Skip to main content

The ChatGPT command-line wrapper simplifies the execution of predetermined tasks through ChatGPT.

Project description

GPT Simplify Your Daily Workflow (gptW)

No longer is it necessary to manually input prompts and interact with ChatGPT.

With the GPTW tool, prompt operations are fully automated! Simplify your daily workflow.

Example

Translate

You can simply use the "ww" command without having to first instruct ChatGPT that the following task is a translation.

Translate to English:

$ ww e "今天天气怎么样"
How's the weather today?

Translate to Chinese:

$ ww c "who are you? "
你是谁?( shì shéi?)

Polish the Document

Polish a document with files as input.

ww d -f README.md

Code Review

$ ww r -f gptw/gptw.py
As an AI language model, I cannot run the code provided, but I can provide some feedback based on the code structure and syntax.

1. The code appears to be well-organized and follows the PEP 8 guidelines for Python code.

2. The argparse module is used to parse command-line arguments, which is a good practice for command-line applications.

...

Overall, the code seems to be well-written and organized, but could benefit from some additional security measures and error handling.

Ask

Ask ChatGPT directly:

$ ww a "who are you? "
I am an AI language model created by OpenAI.

Add Your Custom Prompt

Prepare your prompt and modify the gptw/config.json file following the existing format. Then, submit a PR or directly raise an issue to explain the command you want to add.

gtpw/config.json:

{
    "version": "v1.0.0",
    "cmds": {
        ## cmd to use
        "e": {
            ## replace with your prompt
            "prompt": "Please translate the following text into English, and polish it to make it sound more natural and in line with native speaker conventions. Please refrain from providing any additional output beyond the translated text",
            ## A simple explanation of what this prompt is used for
            "_comment": "Translate into English"
        },
        ...
    }
}

Currently, the following workflows are supported. You can run "ww -l" to obtain the available workflows.

$ ww --list
cmd | meaning                        | example
e   | Translate into English         | ww e 你好
c   | Translate into Chinese         | ww c how r u
p   | Polish sentence                | ww p hwo are you
a   | Just ask ChatGPT directly      | ww a who are you
d   | Polish document                | ww d -f README.md
r   | Code Review                    | ww r -f gptw/gptw.py
dic | Dictionary                     | ww dic dictionary

Installation

pip install --upgrade gptw

OpenAI Config

ww --config provider=openai
ww --config openai-model=gpt-3.5-turbo
ww --config openai-token={YOUR_TOKEN}

POE Config

ww --config provider=poe
ww --config poe-bot-name=chinchilla
ww --config poe-token={YOUR_TOKEN}

Bot names:

{'capybara': 'Sage', 'beaver': 'GPT-4', 'a2_2': 'Claude+', 'a2': 'Claude', 'chinchilla': 'ChatGPT', 'nutria': 'Dragonfly'}

Uninstall

pip uninstall gptw

Development

pip install tox
make test

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

gptw-0.2.0.tar.gz (9.6 kB view details)

Uploaded Source

Built Distribution

gptw-0.2.0-py3-none-any.whl (10.1 kB view details)

Uploaded Python 3

File details

Details for the file gptw-0.2.0.tar.gz.

File metadata

  • Download URL: gptw-0.2.0.tar.gz
  • Upload date:
  • Size: 9.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.16

File hashes

Hashes for gptw-0.2.0.tar.gz
Algorithm Hash digest
SHA256 1a11e3b7ba0569e9866ec0a7ca1e64e143340116f18e903334fc97e3f08cf806
MD5 a181ea7876ec0aca0d288a4ed5cf105e
BLAKE2b-256 3e74f84f96d3d6f06359b1772af09edbd752cd2d485f9e3edc3744366f868693

See more details on using hashes here.

File details

Details for the file gptw-0.2.0-py3-none-any.whl.

File metadata

  • Download URL: gptw-0.2.0-py3-none-any.whl
  • Upload date:
  • Size: 10.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.16

File hashes

Hashes for gptw-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 8173abda3f0d2b847180aaba0063a578ee70827216f05fd6ddc90f3add49fde5
MD5 08fbc943e75ae46414f90e99fa358bca
BLAKE2b-256 6c5770ea5d30e9fb05c982f0e65a7b39468c032c165524e1a511b49b013e3953

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page