ilaa-chenjeri-15's picture
Initial commit: Explainable RAG system
2db7cb0
Raw
History Blame Contribute Delete
230 Bytes
from nltk.stem import WordNetLemmatizer
from nltk.tokenize import word_tokenize
lemmatizer = WordNetLemmatizer()
def preprocess(text):
tokens = word_tokenize(text.lower())
return [lemmatizer.lemmatize(t) for t in tokens]