Update app.py

app.py

@@ -27,11 +27,13 @@ if st.button('Run semantic question answering'):
         top_5_hits = kws_result['hits']['hits'][:5] # print("First 5 results:")
         top_5_text = [{'text': hit['_source']['content'][:500],
                        'confidence': hit['_score']} for hit in top_5_hits ]
+        top_3_para = [hit['_source']['content'][:5000] for hit in top_5_hits[:3]]
         top_5_para = [hit['_source']['content'][:5000] for hit in top_5_hits]
 
         DPR_MODEL = "deepset/roberta-base-squad2" #, model="distilbert-base-cased-distilled-squad"
         pipe_exqa = pipeline("question-answering", model=DPR_MODEL) 
-        qa_results = [pipe_exqa(question=question, context=paragraph) for paragraph in top_5_para]
+        # qa_results = [pipe_exqa(question=question, context=paragraph) for paragraph in top_5_para]
+        qa_results = [pipe_exqa(question=question, context=paragraph) for paragraph in top_3_para]
         
         for i, qa_result in enumerate(qa_results):
             if "answer" in qa_result.keys():
@@ -40,8 +42,10 @@ if st.button('Run semantic question answering'):
                 paragraph = top_5_para[i]
                 start_par, stop_para = max(0, qa_result["start"]-86), min(qa_result["end"]+90, len(paragraph))
                 answer_context = paragraph[start_par:stop_para].replace(answer_span, f'**{answer_span}**')
-                st.write(f'Answer context (and score): ... _{answer_context}_ ...')            
-                st.write(f'(answer confidence: {format(answer_score, ".3f")})')            
+                st.write(f'Answer context (and score): ... _{answer_context}_ ...') 
+                color_string = 'green' if answer_score > 0.65 else 'orange' if answer_score > 0.45 else 'red'
+                # st.markdown("""This text is :red[colored red]""")
+                st.markdown(f'(answer confidence: :{color_string}[{format(answer_score, ".3f")}])')            
 
         st.write(f'Answers JSON: '); st.write(qa_results)