RMA-MUN/RAGNotebook

What it solves

RAG Notebook is an AI-powered personal knowledge management tool designed to prevent notes from becoming "isolated islands" of information. It solves the problem of users writing notes but never revisiting them by integrating note-taking with a knowledge graph and AI-driven retrieval and writing assistance.

How it works

The system combines a Markdown editor with a GraphRAG engine. It uses FastAPI and LangChain to process uploaded documents (PDF, DOCX, PPTX, etc.) and manual notes, extracting entities and relationships to build a knowledge graph in Neo4j. When a user asks a question, the system employs an Agentic RAG approach, using the knowledge graph to guide retrieval and fuse evidence for a grounded answer. It also features a hybrid search mechanism (Neo4j vector + full-text search) with RRF fusion and cloud-based reranking to ensure high-quality information retrieval.

Who it’s for

• Personal users who need an AI-enhanced way to manage their notes and knowledge bases.
• Developers looking to implement or study Agentic RAG and Knowledge Graph integrations.
• Job seekers wanting to showcase a practical AI knowledge management project on their resumes.

Highlights

• GraphRAG Integration: Uses Neo4j to store entities and relationships, allowing the AI to navigate the graph for more comprehensive answers.
• AI Writing Assistant: Provides real-time inline completion, expansion, summarization, and cross-source related note recommendations.
• Intelligent Tagging: Automatically generates tags and categories for notes using an LLM asynchronously.
• Spaced Repetition: Implements the Ebbinghaus forgetting curve algorithm to help users review and retain information.
• Multi-format Support: Handles TXT, PDF, MD, PPTX, and DOCX files for knowledge base construction.