An AI-powered mobile library management system that combines Retrieval-Augmented Generation (RAG), Large Language Models (LLMs), and a Multi-Agent AI architecture to support intelligent event management, document-based question answering, and administrative decision-making through an interactive Streamlit application.
AI Mobile Library is an intelligent assistant designed to enhance the management of a mobile library platform by integrating modern AI technologies.
The system leverages Retrieval-Augmented Generation (RAG) to answer user questions based on uploaded documents, while a Multi-Agent workflow coordinates specialized AI agents responsible for request validation, conflict detection, planning support, and decision assistance. An interactive Streamlit interface enables users and administrators to access AI-powered services through a simple and intuitive dashboard.
- AI-powered event planning assistant
- Retrieval-Augmented Generation (RAG)
- Document-based question answering
- Multi-Agent AI workflow
- Intelligent request validation
- AI-assisted decision support
- Smart event booking and scheduling
- Event request management
- Administrative dashboard
- AI-generated planning insights
- Automatic conflict detection
- Interactive Streamlit interface
- Python
- Streamlit
- LangChain
- LangGraph
- DeepSeek API
- ChromaDB
- Sentence Transformers
- SQLite
- Pandas
- NumPy
- Requests
- Upload library documents.
- Split documents into semantic chunks.
- Generate vector embeddings.
- Store embeddings in ChromaDB.
- Retrieve the most relevant document chunks.
- Provide contextual information to the LLM through the RAG pipeline.
- Generate accurate responses based on retrieved knowledge.
- Coordinate planning and decision-making using multiple AI agents.
Project Demonstration
- The
docs/folder contains the knowledge base used by the RAG pipeline for indexing and document retrieval. - API keys and local configuration files are intentionally excluded from the repository.
Developed as an educational Artificial Intelligence project demonstrating Retrieval-Augmented Generation (RAG), Multi-Agent AI systems, and LLM-powered applications.