Loading video player...
Complete tutorial and source code (requires MLExpert Pro): https://www.mlexpert.io/academy/v2/context-engineering/embeddings-and-vector-databases Simple keyword is not enough for your RAG. If a user asks for "money" but your documents say "revenue," traditional search fails. In this tutorial, we'll build the storage layer of a production-grade RAG system using Vector Embeddings. We will move beyond simple TF-IDF and implement Semantic Search using local open-source models (Qwen3 Embedding), PostgreSQL, and pgvector via Supabase. Qwen3 Embedding: https://qwenlm.github.io/blog/qwen3-embedding/ Supabase: https://github.com/supabase/supabase HNSW index: https://github.com/pgvector/pgvector?tab=readme-ov-file#hnsw AI Academy: https://www.mlexpert.io/ LinkedIn: https://www.linkedin.com/in/venelin-valkov/ Follow me on X: https://twitter.com/venelin_valkov Discord: https://discord.gg/UaNPxVD6tv Subscribe: http://bit.ly/venelin-subscribe GitHub repository: https://github.com/curiousily/AI-Bootcamp š Don't Forget to Like, Comment, and Subscribe for More Tutorials! 00:00 - How to store your chunks? 01:06 - What are Vector Embeddings? 03:16 - Local Postgres & pgvector setup 06:31 - Initializing Supabase & Docker 07:17 - Generating Embeddings with Ollama and Qwen3 Embedding 09:00 - Storing Data: Inserting Vectors into SQL 09:45 - Full-Text Search Limitations 10:27 - Vector Semantic Search Success 11:30 - Why you need persistence and what's next Join this channel to get access to the perks and support my work: https://www.youtube.com/channel/UCoW_WzQNJVAjxo4osNAxd_g/join