Word/token meanings are embedded in high dimensional space from different embedding models, but projected down to 3D, we can get a sense of how they are stored.
Fly through a 3D visualization of open source texts stored in a vector database.
I used this to demonstrate a portion of the RAG process. (After chunking and embedding, and before relevant text are searched for.)
Good things to watch out for, but also watch out for project or program running the show. For example, project sees it as a piece of work to churn, and program is trying to execute a multitude of projects.
Someone has got to care about the user and the business.
It can be much worse with a project manager who doesnt care about the user, doesnt care about the business and is just trying to complete tasks per sprint without any focus. It is even worse when the project or program manager has no technical background and doesnt understand what it takes to build something.
In each role, product, project, program, and all the other lead roles (technical), it takes people who really care.
Fly through a 3D visualization of open source texts stored in a vector database.
I used this to demonstrate a portion of the RAG process. (After chunking and embedding, and before relevant text are searched for.)
https://youtu.be/S9InoEjxly8