Transform natural language queries into Cypher using LLMs and build intelligent knowledge graph applications.

This project demonstrates how to build an intelligent query system combining Large Language Models (LLM), Retrieval-Augmented Generation (RAG), an

d Knowledge Graphs using Neo4j. Perfect for developers and data scientists looking to build natural language interfaces for graph databases.

• 🤖 Natural Language to Cypher query conversion using fine-tuned BART
• 📊 Automated data ingestion and categorization pipeline
• 🎯 Knowledge Graph creation and management
• 🔍 Intelligent query processing and retrieval
• 🎓 Educational examples using organizational data

1. employees.csv: Sample organizational dataset
2. sync.py: Data ingestion and Neo4j graph population script
3. train-bart.py: LLM training pipeline for natural language to Cypher conversion
4. neo4j_client.py: Neo4j interaction and query processing interface

pip install -r requirements.txt

1. Set up Neo4j database
2. Update connection settings in neo4j_client.py
3. Run data ingestion:

   python sync.py

4. Train the model:

   python train-bart.py

• 🏢 Enterprise Knowledge Management
• 👥 HR Analytics and Organizational Insights
• 📊 Data Discovery and Exploration
• 🤖 Conversational AI Interfaces
• 🎯 Intelligent Search Systems

LLM RAG Neo4j Knowledge Graphs Natural Language Processing BART Fine-tuning Graph Database Cypher Transformers Enterprise Data HR Analytics Python Machine Learning AI Data Engineering Information Retrieval Semantic Search Data Science Graph AI

This project serves as a practical example of:

• Building LLM-powered applications
• Implementing RAG systems
• Working with Knowledge Graphs
• Natural Language Understanding
• Enterprise Data Management

Contributions are welcome! Please feel free to submit a Pull Request.

This project is licensed under the MIT License - see the LICENSE file for details.

• LangChain
• Neo4j Graph Data Science
• Hugging Face Transformers