動画検索
関連広告
検索結果
Intro/NVIDIA GTC
Part 0: Resources and overview
Part 1: What is RAG? Why RAG? Why locally?
Why RAG?
What can RAG be used for?
Part 2: What we're going to build
Original Retrieval Augmented Generation paper
Part 3: Importing and processing a PDF document
Code starts! Importing a PDF and making it readable
Part 4: Preprocessing our text into chunks (text splitting)
Part 5: Embedding creation
Incredible embeddings resource by Vicky Boykis
Open-source embedding models
Creating our embedding model
Creating embeddings on CPU vs GPU
Creating a small semantic search pipeline
Showcasing the speed of vector search on GPUs
Part 7: Similarity measures between embedding vectors explained
Part 8: Functionizing our semantic search pipeline (retrieval)
Part 9: Getting a Large Langue Model (LLM) to run locally
Loading a LLM locally
Part 10: Generating text with our local LLM
Part 11: Augmenting our prompt with context items
Part 12: Functionizing our text generation step (putting it all together)
Leave a comment if there's any other videos you'd like to see!