AI DEV SCRIPTS

Streamline Code Review, Commit & Speed Up Dev Process. Your Own Personal Senior Engineer For Free!

📍 Overview

AI DEV SCRIPTS, leverages Local LLMs to streamline code improvement workflows and enhance your coding. It includes scripts like ai_review for suggestion generation, ai_pr for pull request analysis, and ai_commit for suggested commit messages, ai_chat for full RAG compatible chat feature. Additionally, it features an ai_readme script that generates customized readmes based on directory locations. Overall, it utilizes Ollama's DeepSeek Coder, and Mistral model to automate code improvements, security checks, and documentation within the repository ecosystem.

🧩 Features

• AI Review: Scours through specified file formats and requests AI-generated suggestions for improvement.
• AI PR: Analyzes GitHub Pull Requests by calling an external Ollama DeepSeek Coder service.
• AI Commit: Generates commit messages using an AI model, adhering to conventional commit style and active voice guidelines.
• AI Readme: Generates customized readmes based on the repository's location, utilizing OpenAI's Ollama API and the Mistral model.
• AI Chat: Chat with websites, pdf, and markdown files, a RAG in your own terminal.
• AI Describe: Describe an image.

📦 Scripts

🚀 Getting Started

Requirements:

• Bash
• readmeai
• ollama
• deepseek-coder
• mistral

⚙️ Installation

1. Clone the repository:

git clone https://github.com/ikramhasan/AI-Dev-Scripts.git

2. Install the required dependencies:

pip install readmeai

3. Install ollama: Download the latest release from here

4. Install deepseek-coder:

ollama run deepseek-coder:6.7b-instruct

5. Install mistral:

ollama run mistral:7b-instruct

6. Make the scripts executable:

chmod +x ./ai_review

7. (Optional) Add the scripts to your PATH:

export PATH=$PATH:/path/to/AI-Dev-Scripts

🤖 Usage

ai_review

Navigate to the directory where you want to run the script and execute the command below:

$ ./ai_review file.py file.js # for specific files

Or,

$ ./ai_review *.py *.js # for all files with .py and .js extensions

ai_readme

Navigate to the directory where you want to generate the readme and run the command below:

$ ./ai_readme

ai_commit

Navigate to your repo and run ai_commit using the command below:

$ ./ai_commit

ai_pr

Copy the pr link and run the command below:

$ ./ai_pr <pr_link>

ai_chat

Navigate to the directory where you want to run the script and run the command below:

$ ./ai_chat -t md -f blog.md -q "What is this blog about?"

Or,

$ ./ai_chat -t pdf -f blog.pdf -q "What is this blog about?"

Or,

$ ./ai_chat -t web -f https://www.example.com -q "What is this blog about?"

ai_describe

Navigate to the directory of your image and run the command below:

$ ./ai_describe

Then follow the on-screen instructions.

openai

The script requires jq to be installed. Run the following command to install it.

brew install jq

After jq is installed, add the OPENAI_API_KEY variable to your path by running this command:

export OPENAI_API_KEY=your_openai_api_key

Then run the script using the command below:

$ ./openai <prompt>

Then follow the on-screen instructions.

🤝 Contributing

Contributions are welcome! Here are several ways you can contribute:

• Report Issues: Submit bugs found or log feature requests for the scripts project.
• Submit Pull Requests: Review open PRs, and submit your own PRs.

🎗 License

This project is protected under the MIT License.

🔗 Acknowledgments

• ollama
• readmeai
• Janlay Wu for the openai script

⭐ Star History

Return