Welcome to the world of coding efficiency, where the command line meets the power of AI! In this blog, we’ll guide you through using Promptr, a Command Line Interface (CLI) tool that enables you to fluently instruct OpenAI’s large language models (LLM) using plain English to make changes in your codebase. Ready to transform how you manage your code? Let’s dive in!

Getting Started with Promptr

Promptr allows you to execute specific changes in your code by simply crafting a clear instruction file. Below is how you can get started:

• Commit any changes in your codebase to maintain a clean working area.
• Write your specific instructions in a prompt file (e.g., my_prompt.txt), ensuring it includes relative paths to the files you want to modify.
• Run Promptr with the following command:

promptr -p my_prompt.txt

Once executed, Promptr will directly apply the AI-generated changes to your specified files. You can use your favored git UI to review the results.

Examples of What You Can Achieve

Promptr can work wonders in your codebase! Here are some example pull requests showcasing its capabilities:

• Pull Request 38
• Pull Request 41

Utilizing Templating with LiquidJS

Promptr supports templating with LiquidJS, which brings flexibility and reusability to your prompts. By incorporating reusable snippets of code or instructions within your prompt files, you can standardize modifications across various projects effectively.

Including Reusable Snippets

Using the render function, you can embed common standards in your prompt files. Imagine your coding standards summarized in an include file named _project.liquid:

liquid
This project uses Node version 18.
Use yarn for dependency management.
Use import not require in Javascript.
Don’t include module.exports at the bottom of Javascript classes.
Alphabetize method names and variable declarations.

In your prompt file, you would include it like this:

liquid
% render _project.liquid % your prompt here

Use Cases

Here are some practical applications for templating in Promptr:

• Create a file outlining coding standards to include in every new code file.
• Develop reusable boilerplate snippets for various application components.
• Maintain guidelines for specific tasks within relevant prompt files.

Options You Can Use with Promptr

Promptr offers various options to tailor your use, such as:

• -p, –prompt: Path to your prompt file.
• -m, –model: Specify your desired model.
• -d, –dry-run: Verify your command without applying changes.
• -i, –interactive: Enables interactive input.
• -v, –verbose: Provides detailed execution logs.

Troubleshooting Tips

If you encounter issues while using Promptr, consider the following troubleshooting steps:

• Ensure your OpenAI API key is correctly set in your environment variables.
• Confirm that your file paths in the prompt are accurate and relevant to the task.
• Run Promptr in dry-run mode to view the proposed changes before applying them.
• If your prompt doesn’t behave as expected, verify that it is specific and clear.
• For more insights, updates, or to collaborate on AI development projects, stay connected with fxis.ai.

Installation Guide

Follow these steps to install Promptr:

• With yarn: yarn global add @ifnotnowwhen/promptr
• With npm: npm install -g @ifnotnowwhen/promptr
• You can also install it with recent binaries, currently supporting MacOS.

Conclusion

At fxis.ai, we believe that such advancements are crucial for the future of AI, as they enable more comprehensive and effective solutions. Our team is continually exploring new methodologies to push the envelope in artificial intelligence, ensuring that our clients benefit from the latest technological innovations.

Now that you have the inside scoop on how to use Promptr, you’re all set to transform your coding workflow with AI! Happy coding!