pr-pilot-cli 1.3.2

CLI for PR Pilot, a text-to-task automation platform for Github.

Install | Documentation | Blog | Website

PR Pilot CLI

PR Pilot gives you a natural language interface for your Github projects. Given a prompt, it uses LLMs (Large Language Models) to autonomously fulfill tasks by interacting with your code base and Github issues.

Using templates, you can create powerful, reusable commands that can be executed by PR Pilot. Here is how it works:

Write a template file:

Take a look at our test results:

---
{{ sh('pytest') }}
---

Understand why the tests are failing by reading the relevant code files. 
Give a short, concise, structured analysis of the test results.

Execute the file:

pilot -f analyze_test_results.md.jinja2

For more examples, check out the prompts directory in this repository.

Installation

Make sure you have PR Pilot installed in your repository

To install the CLI, run the following command:

pip install --upgrade pr-pilot-cli

By default, the CLI will prompt you to input your API key if it is not already configured.

Usage

After installation, open a terminal and ls into a repository you have installed PR Pilot in and talk to PR Pilot:

Examples

Translate a file:

pilot --raw "translate the README into German" > README_German.md

Let it write some unit tests:

pilot "Write some unit tests for the utils.py file."

Find some information in your Github issues:

pilot "Do we have any open Github issues regarding the AuthenticationView class?"

For more information, check out our User Guide.

Options and Parameters

You can change the default settings with parameters and options:

Usage: pilot [OPTIONS] [PROMPT]...

Options:
  --wait / --no-wait  Wait for the result.
  --repo TEXT         Github repository in the format owner/repo.
  --chatty            Print more information.
  --raw               For piping. No pretty-print, no status indicator.
  --code              Disable formatting, enable RAW mode, use GPT-4 model.
  -f, --file PATH     Load prompt from a template file.
  --direct            Do not use the rendered template as a prompt for PR
                      Pilot, but render it directly as output.
  -o, --output PATH   Output file for the result.
  --model TEXT        GPT model to use.
  --debug             Display debug information.
  --help              Show this message and exit.

Features

• Configuration Management: Automatically manages API key configuration by prompting the user to input their API key if not already configured.
• Task Creation: Users can create tasks by specifying a repository and a prompt. The CLI handles task creation and optionally waits for the result.
• Result Retrieval: If the --wait option is used, the CLI waits for the task to complete and displays the result directly in the terminal.
• Dashboard Link: For tasks that are not awaited, the CLI provides a link to the task's dashboard for further monitoring.

Configuration

The configuration file is located at ~/.pr-pilot.yaml.

Contributing

Contributors are welcome to improve the CLI by submitting pull requests or reporting issues. For more details, check the project's GitHub repository.

License

The PR Pilot CLI is open-source software licensed under the GPL-3 license.