Vector embedding AI in production systems
Modern AI solutions are based on mapping the objects of interest into a vector space to make inferences. This is the basis for recommendation and personalization systems, modern text search and question answering, and natural language based AI’s such as BERT and GPT-3. However, applying these techniques in online production systems can be challenging. In this talk we’ll see through real-world examples how you can accomplish this at scale, using open source platforms and without a big budget.