current_model)
   models = ollama.tags.models.map(&:name).sort
   model = if cli_model == ''
-            Ollama::Utils::Chooser.choose(models) || current_model
+            Utils::Chooser.choose(models) || current_model
           else
             cli_model || current_model
           end
@@ -663,7 +683,7 @@ def choose_collection(current_collection)
   collections = [ current_collection ] + $documents.collections
   collections = collections.compact.map(&:to_s).uniq.sort
   collections.unshift('[EXIT]').unshift('[NEW]')
-  collection = Ollama::Utils::Chooser.choose(collections) || current_collection
+  collection = Utils::Chooser.choose(collections) || current_collection
   case collection
   when '[NEW]'
     $documents.collection = ask?(prompt: "Enter name of the new collection: ")
@@ -674,7 +694,29 @@ def choose_collection(current_collection)
   end
 ensure
   puts "Using collection #{bold{$documents.collection}}."
-  collection_stats
+  info
+end
+
+def choose_document_policy
+  policies = %w[ importing embedding summarizing ].sort
+  current  = if policies.index($document_policy)
+               $document_policy
+             elsif policies.index($config.document_policy)
+               $config.document_policy
+             else
+               policies.first
+             end
+  policies.unshift('[EXIT]')
+  policy = Utils::Chooser.choose(policies)
+  case policy
+  when nil, '[EXIT]'
+    puts "Exiting chooser."
+    policy = current
+  end
+  $document_policy = policy
+ensure
+  puts "Using document policy #{bold{$document_policy}}."
+  info
 end
 
 def collection_stats
@@ -695,19 +737,19 @@ end
 
 def configure_cache
   if $opts[?M]
-    Ollama::Documents::MemoryCache
+    Documents::MemoryCache
   else
     Object.const_get($config.cache)
   end
 rescue => e
   STDERR.puts "Caught #{e.class}: #{e} => Falling back to MemoryCache."
-  Ollama::Documents::MemoryCache
+  Documents::MemoryCache
 end
 
 def show_system_prompt
   puts <<~EOT
     Configured system prompt is:
-    #{Ollama::Utils::ANSIMarkdown.parse($system.to_s).gsub(/\n+\z/, '').full? || 'n/a'}
+    #{Utils::ANSIMarkdown.parse($system.to_s).gsub(/\n+\z/, '').full? || 'n/a'}
   EOT
 end
 
@@ -731,7 +773,7 @@ end
 
 def change_system_prompt(messages, default)
   prompts = $config.system_prompts.attribute_names.compact
-  chosen  = Ollama::Utils::Chooser.choose(prompts)
+  chosen  = Utils::Chooser.choose(prompts)
   system  = if chosen
               $config.system_prompts.send(chosen)
             else
@@ -741,7 +783,7 @@ def change_system_prompt(messages, default)
 end
 
 def change_voice
-  chosen  = Ollama::Utils::Chooser.choose($config.voice.list)
+  chosen  = Utils::Chooser.choose($config.voice.list)
   $current_voice = chosen.full? || $config.voice.default
 end
 
@@ -756,6 +798,7 @@ def info
   $markdown.show
   $stream.show
   $location.show
+  puts "Document policy for references in user text: #{bold{$document_policy}}"
   if $voice.on?
     puts "Using voice #{bold{$current_voice}} to speak."
   end
@@ -799,6 +842,7 @@ def display_chat_help
     /regenerate                     the last answer message
     /collection( clear|change)      change (default) collection or clear
     /info                           show information for current session
+    /document_policy                pick a scan policy for document references
     /import source                  import the source's content
     /summarize [n] source           summarize the source's content in n words
     /embedding                      toggle embedding paused or not
@@ -832,7 +876,7 @@ def usage
 end
 
 def version
-  puts "%s %s" % [ File.basename($0), Ollama::VERSION ]
+  puts "%s %s" % [ File.basename($0), VERSION ]
   exit 0
 end
 
@@ -853,10 +897,11 @@ $opts[?V] and version
 base_url = $opts[?u] || $config.url
 $ollama      = Client.new(base_url:, debug: $config.debug)
 
-$model       = choose_model($opts[?m], $config.model.name)
-options      = Options[$config.model.options]
-model_system = pull_model_unless_present($model, options)
-messages     = []
+$document_policy = $config.document_policy
+$model           = choose_model($opts[?m], $config.model.name)
+options          = Options[$config.model.options]
+model_system     = pull_model_unless_present($model, options)
+messages         = []
 $embedding_enabled.set($config.embedding.enabled && !$opts[?E])
 
 if $opts[?c]
@@ -866,7 +911,7 @@ else
   if $opts[?s] == ??
     change_system_prompt(messages, default)
   else
-    system = Ollama::Utils::FileArgument.get_file_argument($opts[?s], default:)
+    system = Utils::FileArgument.get_file_argument($opts[?s], default:)
     system.present? and set_system_prompt(messages, system)
   end
 end
@@ -916,7 +961,7 @@ else
 end
 
 if redis_expiring_url = $config.redis.expiring.url?
-  $cache = Ollama::Documents::RedisCache.new(
+  $cache = Documents::RedisCache.new(
     prefix: 'Expiring-',
     url:    redis_expiring_url,
     ex:     $config.redis.expiring.ex,
@@ -969,7 +1014,7 @@ loop do
     puts "Cleared messages."
     next
   when %r(^/clobber$)
-    if ask?(prompt: 'Are you sure? (y/n) ') =~ /\Ay/i
+    if ask?(prompt: 'Are you sure to clear messages and collection? (y/n) ') =~ /\Ay/i
       clear_messages(messages)
       $documents.clear
       puts "Cleared messages and collection #{bold{$documents.collection}}."
@@ -1010,7 +1055,7 @@ loop do
     when 'clear'
       loop do
         tags = $documents.tags.add('[EXIT]').add('[ALL]')
-        tag = Ollama::Utils::Chooser.choose(tags, prompt: 'Clear? %s')
+        tag = Utils::Chooser.choose(tags, prompt: 'Clear? %s')
         case tag
         when nil, '[EXIT]'
           puts "Exiting chooser."
@@ -1034,9 +1079,12 @@ loop do
       choose_collection($documents.collection)
     end
     next
-  when %r(/info)
+  when %r(^/info$)
     info
     next
+  when %r(^/document_policy$)
+    choose_document_policy
+    next
   when %r(^/import\s+(.+))
     parse_content = false
     content       = import($1) or next

data/lib/ollama/handlers/markdown.rb

@@ -7,7 +7,7 @@ class Ollama::Handlers::Markdown
   def initialize(output: $stdout)
     super
     @output.sync = true
-    @content = ''
+    @content     = ''
   end
 
   def call(response)
@@ -16,7 +16,6 @@ class Ollama::Handlers::Markdown
       markdown_content = Ollama::Utils::ANSIMarkdown.parse(@content)
       @output.print clear_screen, move_home, markdown_content
     end
-    response.done and @output.puts
     self
   end
 end