Upload retrieval.py

retrieval.py

@@ -7,11 +7,14 @@ from data_processing import embedding_model
 from sentence_transformers import CrossEncoder
 from nltk.tokenize import word_tokenize
 import string
+import nltk
 
 reranker = CrossEncoder("cross-encoder/ms-marco-MiniLM-L-6-v2")
 
 retrieved_docs = None
 
+nltk.download('punkt')
+
 # Tokenize the documents and remove punctuation
 def preprocess(doc):
     return [word.lower() for word in word_tokenize(doc) if word not in string.punctuation]