Fix problems

app.py

@@ -3,6 +3,9 @@ from transformers import pipeline
 import numpy as np
 import pandas as pd
 from sentence_transformers import SentenceTransformer, util
+import nltk
+from nltk import sent_tokenize
+nltk.download("punkt")
 
 # Loading in quotes dataset
 df = pd.read_json("krishnamurti_df.json")
@@ -10,12 +13,13 @@ df = pd.read_json("krishnamurti_df.json")
 # Loading back in our sentence similarity and language model
 model = SentenceTransformer("msmarco-roberta-base-v3") # best performing model
 
-krishnamurti_generator = pipeline("text-generation", model="distilgpt2",)
+krishnamurti_generator = pipeline("text-generation", model="distilgpt2")
 
 ############### DEFINING FUNCTIONS ###########################
 
 def ask_krishnamurti(question):
-  answer = krishnamurti_generator(question,)[0]['generated_text']
+  answer = krishnamurti_generator(question, min_length=40, max_length=60)[0]['generated_text'] # generate about 50 word tokens
+  answer = " ".join(sent_tokenize(answer)[:5]) # Get the first five sentences
   return answer
 
 def get_similar_quotes(question):
@@ -24,7 +28,7 @@ def get_similar_quotes(question):
   ind = np.argpartition(sims, -5)[-5:]
   similar_sentences = [df['Quotes'][i] for i in ind]
   top5quotes = pd.DataFrame(data = similar_sentences, columns=["Quotes"], index=range(1,6))
-  top5quotes['Quotes'] = top5quotes['Quotes'].str[:500] + "..."
+  top5quotes['Quotes'] = top5quotes['Quotes'].str[:-1].str[:250] + "..."
   return top5quotes
  
 def main(question):