ViNNan is an intelligent medical chatbot system designed to assist users in diagnosing diseases and retrieving detailed medical information in Vietnamese. The system leverages advanced natural language processing (NLP) techniques, vector search, and machine learning models to provide accurate and context-aware responses. It supports multi-turn conversations and integrates with a structured medical knowledge base.
demo.mp4
- Disease Diagnosis: Analyze user symptoms and provide potential disease predictions.
- Medical Information Retrieval: Retrieve detailed information about diseases from a structured knowledge base.
- Context Management: Combine previous and current symptoms for accurate diagnosis when needed.
- Multi-Turn Conversations: Maintain context across multiple user interactions.
- Interactive User Interface: Built with Streamlit for real-time interaction.
🔹 Programming Language: Python
🔹 Frameworks: LangChain, Streamlit
🔹 Tools: Qdrant, OpenRouter API, BeautifulSoup
🔹 ML Libraries: HuggingFace Transformers, Cross-Encoder
- Python 3.8 or higher
- Virtual environment (recommended)
- Qdrant server (for vector search)
-
Clone the repository:
git clone https://github.com/your-username/vinnan-medical-chatbot.git cd vinnan-medical-chatbot -
Create and activate a virtual environment:
python -m venv env source env/bin/activate # On Windows: env\Scripts\activate
-
Install dependencies:
pip install -r requirements.txt
-
Set up environment variables:
- Create a
.envfile in the root directory and add the following:
OPENROUTER_API_KEY=your_openrouter_api_key QDRANT_URL=your_qdrant_url QDRANT_API_KEY=your_qdrant_api_key - Create a
-
Start the chatbot:
streamlit run src/interface.py
Developed by THUC TU
For any questions or feedback, please contact:
- Email: tuthucdz@gmail.com
- GitHub: Ne4nf