Dynamic FewShot GPTClassifier: does it cache Embd locally? about scikit-llm HOT 3 OPEN

Hello, @KennyNg-19
The embeddings are stored inside the estimator and in theory can be accessed. However, reusing them for other use cases might not be easily achievable. Could you elaborate how exactly would you like to reuse the embeddings?

from scikit-llm.

Hi, @iryna-kondr
As the whole dataset gets embeddings before fewshotclassifier runs, so their embeddings cached locally may be used in other downstream tasks after the classfication task, like semantic search or similarity comparison.

If we cannot use the embeddings generated here, the embedding functions(especially paid API service) will be called again, which increases cost.

from scikit-llm.

I am having the same problem. I dont want to recreate the embeddings at every request. I wanna do it once and reuse (both embeddings + fitted classifier) it for future calls in my system.

from scikit-llm.