Learn Embeddings and Vector Databases

Learn how to improve the accuracy and reliability of LLM-based apps by implementing Retrieval-augmented Generation (RAG) using embeddings and a vector database.

• What is an embedding?
• Setting up a vector database
• Supabase & pgvector
• Semantic search
• Similarity search
• Chunking text documents
• RAG

• Learn Embeddings and Vector Databases
• 1. Your next big step in AI engineering
• 2. What are embeddings?
• 3. Set up environment variables
• 4. Create an embedding
• 5. Challenge: Pair text with embedding
• 6. Vector databases
• 7. Set up your vector database with Supabase
• 8. Store vector embeddings
• 9. Semantic search
• 10. Query embeddings using similarity search
• 11. Create a conversational response using OpenAI
• 12. Chunking text from documents
• 13. Challenge: Split text, get vectors, insert into Supabase
• 14. Error handling
• 15. Query database and manage multiple matches
• 16. AI chatbot proof of concept
• 17. Retrieval-augmented generation (RAG)
• 18. Solo Project: PopChoice
• 19. You made it to the finish line!