Update app.py

app.py

@@ -1,7 +1,9 @@
 import gradio as gr
+import pysbd
 from transformers import pipeline
 from sentence_transformers import CrossEncoder
 
+sentence_segmenter = pysbd.Segmenter(language='en',clean=False)
 passage_retreival_model = CrossEncoder('cross-encoder/ms-marco-MiniLM-L-6-v2')
 qa_model = pipeline("question-answering",'a-ware/bart-squadv2')
 
@@ -17,9 +19,17 @@ def fetch_answers(question, clincal_note ):
     top_5_query_paragraph_answer_list = ""
     count = 1
     for query, passage in top_5_query_paragraph_list:
+     passage_sentences = sentence_segmenter.segment(passage)
      answer = qa_model(question = query, context = passage)['answer']
+     
+     for i in range(len(passage_sentences)):
+         if answer.startswith('.') or answer.startswith(':'):
+             answer = answer[1:].strip()
+         if answer in passage_sentences[i]:
+             passage_sentences[i] = "**"+passage_sentences[i].strip()+"**"
+     
      result_str = "# RESULT "+str(count)+"\n"  
-     result_str = result_str + passage.replace(answer,"**"+answer.replace('.','')+"**") + "\n\n"
+     result_str = result_str + " ".join(passage_sentences) + "\n\n"
      top_5_query_paragraph_answer_list += result_str
      count+=1