Knowledge Graph Chatbot

A web application that combines a chatbot with Neo4j knowledge graph visualization capabilities.

Features

• Chat Interface: Ask questions in Vietnamese and get answers based on the knowledge graph
• Neo4j Explorer: Run Cypher queries directly against the Neo4j database and view results
• Schema Viewer: View the Neo4j database schema to understand the data structure

Requirements

• Python 3.8+
• Neo4j Database (local or cloud)
• HuggingFace API token for PhoGPT model

Installation

1. Clone the repository:

git clone <repository-url>
cd Graduate-project

2. Install dependencies:

pip install -r requirements.txt

3. Set up environment variables: Create a .env file in the root directory with the following content:

NEO4J_URI=your_neo4j_uri
NEO4J_USER=your_neo4j_username
NEO4J_PASSWORD=your_neo4j_password

Usage

1. Start the application:

python app.py

2. Open your browser and navigate to http://localhost:5000

3. Use the chat interface to ask questions in Vietnamese

4. Navigate to the Neo4j Explorer page to run Cypher queries

Project Structure

• app.py: Main Flask application
• neo4j_retriever.py: Neo4j query and retrieval functionality
• knowledge_graph.py: Knowledge graph integration with the chatbot
• Chat/chat.py: HuggingFace PhoGPT integration
• utils/: Utility functions for Neo4j, embedding, and reranking
• templates/: HTML templates for the web interface

License

MIT License