Intro to GraphRAG

In this presentation, you'll gain an understanding of GraphRAG, a technique that enhances document analysis and question-and-answer performance by leveraging large language models (LLMs) to create knowledge graphs. We'll explore how GraphRAG builds upon Retrieval-Augmented Generation (RAG) by using knowledge graphs instead of vector similarity for retrieval. You'll learn how to set up the environment, prepare data, and implement GraphRAG using LangChain, with practical code examples. Additionally, we'll explore some advanced features and customization options available in LangChain to optimize and tailor GraphRAG to your specific needs.
Presented by John Alexander, Content Developer and Apurva Mody, Principal Program Manager
** Part of RAGHack, a free global hackathon to develop RAG applications. Join at aka.ms/raghack **
*📌 [Check out the RAGHack 2024 series here!](aka.ms/RAGHack...
#MicrosoftReactor #RAGHack
[eventID:23432]

[@peezyplayz4172]

Awesome 😎

[@swanandbagve4589]

does this support both structured and unstructured data together ?

[@gopikapurnima-qb4iu]

does this support both structured data

[@nispeter222]

Are this the same techniques as in the paper From Local to Global: A Graph RAG Approach to
Query-Focused Summarization?

[@kk008]

Does this support Knowledge graph as input ?!

[@Anonymous-bu9ch]

Can we get the colab?

[@lordshifu]

incorrect code ignore tutorial