Exactly!
To complement on the end: thanks to the RAG system, the model was fed around 2k tokens each time, down from the 128k tokens of the original document.
RAG system reduces token input from 128k to 2k
By
–
By
–
Exactly!
To complement on the end: thanks to the RAG system, the model was fed around 2k tokens each time, down from the 128k tokens of the original document.