Local LightRAG: A GraphRAG Alternative but Fully Local with Ollama

In this video, we explore how to set up and run LightRAG—a retrieval augmented generation (RAG) system that combines knowledge graphs with embedding-based retrieval—locally using OLLAMA. This video provides a step-by-step guide on cloning the repo, configuring local models like the Qwen2 LLM, adjusting context windows, and visualizing knowledge graphs generated from example data such as "A Christmas Carol" by Charles Dickens.


LINKS:
github.com/HKUDS/LightRAG
lightrag.github.io/
arxiv.org/pdf/2410.05779
microsoft.github.io/graphrag/
   • Graph RAG: Improving RAG with Knowled...  


💻 RAG Beyond Basics Course:
prompt-s-site.thinkific.com/courses/rag

Let's Connect:
🦾 Discord: discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: ko-fi.com/promptengineering
|🔴 Patreon: www.patreon.com/PromptEngineering
💼Consulting: calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: bit.ly/localGPT (use Code: PromptEngineering for 50% off).

Signup for Newsletter, localgpt:
tally.so/r/3y9bb0

TIMESTAMP
00:00 LightRAG with local models
01:38 Setup with Ollama
02:53 Serving Embeddings with Ollama
03:40 Changing the context window of the LLM
07:00 Configuring the Ingestion process
08:12 Advanced RAG Course
09:14 Indexing and Knowledge Graph Creation
10:45 Testing it out with local models


All Interesting Videos:
Everything LangChain:    • LangChain  

Everything LLM:    • Large Language Models  

Everything Midjourney:    • MidJourney Tutorials  

AI Image Generation:    • AI Image Generation Tutorials