AI Document Intelligence & Q&A System

This system helps users manage large amounts of documents and quickly find useful information from them using AI. Users can upload files such as PDFs, Word documents, Excel sheets, or CSV datasets. After upload, the system automatically extracts text, splits the content into searchable chunks, generates embeddings, and stores them in a vector database for semantic search.

At the same time, important entities and relationships are extracted from the documents and stored in Neo4j as a knowledge graph. This allows the system to understand not only similar text, but also how people, companies, topics, documents, and concepts are connected.

Once processing is complete, users can ask questions in natural language. The AI searches the vector database, checks related graph data from Neo4j, and generates a clear answer with source references from the original documents.

The dashboard also shows the status of document processing, vector database health, Neo4j graph database status, storage usage, and recent user activities.