Class: OllamaChat::Chat
- Inherits:
-
Object
- Object
- OllamaChat::Chat
- Includes:
- Clipboard, CommandConcern, ConfigHandling, Conversation, Dialog, DocumentCache, FileEditing, HTTPHandling, History, Information, InputContent, KramdownANSI, LocationHandling, Logging, MessageEditing, MessageFormat, MessageOutput, ModelHandling, Pager, Parsing, PersonaeManagement, ServerSocket, SourceFetching, StateSelectors, Switches, ThinkControl, ToolCalling, WebSearching, Term::ANSIColor, Tins::GO
- Defined in:
- lib/ollama_chat/chat.rb
Overview
A chat client for interacting with Ollama models through a terminal interface.
The Chat class provides a complete command-line interface for chatting with language models via the Ollama API. It handles configuration management, message history, document processing, web searching, and various interactive features including voice output, markdown rendering, and embedding capabilities.
Constant Summary
Constants included from Parsing
Instance Attribute Summary collapse
-
#cache ⇒ Object
readonly
Provides read-only access to the cache instance used by the object.
-
#document_policy ⇒ OllamaChat::StateSelector
readonly
The document_policy reader returns the document policy selector for the chat session.
-
#documents ⇒ Documentrix::Documents
readonly
Returns the documents set for this object, initializing it lazily if needed.
-
#messages ⇒ OllamaChat::MessageList
readonly
Returns the messages set for this object, initializing it lazily if needed.
-
#ollama ⇒ Ollama::Client
readonly
The ollama reader returns the Ollama API client instance.
-
#think_mode ⇒ OllamaChat::StateSelector
readonly
The think_mode reader returns the think mode selector for the chat session.
Attributes included from ToolCalling
#enabled_tools, #tool_call_results
Attributes included from ServerSocket
Attributes included from Switches
#embedding, #embedding_enabled, #embedding_paused, #location, #markdown, #runtime_info, #stream, #think_loud, #tools_support, #voice
Instance Method Summary collapse
-
#add_documents_from_argv(document_list) ⇒ Object
private
Adds documents from command line arguments to the document collection.
-
#base_url ⇒ String
private
The base_url method returns the Ollama server URL from command-line options or environment configuration.
-
#clean(what) ⇒ Object
private
The clean method clears various parts of the chat session based on the specified parameter.
-
#collection ⇒ Object
private
Collection.
-
#compose ⇒ Object
private
Input.
-
#config ⇒ Object
private
Settings.
-
#connect_ollama ⇒ Ollama::Client
private
The connect_ollama method establishes a connection to the Ollama API server.
-
#copy ⇒ Object
private
Clipboard.
-
#debug ⇒ TrueClass, FalseClass
The debug method accesses the debug configuration setting.
-
#disable_content_parsing ⇒ Object
private
The disable_content_parsing method turns off content parsing by setting ‘@parse_content` to false.
-
#enable_command_completion(&block) ⇒ Object
private
Enables tab completion for chat commands within the interactive session.
-
#handle_input(content) ⇒ Symbol, ...
private
Handles user input commands and processes chat interactions.
-
#initialize(argv: ARGV.dup) ⇒ Chat
constructor
Initializes a new OllamaChat::Chat instance with the given command-line arguments.
-
#interact_with_user ⇒ Object
private
The interact_with_user method manages the interactive loop for user input and chat processing.
-
#list ⇒ Object
private
Conversation.
-
#manage_links(command) ⇒ Object
private
The manage_links method handles operations on a collection of links, such as displaying them or clearing specific entries.
-
#reconnect ⇒ Object
private
Actions.
-
#setup_cache ⇒ OllamaChat::RedisCache?
private
The setup_cache method initializes and returns a Redis cache instance with expiring keys if a Redis URL is configured.
-
#setup_documents ⇒ Documentrix::Documents, NULL
private
The setup_documents method initializes the document processing pipeline by configuring the embedding model and database connection.
-
#setup_system_prompt ⇒ Object
private
Sets up the system prompt for the chat session.
-
#start ⇒ Object
The start method initializes the chat session by displaying information, then prompts the user for input to begin interacting with the chat.
-
#strip_internal_json_markers(name, content) ⇒ String
private
Removes lines that are JSON objects containing the given key.
-
#web(count, query) ⇒ String, Symbol
private
Performs a web search and processes the results based on document processing configuration.
Methods included from PersonaeManagement
#add_persona, #available_personae, #choose_persona, #default_persona_name, #delete_persona, #edit_persona, #info_persona, #list_personae, #load_persona_file, #load_personae, #persona_backup_pathname, #personae_backup_directory, #personae_directory, #personae_result, #play_persona, #play_persona_file, #play_persona_prompt, #reload_default_persona, #setup_persona_from_opts, #setup_personae_directory
Methods included from ConfigHandling
#config=, #display_config, #edit_config, #fix_config, #reload_config
Methods included from ToolCalling
#configured_tools, #default_enabled_tools, #disable_tool, #enable_tool, #handle_tool_call_results?, #list_tools, #tool_configured?, #tool_enabled?, #tool_function, #tool_paths_allowed, #tool_registered?, #tools
Methods included from LocationHandling
#location_data, #location_description, #location_description?
Methods included from MessageEditing
Methods included from InputContent
#all_file_set, #choose_filename, #context_spook, #file_set_each, #input, #provide_file_set_content
Methods included from Conversation
#load_conversation, #save_conversation
Methods included from FileEditing
#edit_file, #edit_text, #perform_insert, #vim
Methods included from KramdownANSI
#configure_kramdown_ansi_styles, #kramdown_ansi_parse
Methods included from ServerSocket
create_socket_server, #init_server_socket, send_to_server_socket
Methods included from History
#clear_history, #init_chat_history, #save_history
Methods included from Pager
#determine_pager_command, #use_pager
Methods included from MessageFormat
#message_type, #talk_annotate, #think_annotate
Methods included from Clipboard
#copy_to_clipboard, #last_message_content, #paste_from_clipboard, #perform_copy_to_clipboard, #perform_paste_from_clipboard
Methods included from MessageOutput
#attempt_to_write_file, #output, #pipe
Methods included from Information
#client, #collection_stats, #display_chat_help, #info, #runtime_information, #runtime_information_values, #server_url, #server_version, #usage, #version
Methods included from ThinkControl
Methods included from Dialog
#ask?, #change_system_prompt, #change_voice, #choose_collection, #choose_file_set, #choose_prompt, #confirm?, #connect_message, #go_command, #message_list
Methods included from WebSearching
#search_engine, #search_web, #search_web_with_duckduckgo, #search_web_with_searxng
Methods included from SourceFetching
#add_image, #embed, #embed_source, #fetch_source, #fetch_source_as_filename, #import, #import_source, #links, #summarize, #summarize_source
Methods included from Parsing
#parse_atom, #parse_content, #parse_csv, #parse_rss, #parse_source, #pdf_read, #ps_read, #reverse_markdown
Methods included from Utils::AnalyzeDirectory
#generate_structure, #recurse_generate_structure, #structure_each_entry
Methods included from ModelHandling
#choose_model, #model_present?, #model_with_size, #pull_model_from_remote, #pull_model_unless_present, #use_model
Methods included from StateSelectors
Methods included from Switches
Methods included from DocumentCache
#configure_cache, #document_cache_class
Methods included from Logging
Methods included from HTTPHandling
Constructor Details
#initialize(argv: ARGV.dup) ⇒ Chat
Initializes a new OllamaChat::Chat instance with the given command-line arguments.
Sets up the chat environment including configuration parsing, Ollama client initialization, model selection, system prompt handling, document processing setup, and history management. This method handles all the bootstrapping necessary to create a functional chat session that can communicate with an Ollama server and process various input types including text, documents, web content, and images.
The initialization process includes parsing command-line options using Tins::GO for robust argument handling, setting up the Ollama client with configurable timeouts (connect, read, write), validating Ollama API version compatibility (requires >= 0.9.0 for features used), configuring model selection based on command-line or configuration defaults, initializing system prompts from files or inline content, setting up document processing pipeline with embedding capabilities through Documentrix::Documents, creating message history management through OllamaChat::MessageList, initializing cache systems for document embeddings, setting up voice support and image handling for multimodal interactions, enabling optional server socket functionality for remote input, and handling configuration errors with interactive recovery mechanisms.
92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 |
# File 'lib/ollama_chat/chat.rb', line 92 def initialize(argv: ARGV.dup) @opts = go 'f:u:m:s:p:c:C:D:MESVh', argv @opts[?h] and exit usage @opts[?V] and exit version @messages = OllamaChat::MessageList.new(self) @ollama_chat_config = OllamaChat::OllamaChatConfig.new(@opts[?f]) self.config = @ollama_chat_config.config setup_switches(config) setup_state_selectors(config) connect_ollama if conversation_file = @opts[?c] .load_conversation(conversation_file) elsif backup_file = OC::XDG_CACHE_HOME + 'backup.json' and backup_file.exist? .load_conversation(backup_file) FileUtils.rm_f backup_file else @setup_system_prompt = true end .set(config..enabled && !@opts[?E]) @documents = setup_documents @cache = setup_cache @images = [] @kramdown_ansi_styles = configure_kramdown_ansi_styles @enabled_tools = default_enabled_tools @tool_call_results = {} init_chat_history setup_personae_directory @opts[?S] and init_server_socket rescue ComplexConfig::AttributeMissing, ComplexConfig::ConfigurationSyntaxError => e fix_config(e) end |
Instance Attribute Details
#cache ⇒ Object (readonly)
Provides read-only access to the cache instance used by the object
164 165 166 |
# File 'lib/ollama_chat/chat.rb', line 164 def cache @cache end |
#document_policy ⇒ OllamaChat::StateSelector (readonly)
The document_policy reader returns the document policy selector for the chat session.
128 129 130 |
# File 'lib/ollama_chat/chat.rb', line 128 def document_policy @document_policy end |
#documents ⇒ Documentrix::Documents (readonly)
Returns the documents set for this object, initializing it lazily if needed.
The documents set is memoized, meaning it will only be created once per object instance and subsequent calls will return the same Documentrix::Documents instance.
149 150 151 |
# File 'lib/ollama_chat/chat.rb', line 149 def documents @documents end |
#messages ⇒ OllamaChat::MessageList (readonly)
Returns the messages set for this object, initializing it lazily if needed.
The messages set is memoized, meaning it will only be created once per object instance and subsequent calls will return the same OllamaChat::MessageList instance.
159 160 161 |
# File 'lib/ollama_chat/chat.rb', line 159 def @messages end |
#ollama ⇒ Ollama::Client (readonly)
The ollama reader returns the Ollama API client instance.
139 140 141 |
# File 'lib/ollama_chat/chat.rb', line 139 def ollama @ollama end |
#think_mode ⇒ OllamaChat::StateSelector (readonly)
The think_mode reader returns the think mode selector for the chat session.
134 135 136 |
# File 'lib/ollama_chat/chat.rb', line 134 def think_mode @think_mode end |
Instance Method Details
#add_documents_from_argv(document_list) ⇒ Object (private)
Empty entries in the document list will trigger a collection clear operation
Documents are processed in batches of 25 to manage memory usage
Progress is reported to STDOUT during processing
Adds documents from command line arguments to the document collection
Processes a list of document paths or URLs, handling both local files and remote resources.
1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 |
# File 'lib/ollama_chat/chat.rb', line 1201 def add_documents_from_argv(document_list) if document_list.any?(&:empty?) STDOUT.puts "Clearing collection #{bold{documents.collection}}." documents.clear document_list.reject!(&:empty?) end unless document_list.empty? document_list.map! do |doc| if doc =~ %r(\Ahttps?://) doc else File.(doc) end end STDOUT.puts "Collection #{bold{documents.collection}}: Adding #{document_list.size} documents…" count = 1 document_list.each_slice(25) do |docs| docs.each do |doc| fetch_source(doc) do |doc_io| (doc_io, doc, count:) end count += 1 end end end end |
#base_url ⇒ String (private)
The base_url method returns the Ollama server URL from command-line options or environment configuration.
1100 1101 1102 |
# File 'lib/ollama_chat/chat.rb', line 1100 def base_url @opts[?u] || OC::OLLAMA::URL end |
#clean(what) ⇒ Object (private)
The clean method clears various parts of the chat session based on the specified parameter.
902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 |
# File 'lib/ollama_chat/chat.rb', line 902 def clean(what) persona_profile = nil case what when 'messages', nil .clear persona_profile = reload_default_persona STDOUT.puts "Cleared messages." when 'links' links.clear STDOUT.puts "Cleared links." when 'history' clear_history STDOUT.puts "Cleared history." when 'tags' @documents.clear STDOUT.puts "Cleared all tags." when 'all' if confirm?(prompt: '🔔 Are you sure to clear messages and collection? (y/n) ') =~ /y/i .clear @documents.clear links.clear clear_history persona_profile = reload_default_persona STDOUT.puts "Cleared messages and collection #{bold{@documents.collection}}." else STDOUT.puts 'Cancelled.' end end persona_profile end |
#collection ⇒ Object (private)
Collection
479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 |
# File 'lib/ollama_chat/chat.rb', line 479 command( name: :collection, regexp: %r(^/collection(?:\s+(clear|change))?$), complete: [ 'collection', %w[ clear change ] ], help: 'change (default) collection or clear' ) do |subcommand| case subcommand || 'change' when 'clear' loop do = @documents..add('[EXIT]').add('[ALL]') tag = OllamaChat::Utils::Chooser.choose(, prompt: 'Clear? %s') case tag when nil, '[EXIT]' STDOUT.puts "Exiting chooser." break when '[ALL]' if confirm?(prompt: '🔔 Are you sure? (y/n) ') =~ /y/i @documents.clear STDOUT.puts "Cleared collection #{bold{@documents.collection}}." break else STDOUT.puts 'Cancelled.' sleep 3 end when /./ @documents.clear(tags: [ tag ]) STDOUT.puts "Cleared tag #{tag} from collection #{bold{@documents.collection}}." sleep 3 end end when 'change' choose_collection(@documents.collection) end :next end |
#compose ⇒ Object (private)
Input
581 582 583 584 585 586 587 |
# File 'lib/ollama_chat/chat.rb', line 581 command( name: :compose, regexp: %r(^/compose$), help: 'compose content using an EDITOR' ) do compose or :next end |
#config ⇒ Object (private)
Settings
239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 |
# File 'lib/ollama_chat/chat.rb', line 239 command( name: :config, regexp: %r(^/config(?:\s+(edit|reload))?$), complete: [ 'config', %w[ edit reload ] ], optional: true, help: 'output/edit/reload configuration' ) do |subcommand| case subcommand when 'edit' edit_config when 'reload' reload_config else display_config end :next end |
#connect_ollama ⇒ Ollama::Client (private)
The connect_ollama method establishes a connection to the Ollama API server.
This method initializes a new Ollama::Client instance with configured timeouts and connection parameters, then verifies that the connected server meets the minimum required API version (0.9.0). It sets the @ollama instance variable to the configured client and stores the server version in @server_version.
1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 |
# File 'lib/ollama_chat/chat.rb', line 1114 def connect_ollama @server_version = nil @ollama = Ollama::Client.new( connect_timeout: config.timeouts.connect_timeout?, read_timeout: config.timeouts.read_timeout?, write_timeout: config.timeouts.write_timeout?, base_url: base_url, debug: , user_agent: ) if server_version.version < '0.9.0'.version raise 'require ollama API version 0.9.0 or higher' end log(:info, "Connection to #{base_url} established.") @ollama end |
#copy ⇒ Object (private)
Clipboard
219 220 221 222 223 224 225 226 |
# File 'lib/ollama_chat/chat.rb', line 219 command( name: :copy, regexp: %r(/copy$), help: 'to copy last response to clipboard' ) do copy_to_clipboard :next end |
#debug ⇒ TrueClass, FalseClass
The debug method accesses the debug configuration setting.
186 187 188 |
# File 'lib/ollama_chat/chat.rb', line 186 def debug OC::OLLAMA::CHAT::DEBUG end |
#disable_content_parsing ⇒ Object (private)
The disable_content_parsing method turns off content parsing by setting ‘@parse_content` to false.
This prevents automatic parsing of user input content during chat processing.
211 212 213 |
# File 'lib/ollama_chat/chat.rb', line 211 def disable_content_parsing @parse_content = false end |
#enable_command_completion(&block) ⇒ Object (private)
Enables tab completion for chat commands within the interactive session
Temporarily replaces the current Reline completion procedure with a custom one that provides command completion based on the chat help message.
1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 |
# File 'lib/ollama_chat/chat.rb', line 1253 def enable_command_completion(&block) old = Reline.completion_proc Reline.autocompletion = true Reline.completion_proc = -> input, pre { before = [ pre, input ].join case before when %r(^/) start = [ pre, input ].join(' ').strip.gsub(/\s+/, ' ') command_completions.select { _1.start_with?(start) } when %r((./\S*)) OllamaChat::Utils::PathCompleter.new(pre, input).complete end } block.() ensure Reline.completion_proc = old end |
#handle_input(content) ⇒ Symbol, ... (private)
Handles user input commands and processes chat interactions.
785 786 787 788 789 790 791 |
# File 'lib/ollama_chat/chat.rb', line 785 def handle_input(content) commands.each do |_name, command| action = command.execute_if_match?(content) {} action and return action end content end |
#interact_with_user ⇒ Object (private)
The interact_with_user method manages the interactive loop for user input and chat processing. It handles reading user input, processing commands, managing messages, and communicating with the Ollama server. The method supports command completion, prefilling prompts, socket input handling, and various chat features including embedding context and voice support. It processes user input through command handling, content parsing, and message formatting before sending requests to the Ollama server. The method also handles server socket messages, manages chat history, and ensures proper cleanup and configuration handling throughout the interaction.
945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 |
# File 'lib/ollama_chat/chat.rb', line 945 def interact_with_user loop do if persona_result = setup_persona_from_opts disable_content_parsing content = persona_result else @parse_content = true type = :terminal_input input_prompt = bold { color(172) { (@images) + " user" } } + bold { "> " } begin if content = handle_tool_call_results? disable_content_parsing else content = enable_command_completion do if prefill_prompt = @prefill_prompt.full? Reline.pre_input_hook = -> { Reline.insert_text prefill_prompt.gsub(/\n*\z/, '') @prefill_prompt = nil } else Reline.pre_input_hook = nil end Reline.readline(input_prompt, true)&.chomp end end rescue Interrupt if = type = .type.full?(:to_sym) || :socket_input content = .content @parse_content = .parse STDOUT.puts color(112) { "Received a server socket message. Processing now…" } else raise end end if type == :terminal_input case next_action = handle_input(content) when :next next when :redo redo when :return return when String content = next_action end end end content = content.encode(invalid: :replace) content, = if @parse_content parse_content(content, @images) else [ content, Documentrix::Utils::Tags.new(valid_tag: /\A#*([\w\]\[]+)/) ] end if .on? && content records = @documents.find_where( content.downcase.first(config..model.context_length), tags:, prompt: config..model.prompt?, text_size: config..found_texts_size?, text_count: config..found_texts_count?, ) unless records.empty? content << ?\n << JSON( prompt: "Consider these snippets generated from retrieval when formulating your response!", ollama_chat_retrieval_snippets: records.map { |r| { text: r.text, tags: r..map { |t| { name: t.to_s(link: false), source: t.source }.compact } } }, ) end end runtime_info.on? && content and content << ?\n << { ollama_chat_runtime_information: runtime_information }.to_json << Ollama::Message.new(role: 'user', content:, images: @images.dup) @images.clear handler = OllamaChat::FollowChat.new( chat: self, messages:, voice: (@voices.selected if voice.on?) ) begin retried = false ollama.chat( model: @model, messages: , options: @model_options, stream: stream.on?, think: , tools: , &handler ) rescue Ollama::Errors::BadRequestError if (think? || tools_support.on?) && !retried STDOUT.puts "#{bold('Error')}: in think mode/with tool support, switch both off and retry." sleep 1 think_mode.selected = 'disabled' tools_support.set false retried = true retry else raise end end if .on? && !records.empty? STDOUT.puts "", records.map { |record| link = if record.source =~ %r(\Ahttps?://) record.source else 'file://%s' % File.(record.source) end [ link, ?# + record..first ] }.uniq.map { |l, t| hyperlink(l, t) }.join(' ') debug and jj .to_ary end case type when :socket_input &.disconnect when :socket_input_with_response if = handler..last .respond({ role: .role, content: .content }) end &.disconnect end rescue Ollama::Errors::TimeoutError msg = "Currently lost connection to ollama server and cannot send command." log(:warn, msg, warn: true) rescue Interrupt STDOUT.puts "Type /quit to quit." ensure self. = nil end 0 rescue ComplexConfig::AttributeMissing, ComplexConfig::ConfigurationSyntaxError => e log(:error, e) fix_config(e) ensure save_history end |
#list ⇒ Object (private)
Conversation
361 362 363 364 365 366 367 368 369 370 |
# File 'lib/ollama_chat/chat.rb', line 361 command( name: :list, regexp: %r(^/list(?:\s+(\d*))?$), options: '[n=1]', help: 'list the last n / all conversation exchanges' ) do n = 2 * _1.to_i if _1 .list_conversation(n) :next end |
#manage_links(command) ⇒ Object (private)
The manage_links method handles operations on a collection of links, such as displaying them or clearing specific entries.
It supports two main commands: ‘clear’ and nil (default). When the command is ‘clear’, it presents an interactive menu to either clear all links or individual links. When the command is nil, it displays the current list of links with hyperlinks.
860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 |
# File 'lib/ollama_chat/chat.rb', line 860 def manage_links(command) case command when 'clear' loop do = links.dup.add('[EXIT]').add('[ALL]') link = OllamaChat::Utils::Chooser.choose(, prompt: 'Clear? %s') case link when nil, '[EXIT]' STDOUT.puts "Exiting chooser." break when '[ALL]' if confirm?(prompt: '🔔 Are you sure? (y/n) ') =~ /y/i links.clear STDOUT.puts "Cleared all links in list." break else STDOUT.puts 'Cancelled.' sleep 3 end when /./ links.delete(link) STDOUT.puts "Cleared link from links in list." sleep 3 end end when nil if links.empty? STDOUT.puts "List is empty." else w = Math.log10(links.size + 1).ceil format = "%#{w}s. %s" connect = -> link { hyperlink(link) { link } } STDOUT.puts links.each_with_index.map { |x, i| format % [ i + 1, connect.(x) ] } end end end |
#reconnect ⇒ Object (private)
Actions
719 720 721 722 723 724 725 726 727 728 |
# File 'lib/ollama_chat/chat.rb', line 719 command( name: :reconnect, regexp: %r(^/reconnect$), help: 'reconnect to current ollama server' ) do STDERR.print green { "Reconnecting to ollama #{base_url.to_s.inspect}…" } connect_ollama STDERR.puts green { " Done." } :next end |
#setup_cache ⇒ OllamaChat::RedisCache? (private)
The setup_cache method initializes and returns a Redis cache instance with expiring keys if a Redis URL is configured.
1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 |
# File 'lib/ollama_chat/chat.rb', line 1233 def setup_cache if url = config.redis.expiring.url? ex = config.redis.expiring.ex?.to_i OllamaChat::RedisCache.new( prefix: 'Expiring-', url:, ex: ) end end |
#setup_documents ⇒ Documentrix::Documents, NULL (private)
The setup_documents method initializes the document processing pipeline by configuring the embedding model and database connection. It then loads specified documents into the system and returns the configured document collection.
1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 |
# File 'lib/ollama_chat/chat.rb', line 1156 def setup_documents if .on? @embedding_model = config..model.name @embedding_model_options = Ollama::Options[config..model.] pull_model_unless_present(@embedding_model) collection = @opts[?C] || config..collection @documents = Documentrix::Documents.new( ollama:, model: @embedding_model, model_options: config..model., embedding_length: config..model., database_filename: config..database_filename || @ollama_chat_config.database_path, collection: , cache: configure_cache, redis_url: config.redis.documents.url?, debug: ) document_list = @opts[?D].to_a add_documents_from_argv(document_list) @documents else NULL end end |
#setup_system_prompt ⇒ Object (private)
Sets up the system prompt for the chat session.
This method determines whether to use a default system prompt or a custom one specified via command-line options. If a custom system prompt is provided with a regexp selector (starting with ?), it invokes the change_system_prompt method to handle the selection. Otherwise, it retrieves the system prompt from a file or uses the default value, then sets it in the message history.
1139 1140 1141 1142 1143 1144 1145 1146 1147 |
# File 'lib/ollama_chat/chat.rb', line 1139 def setup_system_prompt default = config.system_prompts.default? || @model_metadata.system if @opts[?s] =~ /\A\?/ change_system_prompt(default, system: @opts[?s]) else system = OllamaChat::Utils::FileArgument.get_file_argument(@opts[?s], default:) system.present? and .set_system_prompt(system) end end |
#start ⇒ Object
The start method initializes the chat session by displaying information, then prompts the user for input to begin interacting with the chat.
168 169 170 171 172 173 174 175 176 177 178 179 180 181 |
# File 'lib/ollama_chat/chat.rb', line 168 def start begin use_model(@opts[?m].full? || config.model.name) rescue OllamaChat::UnknownModelError => e abort "Failed to use to model: #{e}" end @model_options = Ollama::Options[config.model.] @setup_system_prompt and setup_system_prompt STDOUT.puts "\nType /help to display the chat help." interact_with_user end |
#strip_internal_json_markers(name, content) ⇒ String (private)
Removes lines that are JSON objects containing the given key.
197 198 199 200 201 202 203 204 |
# File 'lib/ollama_chat/chat.rb', line 197 def strip_internal_json_markers(name, content) name = name.to_s content.each_line.map do |line| JSON(line).fetch(name) and next rescue line end.compact.join end |
#web(count, query) ⇒ String, Symbol (private)
Performs a web search and processes the results based on document processing configuration.
Searches for the given query using the configured search engine and processes up to the specified number of URLs. The processing approach varies based on the current document policy and embedding status:
-
**Embedding mode**: When ‘document_policy.selected == ’embedding’‘ AND `@embedding.on?` is true, each result is embedded and the query is interpolated into the
web_embedprompt. -
**Summarizing mode**: When ‘document_policy.selected == ’summarizing’‘, each result is summarized and both query and results are interpolated into the
web_summarizeprompt. -
**Importing mode**: For all other cases, each result is imported and both query and results are interpolated into the
web_importprompt.
823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 |
# File 'lib/ollama_chat/chat.rb', line 823 def web(count, query) urls = search_web(query, count.to_i) or return :next if document_policy.selected == 'embedding' && @embedding.on? prompt = config.prompts. urls.each do |url| fetch_source(url) { |url_io| (url_io, url) } end prompt.named_placeholders_interpolate({query:}) elsif document_policy.selected == 'summarizing' prompt = config.prompts.web_import results = urls.each_with_object('') do |url, content| summarize(url).full? do |c| content << c.ask_and_send_or_self(:read) end end prompt.named_placeholders_interpolate({query:, results:}) else prompt = config.prompts.web_summarize results = urls.each_with_object('') do |url, content| import(url).full? do |c| content << c.ask_and_send_or_self(:read) end end prompt.named_placeholders_interpolate({query:, results:}) end end |