Completed
How do we construct multi-modal embeddings
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Supercharge eCommerce Search - OpenAI's CLIP, BM25, and Python
Automatically move to the next video in the Classroom when playback concludes
- 1 Multi-modal hybrid search
- 2 Multi-modal hybrid search in e-commerce
- 3 How do we construct multi-modal embeddings
- 4 Difference between sparse and dense vectors
- 5 E-commerce search in Python
- 6 Connect to Pinecone vector db
- 7 Creating a Pinecone index
- 8 Data preparation
- 9 Creating BM25 sparse vectors
- 10 Creating dense vectors with sentence transformers
- 11 Indexing everything in Pinecone
- 12 Making hybrid queries
- 13 Mixing dense vs sparse with alpha
- 14 Adding product metadata filtering
- 15 Final thoughts on search
