Update app.py

app.py

@@ -51,7 +51,7 @@ def retrieval(query, top_k_retriver, docs, bm25_):
     
     return bm25_hits
 
-def qa_ranker(query, docs_, top_k_ranker):
+def qa_ranker(query, docs_, top_k_ranker, qa_model):
     ans = []
     for doc in docs_:
         answer = qa_model(question = query, 
@@ -91,7 +91,7 @@ def final_qa_pipeline(file, query, model_nm):
                     model = "deepset/"+ str(model_nm))
 
     if len(lvl1) > 0:
-        fnl_rank = qa_ranker(query, [l["docs"] for l in lvl1], top_k_ranker)
+        fnl_rank = qa_ranker(query, [l["docs"] for l in lvl1], top_k_ranker,qa_model)
         top1 = print_colored(fnl_rank[0]['doc'], fnl_rank[0]['start'], fnl_rank[0]['end'], str(np.round(100*fnl_rank[0]["score"],1))+"%")  
         if len(lvl1)>1:
             top2 = print_colored(fnl_rank[1]['doc'], fnl_rank[1]['start'], fnl_rank[1]['end'], str(np.round(100*fnl_rank[1]["score"],1))+"%")