Upload Documents

Upload documents to index them using your preferred RAG mode.

Current Default RAG Mode: Normal RAG
You can override this setting for individual uploads below.
Supported formats: PDF, TXT, DOCX, HTML
⚠️ Graph RAG takes longer but provides richer context
📊 Extracts and stores knowledge graph in Neo4j without vector embeddings

Normal RAG Process

  1. Text extraction from document
  2. Split into overlapping chunks
  3. Generate embeddings for chunks
  4. Store in vector database

Graph RAG Process

  1. Text extraction from document
  2. Extract entities and relationships
  3. Build knowledge graph
  4. Generate embeddings for graph elements
  5. Store both chunks and graph in database

Note: Graph RAG processing takes significantly longer than Normal RAG due to entity extraction and relationship mapping, but provides much richer contextual understanding.