Update app.py

app.py

@@ -2,12 +2,19 @@ import gradio as gr
 import pickle
 import os
 from datasets import load_dataset
-embeddings_a = pickle.load(open(os.getcwd()+"/temp.pkl",'rb'))
-dataset = load_dataset("SandipPalit/Movie_Dataset")
+from gradio.components import Label
 from InstructorEmbedding import INSTRUCTOR
-model = INSTRUCTOR('hkunlp/instructor-xl')
 import heapq
 from sklearn.metrics.pairwise import cosine_similarity
+import nltk
+from nltk.corpus import stopwords
+from nltk.tokenize import word_tokenize, sent_tokenize
+from nltk.stem import WordNetLemmatizer
+import pandas as pd
+
+dataset = load_dataset("SandipPalit/Movie_Dataset")
+
+model = INSTRUCTOR('hkunlp/instructor-xl')
 
 def getSimilarity(sentences_a,sentences_b):
   embeddings_a = pickle.load(open(os.getcwd()+"/temp.pkl",'rb'))
@@ -15,10 +22,7 @@ def getSimilarity(sentences_a,sentences_b):
   similarities = cosine_similarity(embeddings_a,embeddings_b)
   return similarities
   
-import nltk
-from nltk.corpus import stopwords
-from nltk.tokenize import word_tokenize, sent_tokenize
-from nltk.stem import WordNetLemmatizer
+
 
 nltk.download('punkt')
 nltk.download('stopwords')
@@ -72,7 +76,7 @@ def get_top_k_matches(np_array,k,sentences):
    return indices
     
 
-import pandas as pd
+
 df=pd.DataFrame({"Title":dataset['train']['Title'],"Plot":dataset['train']['Overview']})
 
 def getOutput(text, size=1000):