Oct 4, 2023
Hi Stefano. We don’t have to create embedding an every time. Typically we create it and store in a vectorDB. After that we can use that to retrieve augment queries to LLM.
Hi Stefano. We don’t have to create embedding an every time. Typically we create it and store in a vectorDB. After that we can use that to retrieve augment queries to LLM.
IBM Fellow, Master Inventor, Mobile, RPi & Cloud Architect & Full-Stack Programmer