RAG From Scratch: Part 3 (Retrieval)

This is the third video in our series on RAG. The aim of this series is to build up an understanding of RAG from scratch, starting with the basics of indexing, retrieval, and generation. This video focuses on retrieval, covering the process of document search using an index.
Code:
github.com/langchain-ai/rag-f...
Slides:
docs.google.com/presentation/...

[@gnkbhuvan]

Really great explanation sir. Great work from langchain team.

[@mr.daniish]

Lance is the man! love these small bites of gold.

[@bqmac43]

Excellent explanations, Lance! I'm looking forward to the remaining videos.

[@noordin85]

Awesome explanation to the basics

[@Learn-it-all-Do-it-all]

Many thanks Lance for this, a great service for the community. In the example, does get_relevant_documents embed the query internally before running the search?

[@Orcrambo]

Yep, when you create the vector store you input the embedding strategy

[@Learn-it-all-Do-it-all]

Thanks @Orcrambo.

[@jzam5426]

Thank you! With CSVLoaders a document has both "page_content" and "metadata." Do both get embedded, or only page_content? If page_content alone, does the retriever uses natively (without add instructions) metadata as well?

[@zishanahmedshaikh]

First