|
Download README.md from SyedTahir/STHASI-Generative-AI-Documentation-Generator: direct link, hf CLI and curl.
- Browser
- Download file 2.19 kB
-
https://huggingface.co/spaces/SyedTahir/STHASI-Generative-AI-Documentation-Generator/resolve/main/README.md
- Command line
-
hf download hf://spaces/SyedTahir/STHASI-Generative-AI-Documentation-Generator/README.md
-
curl -L -o README.md https://huggingface.co/spaces/SyedTahir/STHASI-Generative-AI-Documentation-Generator/resolve/main/README.md
2.19 kB
| title: STHASI Generative AI Documentation Generator | |
| emoji: ๐ | |
| colorFrom: purple | |
| colorTo: pink | |
| sdk: gradio | |
| sdk_version: 5.49.1 | |
| app_file: app.py | |
| pinned: false | |
| license: apache-2.0 | |
| # ๐ Generative AI Documentation Generator | |
| This is a [Hugging Face Space](link-to-your-space) that automatically generates technical documentation for Python codebases using the power of Large Language Models. | |
|  <!-- It's a good idea to add a screenshot once your app is running --> | |
| ## โจ Features | |
| - **Automated Documentation:** Simply provide a public GitHub repository URL, and the app will generate clear, concise documentation for each function and class. | |
| - **Modern UI/UX:** A clean, responsive interface built with Gradio, featuring a dark mode theme. | |
| - **Advanced - Ask Your Codebase:** An interactive chatbot that lets you ask natural language questions about the repository's code. | |
| - **Powered by CodeLlama:** Utilizes `codellama/CodeLlama-7b-Instruct-hf` for high-quality, code-aware text generation. | |
| ## ๐ ๏ธ How It Works | |
| 1. **Clone Repository:** The app clones the provided public GitHub repository into its temporary storage. | |
| 2. **Parse Code:** It intelligently parses Python files using Abstract Syntax Trees (`ast`) to identify functions and classes, which is more reliable than simple text matching. | |
| 3. **Generate Docs:** For each code element, it creates a detailed prompt and sends it to the CodeLlama model to generate a professional docstring, including purpose, parameters, return values, and usage examples. | |
| 4. **Chat with Code:** The "Ask Your Codebase" feature combines the entire codebase into a single context, allowing the LLM to answer specific questions about the project's logic and structure. | |
| ## ๐ How to Use | |
| 1. Open the **[Hugging Face Space](link-to-your-space)**. | |
| 2. In the "Documentation Generator" tab, enter the URL of a public GitHub repository containing Python code. | |
| 3. Click "Generate Docs" and wait for the process to complete. The status bar will show the current progress. | |
| 4. Switch to the "Ask Your Codebase" tab, ensure the URL is entered, and ask any question about the code! |