Graphrag-UI is designed to help users interact with complex datasets and perform sophisticated rag searches using various AI-powered techniques, including Graph RAG and traditional RAG approaches.

🖇️ Repository   •   📙 Documentation

🧠 GRAPHRAG UI Assistant

Graphrag-UI is a cutting-edge tool that integrates AI capabilities into your rag analysis process. It leverages both Graph RAG and traditional RAG techniques to offer enhanced retrieval and generation capabilities. Graphrag-UI provides global and local search modes, file management, and indexing capabilities, all through a Streamlit-based user interface.

🌟 Features

🔍 Advanced retrieval	Using Graph RAG and traditional RAG
🌐 Global and local search modes	For comprehensive data exploration
🤖 Integration with OpenAI	Leverages OpenAI's language models
📂 File management	Efficient file management and indexing capabilities
🖥️ Streamlit-based UI	User-friendly interface for seamless interaction
⚙️ Customizable search parameters	Tailor search parameters to fit specific needs

Graph RAG Advantages

Graphrag-UI incorporates Graph RAG, a superior technique for retrieval that offers several benefits over traditional RAG:

• Enhanced context understanding: Graph RAG leverages knowledge graphs to capture complex relationships between entities, providing more accurate and contextually rich answers.
• Improved handling of structured and unstructured data: It excels at representing and retrieving heterogeneous and interconnected information.
• Better performance in domain-specific queries: Graph RAG addresses limitations of generic embedding models in company-specific knowledge retrieval.

🚀 Quick Start ⌨️

1. Clone the repository:

   git clone https://github.com/shahshrey/Graphrag-UI.git
   cd Graphrag-UI

2. Create a virtual environment and activate it:

   python -m venv venv
   source venv/bin/activate  # On Windows, use venv\Scripts\activate

3. Install the required dependencies:

   pip install -r requirements.txt

4. Set up your environment variables:

   • Copy the .env.example file to .env
   • Fill in your API keys and other configuration values

5. Run the Streamlit app:

   streamlit run main.py

6. Open your web browser and navigate to the URL provided by Streamlit (usually http://localhost:8501)

7. Use the sidebar to configure Graphrag-UI and upload your documents

8. Ask questions and interact with Graphrag-UI through the main interface, leveraging both Graph RAG and traditional RAG capabilities for comprehensive information retrieval

🗂️ Project Structure

• src/: Contains the main application code
• tests/: Contains test files (to be implemented)
• docs/: Contains additional documentation
• main.py: The entry point of the application
• requirements.txt: Lists all Python dependencies
• .env.example: Template for environment variables

🤝 Contributing

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

📄 License

This project is licensed under the MIT License.