We've partnered with Wey Gu to create the world’s most comprehensive short course on using LLMs with Knowledge Graphs. ✅ Key query techniques: text2cypher, graph RAG ✅ Automated KG construction ✅ vector db RAG vs. KG RAG All this content is contained in a single Colab notebook: https://lnkd.in/gJ3D5Kr6 There's also a full 1.5 hour video tutorial: https://lnkd.in/gDtzGwx5 It's a must watch if you're exploring how to use graph-based data structures in your LLM application!
How can one evaluate the quality and accuracy of the answers generated by LLMs and KGs? Is there a standard metric or benchmark that can be used to compare different LLMs and KGs? I would love to hear your thoughts on this topic.
no doubt that knowledge graphs and llms can be a powerful combination
Amit Keinan ...
Data Product Owner | AI Specialist | Cloud Architect | LLM | ggnicolau.medium.com | github.com/ggnicolau |
1yHi. What are the advantages and disadvantages about using KG RAG? I've been building vector db for storing and querying embeddings for some years now. I've used algorithms such as KDTree, Annoy, Faiss etc. Now that I'm building a RAG with GPT, I'm trying the newer ChromaDB. I've never thought about using knowledge graphs, I'm curious about it!