ការបង្កប់
អត្ថន័យនៃអត្ថបទឬរូបភាពដែលបានបំប្លែងទៅជាបញ្ជីលេខ។ អត្ថន័យស្រដៀងគ្នាទទួលបានលេខស្រដៀងគ្នា.
임베딩
ទិដ្ឋភាពទូទៅ
A computer cannot grasp what a word means directly. An embedding turns text into hundreds or thousands of numbers, so that text with close meanings gets close numbers. "Puppy" and "doggy" are close, while "puppy" and "tax" are far apart.
With this in place, you can find documents with similar meaning even when the words differ. This is called vector search, and it is mainly used to find related material in RAG.
ឧទាហរណ៍ប្រចាំថ្ងៃ
It is like a library putting books on similar topics on nearby shelves. Even if the titles differ, a book next to the others is easy to find.
ហេតុអ្វីវាសំខាន់
It is the base for features like search, recommendations and grouping similar texts. LastAI uses this kind of method too when it groups articles about the same news.
vector
