Summary

WHartTest is an AI-driven test automation platform built using Django REST Framework, designed to automate the generation and management of test cases from requirements. It targets testing teams seeking to improve efficiency and test coverage by leveraging large language models (LLMs) and knowledge retrieval techniques. The platform aims to streamline the process from requirement analysis to executable test case creation.

How It Works

The system integrates Natural Language Understanding (NLU), knowledge base retrieval, and embedding search capabilities. It utilizes frameworks like LangChain and the Model Context Protocol (MCP) for tool invocation and LLM interaction. By processing requirements and querying integrated knowledge bases, WHartTest automatically generates test cases, supporting various embedding services such as OpenAI, Azure OpenAI, and Ollama for flexibility.

Quick Start & Requirements

Docker deployment is recommended for ease of use.

1. Clone the repository: git clone https://github.com/MGdaasLab/WHartTest.git
2. Navigate into the directory: cd WHartTest
3. Copy the example environment file: cp .env.example .env
4. Start the services: docker-compose up -d Access the frontend at http://localhost:8913 and the admin interface at http://localhost:8912/admin (default credentials: admin/admin123456). Docker is the primary prerequisite.

Highlighted Details

• Automated test case generation from natural language requirements using LLMs.
• Integrated knowledge base management and document understanding features.
• Support for multiple LLM and embedding providers (OpenAI, Azure OpenAI, Ollama).
• Built on Django REST Framework, offering a structured backend API.

Maintenance & Community

Users can contact the developers by submitting GitHub Issues or participating in the project discussion forum. Contribution guidelines are available within the repository.

Licensing & Compatibility

The provided README does not specify a software license. This omission requires clarification regarding usage rights, modification permissions, and distribution terms, particularly for commercial applications.

Limitations & Caveats

The default API keys and admin credentials generated during the Docker setup are insecure and must be replaced with new, secure keys before use in a production environment. The project appears to be actively developed, but specific details on stability or long-term maintenance commitments are not provided.