How RAG Finds Answers in Millions of Documents | Embeddings, Vector Databases, LangChain & Supabase
Автор: Venelin Valkov
Загружено: 2025-08-01
Просмотров: 1095
Transform your text documents into a searchable knowledge base that AI can understand. You'll learn how to build semantic search that understands meaning, scales to millions of documents, and powers real-world RAG applications.
Embeddings leaderboard: https://huggingface.co/spaces/mteb/le...
Why vector databases are a scam: https://simon-frey.com/blog/why-vecto...
Supabase: https://supabase.com/
AI Bootcamp: https://www.mlexpert.io/
LinkedIn: / venelin-valkov
Follow me on X: / venelin_valkov
Discord: / discord
Subscribe: http://bit.ly/venelin-subscribe
GitHub repository: https://github.com/curiousily/AI-Boot...
👍 Don't Forget to Like, Comment, and Subscribe for More Tutorials!
00:00 - What are Embeddings?
02:00 - Toy example
05:56 - Using pre-trained embedding model with LangChain
09:28 - How to choose embedding model
11:01 - Do you need a vector database?
12:45 - Supabase install and setup
15:16 - Use Supabase vectors with LangChain
18:47 - Metadata filtering
20:22 - Conclusion
Join this channel to get access to the perks and support my work:
/ @venelin_valkov
Доступные форматы для скачивания:
Скачать видео mp4
-
Информация по загрузке:
