Update app.py

app.py

@@ -7,6 +7,56 @@ query_text = 'Query used for keyword search (you can also edit, and experiment w
 written_question = st.text_input(query_text, question)
 if written_question:
     question = written_question
+
+if st.button('Run semantic question answering'):
+    if question:
+        try:
+            url = f"{ES_URL}/document/_search?pretty"
+            # payload = json.dumps({"query":{"match":{"content":"moldova"}}})
+            payload = json.dumps({"query": {
+                "more_like_this": { "like": question, # "What is the capital city of Netherlands?"
+                "fields": ["content"], "min_term_freq": 1.9, "min_doc_freq": 4, "max_query_terms": 50
+            }}})
+            headers = {'Content-Type': 'application/json'}
+            response = requests.request("GET", url, headers=headers, data=payload) 
+            kws_result = response.json() # print(response.text)
+            
+        except Exception as e:
+            qa_result = str(e)
+
+        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_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]
+        
+        for i, qa_result in enumerate(qa_results):
+            if "answer" in qa_result.keys():
+                answer_span, answer_score = qa_result["answer"], qa_result["score"]
+                st.write(f'Answer: **{answer_span}**')
+                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'Answers JSON: '); st.write(qa_results) 
+
+        for i, doc_hit in enumerate(top_5_text):
+            st.subheader(f'Search result #{i+1} (and score):')
+            st.write(f'<em>{doc_hit["text"]}...</em>', unsafe_allow_html = True)
+            st.markdown(f'> (*confidence score*: **{format(doc_hit["confidence"], ".3f")}**)')
+            
+        st.write(f'Search results JSON: '); st.write(top_5_text) 
+    else:
+        st.write('Write a query to submit your keyword search'); st.stop()
+
+# question_similarity = [ (hit['_score'], hit['_source']['content'][:200])
+#     for hit in result_first_two_hits ] # print(question_similarity)
+
 if st.button('Run keyword search'):
     if question:
         try: