GPT3 Powered CLI

Installation

You'd need to install it globally

npm i @abhagsain/ai-cli -g

Usage

$ ai ask "Check process running on port"

You'd need to enter your own OpenAI API key Here's how you can get one

1. Go to https://openai.com/api/login
2. Create an account or log into your existing account
3. Go to https://beta.openai.com/account/api-keys or
4. Run ai auth, enter your API KEY and you're good to go!

Pricing

The current prompt length is ~800 tokens and average response length is ~40 tokens. The pricing for gpt-3.5-turbo is $0.001 per 1K input tokens and $0.002 per 1K output tokens which is ~$0.0009/command. We'll see if we can improve the response as well as reduce the per-command-cost with fine-tuning.

---

Add autocomplete by running ai autocomplete and follow the instructions. It's super easy.

__

Liked this project? Checkout my other side project. SlidesAI.io - AI Presentation Maker

__

Auto generated documentation

• Usage
• Commands

Usage

$ npm install -g @abhagsain/ai-cli
$ ai COMMAND
running command...
$ ai (--version)
@abhagsain/ai-cli/1.3.0 darwin-arm64 node-v18.0.0
$ ai --help [COMMAND]
USAGE
  $ ai COMMAND
...

Commands

• ai ask [question]
• ai auth
• ai autocomplete [SHELL]
• ai help [COMMAND]
• ai model
• ai update [CHANNEL]

ai ask [question]

Ask question to GPT3 from your terminal

USAGE
  $ ai ask [question]

ARGUMENTS
  QUESTION  Your question

DESCRIPTION
  Ask question to GPT3 from your terminal

EXAMPLES
  $ ai ask "Check running process on port 3000"

See code: dist/commands/ask.ts

ai auth

Update existing or add new OpenAI API Key

USAGE
  $ ai auth

DESCRIPTION
  Update existing or add new OpenAI API Key

EXAMPLES
  $ ai auth (Follow the prompt)

See code: dist/commands/auth.ts

ai autocomplete [SHELL]

display autocomplete installation instructions

USAGE
  $ ai autocomplete [SHELL] [-r]

ARGUMENTS
  SHELL  shell type

FLAGS
  -r, --refresh-cache  Refresh cache (ignores displaying instructions)

DESCRIPTION
  display autocomplete installation instructions

EXAMPLES
  $ ai autocomplete

  $ ai autocomplete bash

  $ ai autocomplete zsh

  $ ai autocomplete --refresh-cache

See code: @oclif/plugin-autocomplete

ai help [COMMAND]

Display help for ai.

USAGE
  $ ai help [COMMAND] [-n]

ARGUMENTS
  COMMAND  Command to show help for.

FLAGS
  -n, --nested-commands  Include all nested commands in the output.

DESCRIPTION
  Display help for ai.

See code: @oclif/plugin-help

ai model

Change model preference (default: gpt-3.5-turbo)

USAGE
  $ ai model

DESCRIPTION
  Change model preference (default: gpt-3.5-turbo)

EXAMPLES
  $ ai model (Follow the prompt)

See code: dist/commands/model.ts

ai update [CHANNEL]

update the ai CLI

USAGE
  $ ai update [CHANNEL] [-a] [-v <value> | -i] [--force]

FLAGS
  -a, --available        Install a specific version.
  -i, --interactive      Interactively select version to install. This is ignored if a channel is provided.
  -v, --version=<value>  Install a specific version.
  --force                Force a re-download of the requested version.

DESCRIPTION
  update the ai CLI

EXAMPLES
  Update to the stable channel:

    $ ai update stable

  Update to a specific version:

    $ ai update --version 1.0.0

  Interactively select version:

    $ ai update --interactive

  See available versions:

    $ ai update --available

See code: @oclif/plugin-update