Configure Enhanced SimpleRAG

Enter your API keys and settings to configure the system with Normal and Graph RAG support.

API Keys
Required for embeddings and Graph RAG entity extraction. Get a key from Google AI Studio.
Required if using Claude LLM. Get a key from Anthropic.
Required for vector database. Get a key from Qdrant Cloud.
URL of your Qdrant instance (e.g., https://your-instance.qdrant.io)
Neo4j Database Configuration
Enable to use Neo4j graph database for storing knowledge graphs
Connection URI for your Neo4j instance. Get from Neo4j Aura or your self-hosted instance.
Username for Neo4j authentication (default is usually 'neo4j')
Password for Neo4j authentication
ℹ️ Neo4j Setup Instructions:
  1. Create a free Neo4j Aura instance at neo4j.com/cloud/aura
  2. Copy the connection URI, username, and password from your instance details
  3. Enable Neo4j integration and enter the credentials above
  4. You can then use the "Neo4j Only" upload mode to store knowledge graphs
RAG Mode Settings
Fast, efficient, good for straightforward Q&A
Advanced reasoning, better for complex queries and relationships
Pure graph storage without vector embeddings, requires Neo4j configuration
LLM Settings
Advanced Settings
Size of text chunks in characters (500-5000 recommended).
Overlap between adjacent chunks (50-500 recommended).
Number of results to retrieve for each query (1-20).
Graph RAG Settings
Maximum entities to extract from each text chunk (5-50).
How many relationship hops to consider (1-5).
Threshold for merging similar entities (0.5-1.0).