Episode 27: Enhancing RAG based Gen AI Applications with Unstructured Data

Today we join Maria Khalusova, Staff Developer Advocate with Unstructured.IO, to discuss how companies can unlock their Unstructured Data to deliver better results from their Large Language Models. We talk about how Unstructured Data can enhance the performance of RAG applications, RAG vs Fine Tuning, data Chunking, Multi-Modal models and more. 

AWS Hosts: Nolan Chen & Malini Chatterjee

Unstructured Enterprise Platform beta signup: 

https://unstructured.io/platform

Embedding models MTEB Leaderboard: 

https://huggingface.co/spaces/mteb/leaderboard

2019 Deloitte report (source of the statistics that only 18% of organizations were using unstructured data):

https://www2.deloitte.com/us/en/insights/topics/analytics/insight-driven-organization.html

80% of data is unstructured, source: https://mitsloan.mit.edu/ideas-made-to-matter/tapping-power-unstructured-data

Papers showing RAG outperforming fine-tuning: 

https://arxiv.org/abs/2312.05934

https://arxiv.org/abs/2401.08406

Email Your Feedback: [e-mail]