In Week 8 you kept 155 NorthPeak vectors in a numpy matrix in memory. That does not scale to ten thousand documents, and it is lost when the program restarts. A vector database keeps each chunk with its id, text, vector and metadata, saves them on disk, and returns the k chunks nearest to a question in one call. This lesson builds the manuals collection of the course in Chroma, with the 31 chunks of Lesson 1, and runs a first search on it.
Preview — the rest of the lesson is for enrolled readers.
Your access is tied to your account, not to this link. Sign in with the same email you used in class: your course is waiting, no need to enter the code again.
Sign inNo account yet? Create oneThe first modules of the course are open to everyone. For the rest you have three options: buy this course once and for all, subscribe, or enter the code handed out in class.