【English|中文】
The Offline AI Client builtin command plugin for managing the configuration file.
Before using, you need to first install the Offline AI Client.
#If not already installed, install the client:
npm install -g @offline-ai/cli🛠️ Manage the AI Configuration.
USAGE
$ ai config [ITEM_NAME] [--json] [-u <value>] [--apiKey <value>] [-s <value>...] [--logLevelMaxLen <value>
-l trace|debug|verbose|info|notice|warn|error|fatal|print|silence] [--histories <value>] [-n] [-k] [-t <value> -i]
[--no-chats] [--no-inputs ] [-m] [-f <value>] [-d <value>] [-D <value>...] [-a <value>] [-b <value>] [-p <value>...]
[-L <value>] [-A <value>] [-e true|false|line] [-C <value>] [-P <value>]
ARGUMENTS
ITEM_NAME the config item name path to get
FLAGS
-A, --aiPreferredLanguage=<value> the ISO 639-1 code for the AI preferred language to translate the user input
automatically, eg, en, etc.
-C, --streamEchoChars=<value> [default: 80] stream echo max characters limit
-D, --data=<value>... the data which will be passed to the ai-agent script: key1=value1 key2=value2
-L, --userPreferredLanguage=<value> the ISO 639-1 code for the user preferred language to translate the AI result
automatically, eg, en, zh, ja, ko, etc.
-P, --provider=<value> the LLM provider, defaults to llamacpp
-a, --arguments=<value> the json data which will be passed to the ai-agent script
-b, --brainDir=<value> the brains(LLM) directory
-d, --dataFile=<value> the data file which will be passed to the ai-agent script
-e, --streamEcho=<option> [default: line] stream echo mode
<options: true|false|line>
-f, --script=<value> the ai-agent script file name or id
-i, --[no-]interactive interactive mode
-k, --backupChat whether to backup chat history before start, defaults to false
-l, --logLevel=<option> the log level
<options: trace|debug|verbose|info|notice|warn|error|fatal|print|silence>
-m, --[no-]stream stream mode, defaults to true
-n, --[no-]newChat whether to start a new chat history, defaults to false in interactive mode, true
in non-interactive
-p, --promptDirs=<value>... the prompts template directory
-s, --agentDirs=<value>... the search paths for ai-agent script file
-t, --inputs=<value> the input histories folder for interactive mode to record
-u, --api=<value> the api URL
--apiKey=<value> the api key (optional)
--histories=<value> the chat histories folder to record
--logLevelMaxLen=<value> the max length of log item to display
--no-chats disable chat histories, defaults to false
--no-inputs disable input histories, defaults to false
GLOBAL FLAGS
--json Format output as json.
DESCRIPTION
🛠️ Manage the AI Configuration.
show current configuration if no commands.
EXAMPLES
# list all configurations
$ ai config
# get the brainDir config item
$ ai config brainDir
AI Configuration:
{
"brainDir": "~/.local/share/ai/brain"
}
See code: src/commands/config/index.ts
💾 Save the current configuration to file which can be used to initialize config.
USAGE
$ ai config:save [DATA] [--json] [--config <value>] [--banner] [-u <value>] [--apiKey <value>] [-s <value>...]
[--logLevelMaxLen <value> -l trace|debug|verbose|info|notice|warn|error|fatal|print|silence] [--histories <value>]
[-n] [-k] [-t <value> -i] [--no-chats] [--no-inputs ] [-m] [-f <value>] [-d <value>] [-D <value>...] [-a <value>]
[-b <value>] [-p <value>...] [-L <value>] [-A <value>] [-e true|false|line] [-C <value>] [-P <value>]
ARGUMENTS
DATA the json data which will be passed to the ai-agent script
FLAGS
-A, --aiPreferredLanguage=<value> the ISO 639-1 code for the AI preferred language to translate the user input
automatically, eg, en, etc.
-C, --streamEchoChars=<value> [default: 80] stream echo max characters limit
-D, --data=<value>... the data which will be passed to the ai-agent script: key1=value1 key2=value2
-L, --userPreferredLanguage=<value> the ISO 639-1 code for the user preferred language to translate the AI result
automatically, eg, en, zh, ja, ko, etc.
-P, --provider=<value> the LLM provider, defaults to llamacpp
-a, --arguments=<value> the json data which will be passed to the ai-agent script
-b, --brainDir=<value> the brains(LLM) directory
-d, --dataFile=<value> the data file which will be passed to the ai-agent script
-e, --streamEcho=<option> [default: line] stream echo mode
<options: true|false|line>
-f, --script=<value> the ai-agent script file name or id
-i, --[no-]interactive interactive mode
-k, --backupChat whether to backup chat history before start, defaults to false
-l, --logLevel=<option> the log level
<options: trace|debug|verbose|info|notice|warn|error|fatal|print|silence>
-m, --[no-]stream stream mode, defaults to true
-n, --[no-]newChat whether to start a new chat history, defaults to false in interactive mode, true
in non-interactive
-p, --promptDirs=<value>... the prompts template directory
-s, --agentDirs=<value>... the search paths for ai-agent script file
-t, --inputs=<value> the input histories folder for interactive mode to record
-u, --api=<value> the api URL
--apiKey=<value> the api key (optional)
--[no-]banner show banner
--config=<value> the config file
--histories=<value> the chat histories folder to record
--logLevelMaxLen=<value> the max length of log item to display
--no-chats disable chat histories, defaults to false
--no-inputs disable input histories, defaults to false
GLOBAL FLAGS
--json Format output as json.
See code: src/commands/config/save.ts