Learn to build large language model applications: vector databases, langchain, fine tuning and prompt engineering. Learn more

Advanced Considerations in RAG Performance


We will delve into the concepts of chunking, embedding models, and vector databases. Following that, we’ll explore various examples showcasing diverse chunking strategies and conduct comparisons between different embedding approaches.

Key takeaways:
– Your data structure has a huge influence on the right chunking strategy
– The way you expect users to use your app also affects your chunking strategy
– There are many ways to store embeddings, and the way you store them is dependent on your use case

Yuijian Tang
Yujian Tang

Developer Advocate at Zilliz

Yujian Tang is an open source and bubble tea enthusiast. He started his career at IBM in 2013 before attending college in 2015 where he worked on machine learning research. Yujian published two first author papers including one to IEEE Big Data. After college, he worked on the AutoML system at Amazon, generating over 2.5M in revenue before leaving to work in startups. Since then, he has written over 400 blog posts, made over 100 videos, and reached over 250k software devs with his content.

We are looking for passionate people willing to cultivate and inspire the next generation of leaders in tech, business, and data science. If you are one of them get in touch with us!