From the course: Fundamentals of AI Engineering: Principles and Practical Applications
Join today to access over 25,300 courses taught by industry experts.
Efficient embedding generation
From the course: Fundamentals of AI Engineering: Principles and Practical Applications
Efficient embedding generation
- [Instructor] Welcome back. In our previous videos, we explored the embeddings ecosystem and different embeddings models. Today, we'll focus on generating embeddings efficiently, a critical scale for production AI systems. To get started, navigate to chapter_four and open the notebook 04_04.ipynb As always, in the upper right hand corner of your notebook, ensure you've selected the .VN virtual environment. When you move from experimenting with embeddings to deploying them in production, efficiency becomes critical. Two key strategies will help you optimize your embeddings pipeline. First, batching. Batching is generally the idea of processing multiple inputs together rather than one at a time. Second is caching. Caching involves storing previously generated embeddings to avoid having to regenerate them at runtime or regenerate them redundantly. These strategies can significantly improve the performance in production systems, especially ones that rely on embeddings. Now, these are…
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.