Update app.py

app.py

@@ -13,11 +13,12 @@ import pdfminer
 from pdfminer.high_level import extract_text
 #from termcolor import colored
 
+len_doc = 400
+overlap = 50 
+
 def read_pdf(file):
   text = extract_text(file.name)
   # Split text into smaller docs
-  len_doc = 400
-  overlap = 50 
   docs = []
   
   i = 0
@@ -50,7 +51,8 @@ def retrieval(query, top_k_retriver, docs, bm25_):
     return bm25_hits
 
 qa_model = pipeline("question-answering", 
-                    model = "deepset/roberta-base-squad2")
+                    model = "deepset/minilm-uncased-squad2")
+                    #model = "deepset/roberta-base-squad2")
                     
 def qa_ranker(query, docs_, top_k_ranker):
     ans = []
@@ -84,7 +86,7 @@ def final_qa_pipeline(file, query):
     
     bm25 = BM25Okapi(tokenized_corpus)
     
-    top_k_retriver, top_k_ranker = 20,3
+    top_k_retriver, top_k_ranker = 30,3
     lvl1 = retrieval(query, top_k_retriver, docs, bm25)
 
     if len(lvl1) > 0: