Colab: https://drp.li/XnRSF

My Links:
Twitter - https://twitter.com/Sam_Witteveen
Linkedin - https://www.linkedin.com/in/samwitteveen/

Github:
https://github.com/samwit/langchain-tutorials (updated)
https://github.com/samwit/llm-tutorials

00:00 Intro
00:10 Precise Zero Shot Dense Retrieval Paper
00:43 Precise Zero Shot Dense Retrieval Paper Diagram
01:29 McDonalds Example
04:13 Code Time

Sam Witteveen AI is a publication offering insights, tutorials, and resources for artificial intelligence (AI) enthusiasts and practitioners. Readers can learn about machine learning algorithms, deep learning frameworks, and AI applications. With tutorials, case studies, and expert interviews, Sam Witteveen AI provides  guidance and expertise for building and deploying AI solutions.

Sam Witteveen

The post discusses the concept of hypothetical document embeddings (HyDE) and how it can be used to improve search systems. HyDE allows a large language model to generate hypothetical answers, which can then be used for embedding-based search. It is a powerful technique that can be effective in certain situations but may not work well for topics the language model has no knowledge of.

Advanced RAG 05 - HyDE - Hypothetical Document Embeddings