RAGent is an AI-powered research assistant designed for users who need to query and synthesize information from uploaded documents and the web. It aims to provide comprehensive answers by integrating Retrieval-Augmented Generation (RAG) with external API capabilities and a user-friendly Streamlit interface.

How It Works

The system processes uploaded PDF documents by initializing a vector store for efficient retrieval. User queries are handled by AI models, which can augment responses with web search results via API integrations. A key feature is the "Dry Run Mode," which simulates API calls and database operations with mock data, enabling testing and development without incurring costs or side effects.

Quick Start & Requirements

• Install: pip install -r requirements.txt
• Prerequisites: Requires API keys for backend services (e.g., Claude, Tavily) configured via a .env file.
• Usage: Run streamlit run streamlit_app.py.
• Documentation: https://github.com/alonlavian/RAGent

Highlighted Details

• Integrates RAG with AI agents and external APIs (e.g., Claude, Tavily).
• Supports PDF uploads for document-based querying.
• Includes a "Dry Run Mode" for testing without live API calls.
• Built with a Streamlit frontend for an interactive user experience.

Maintenance & Community

Contributions are welcome via pull requests. Further community or maintenance details are not specified in the README.

Licensing & Compatibility

Licensed under the MIT License, permitting commercial use and integration with closed-source projects.

Limitations & Caveats

The project's functionality is dependent on the availability and configuration of external API keys. The README does not detail specific performance benchmarks or known limitations beyond the dry run mode's purpose.