{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/e85fb1962ff040bdb999863bc3c44081\" frameborder=\"0\" width=\"1664\" height=\"1248\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1248,"width":1664,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1248,"thumbnail_width":1664,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/e85fb1962ff040bdb999863bc3c44081-41d1d19371fa3141.gif","duration":4146.3389,"title":"Understanding Machine Learning: Embeddings, Retrieval, and Re-Ranking 🤖","description":"In this video, I walk you through the process of using Sentence Transformers for machine learning, specifically focusing on embedding and retrieval techniques. I explain the differences between a neural re-ranker and a cross-encoder, highlighting how they score relevance versus similarity. We also discuss the importance of query expansion and how embeddings are stored in a vector database like pgVector. I encourage you to experiment with the provided notebooks and run the models to see the results for yourself. Please feel free to reach out with any questions as you work through this material."}