This repository contains example implementations of different RAG (Retrieval-Augmented Generation) approaches using LlamaIndex.
Source code for the article GraphRAG vs. Baseline RAG: Solving Multi-Hop Reasoning in LLMs
This example demonstrates how to implement GraphRAG, an advanced RAG approach that excels at multi-hop reasoning tasks
Source code for the article Building a custom RAG pipeline with LlamaIndex and Llama3.2
This example shows how to build a custom RAG pipeline using LlamaIndex with Llama 3.2.
- If you're interested in handling complex, multi-hop queries that require connecting information from multiple sources, check out the GraphRAG Example.
- If you're looking to build a straightforward RAG system with vector embeddings, or specifically want to use Groq's LLM, check out the Simple Vector Index Example.