Graph RAG

Graph RAG builds a knowledge graph from your documents, extracting entities and relationships. It uses community detection to group related concepts, enabling complex multi-hop reasoning that vector search alone cannot achieve.

How it Works

1. Extraction: Entities (people, organizations, concepts) and relationships are extracted from documents
2. Graph Building: A knowledge graph connects all entities across your document collection
3. Community Detection: Related entities are grouped into communities with auto-generated summaries
4. Query Time: Queries leverage both graph structure and community context

RAG Wizard Configuration

Step 1: Project Setup

• Domain: Best for complex domains with many interconnections
• Use Case: "Research", "Knowledge Discovery", or "Document Analysis"

Step 2: Data Sources

Graph RAG shines with document collections that reference each other:

• Research papers with citations
• Legal documents with cross-references
• Technical documentation with dependencies
• Business policies with interconnected rules

Step 3: Document Processing

Step 4: Pipeline Configuration

Graph-Specific Settings

Step 5: API Endpoints

Generate your API key and integrate using REST API, Python SDK, or MCP Protocol:

curl -X POST "https://api.guidedmind.ai/rag/search" \
-H "X-API-Key: rk_your_key_here" \
-H "Content-Type: application/json" \
-d '{
  "query": "How does the expense policy relate to travel approval?",
  "options": {
    "limit": 5,
    "threshold": 0.5,
    "search_method": "graph"
  }
}'

Visualizing Your Graph

After processing, access the Graph Editor from your project dashboard to:

• Explore entity relationships visually
• Browse communities and their summaries
• Filter by entity type or relationship
• Export graph data

When to Use Graph RAG

Performance Considerations

Comparison with Other RAG Types