Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/blacksujit/testcraftai
This project provides a web-based interface to generate test instructions using Visual Question Answering (VQA). Upload screenshots or images, provide an optional context, and let the model do the rest!
https://github.com/blacksujit/testcraftai
llm llmtuner multimodel task-runner test-automation
Last synced: about 1 month ago
JSON representation
This project provides a web-based interface to generate test instructions using Visual Question Answering (VQA). Upload screenshots or images, provide an optional context, and let the model do the rest!
- Host: GitHub
- URL: https://github.com/blacksujit/testcraftai
- Owner: Blacksujit
- Created: 2024-09-09T12:43:14.000Z (4 months ago)
- Default Branch: main
- Last Pushed: 2024-10-26T18:46:44.000Z (2 months ago)
- Last Synced: 2024-10-26T20:35:54.046Z (2 months ago)
- Topics: llm, llmtuner, multimodel, task-runner, test-automation
- Language: Python
- Homepage:
- Size: 192 KB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# 🧪 TestCraftAI:
## Automated Test Instruction Generator
  
### Problem statement :
Generate automated test instructions for your software or application features using images and optional context with the power of Hugging Face's ViLT model!
## 📋 Project Overview
This project provides a web-based interface to generate test instructions using Visual Question Answering (VQA). Upload screenshots or images, provide an optional context, and let the model do the rest!
## 🚀 Features
- **Visual Question Answering:** Automatically generate test instructions based on uploaded images.
- **Context-Aware:** Include optional text context to refine the instructions.
- **Dynamic Interface:** Simple and user-friendly web interface for easy interaction.
- **Scalable:** Easily extendable with more models or features.
## 🏗️ Project Structure
```
├── app/
│ ├── app.py # Main Flask application
│ ├── uploads/ # Directory for uploaded images
│ └── utils/
│ └── llm.py # LLM utilities (model inference functions)
├── templates/
│ └── index.html # HTML template for the web form
├── static/
│ └── css/
│ └── styles.css # Custom CSS for styling
├── README.md # Project documentation
├── requirements.txt # Python dependencies
└── .gitignore # Files and directories to ignore in Git
```
# Project View :
## ⚙️ Setup Instructions:
### Prerequisites:
1.) Python 3.7+: Ensure you have Python installed.
2.) Pip: Make sure pip is installed to manage dependencies.
## Installation:
1. Clone the Repository:
```
git clone https://github.com/Blacksujit/TestCraftAI.git
```
```
cd app
```
2. Create a Virtual Environment:
```
python -m venv venv
```
```
On Windows: venv\Scripts\activate
```
3. Install Dependencies:
```
pip install -r requirements.txt
```
4. Download the Model:
```
transformers-cli download dandelin/vilt-b32-finetuned-vqa
```
5. Run the Application:
```
python app.py
```
6. Access the Application:
Open your web browser and go to: http://127.0.0.1:5000
## 🖥️ Usage:
1.) Upload Images: Click on the upload button and select the images/screenshots you want to use for generating test instructions.
2.) Add Context: (Optional) Provide context to make the instructions more specific.
3.) Generate Instructions: Click the "Generate" button to receive your test instructions.
## 🛠️ Development:
Feel free to contribute by forking the repository, making changes, and submitting a pull request!
## To Do:
1.) Add support for multiple languages.
2.) Integrate more advanced models.
3.) Improve UI/UX for better interaction.
## 📝 Contributing:
Contributions are welcome! Please read the CONTRIBUTING.md for more details.
## 📜 License:
This project is licensed under the MIT License - see the LICENSE file for details.
## 🙏 Acknowledgements:
1.) **Hugging Face for the ViLT model**.
2.) **Flask for providing the web framework.**
3.) **Community contributors for their continuous support.**
### Empowering test automation with AI 🌟