Graph RAG

Graph-based retrieval augmented generation

Graph RAG

Graph RAG combines knowledge graphs with retrieval augmented generation for complex queries.

Quick Start

typescript

import { createGraphRAG, GraphStore } from 'praisonai';

const graphRag = createGraphRAG({
  llm: 'openai/gpt-4o-mini',
  graphStore: new GraphStore()
});

// Add documents
await graphRag.addDocument('TypeScript is a typed superset of JavaScript.');

// Query with graph context
const result = await graphRag.query('What is TypeScript?');

Configuration

typescript

interface GraphRAGConfig {
  llm?: string;
  graphStore: GraphStore;
  verbose?: boolean;
}

Capabilities

Build knowledge graphs from documents
Query relationships between entities
Combine graph traversal with vector search
Extract entities and relationships
Support complex multi-hop queries

CLI Usage

bash

praisonai-ts graph-rag info --json