Update app.py

app.py

@@ -13,8 +13,8 @@ try:
 except:
   spacy.cli.download("en_core_web_sm")
   nlp = spacy.load("en_core_web_sm")
-
 wh_words = ['what', 'who', 'how', 'when', 'which']
+
 def get_concepts(text):
   text = text.lower()
   doc = nlp(text)
@@ -38,14 +38,12 @@ def get_passages(text, k=100):
             passage = sen.text
             passage_len = len(sen)
             continue
-
         elif i==(len(sents)-1):
             passage+=" "+sen.text
             passages.append(passage)
             passage = ""
             passage_len = 0
             continue
-
         passage+=" "+sen.text
     return passages
 
@@ -58,10 +56,8 @@ def get_dicts_for_dpr(concepts, n_results=20, k=100):
         try:
           html_page = wikipedia.page(title = wiki, auto_suggest = False)
         except DisambiguationError:
-          continue
-        
+          continue   
         htmlResults=html_page.content
-        
         passages = get_passages(htmlResults, k=k)
         for passage in passages:
           i_dicts = {}
@@ -90,11 +86,13 @@ def extracted_passage_embeddings(processed_passages, max_length=156):
                     max_length=max_length,
                     return_token_type_ids=True
                 )
-    passage_embeddings = passage_encoder.predict([np.array(passage_inputs['input_ids']), 
-                                                np.array(passage_inputs['attention_mask']), 
-                                                np.array(passage_inputs['token_type_ids'])], 
-                                                batch_size=64, 
-                                                verbose=1)
+    passage_embeddings = passage_encoder.predict(
+                    [np.array(passage_inputs['input_ids']), 
+                    np.array(passage_inputs['attention_mask']), 
+                    np.array(passage_inputs['token_type_ids'])], 
+                    batch_size=64, 
+                    verbose=1
+                )
     return passage_embeddings
 
 def extracted_query_embeddings(queries, max_length=64):
@@ -106,70 +104,56 @@ def extracted_query_embeddings(queries, max_length=64):
                     max_length=max_length,
                     return_token_type_ids=True
                 )
-    query_embeddings = query_encoder.predict([np.array(query_inputs['input_ids']), 
-                                                np.array(query_inputs['attention_mask']), 
-                                                np.array(query_inputs['token_type_ids'])], 
-                                                batch_size=1, 
-                                                verbose=1)
+    query_embeddings = query_encoder.predict(
+                    [np.array(query_inputs['input_ids']), 
+                    np.array(query_inputs['attention_mask']), 
+                    np.array(query_inputs['token_type_ids'])], 
+                    batch_size=1, 
+                    verbose=1
+                )
     return query_embeddings
     
-#Wikipedia API:
+# Wikipedia API:
 
 def get_pagetext(page):
   s=str(page).replace("/t","")
-  
   return s
 
 def get_wiki_summary(search):
     wiki_wiki = wikipediaapi.Wikipedia('en')
     page = wiki_wiki.page(search)
-
     isExist = page.exists()
     if not isExist:
         return isExist, "Not found", "Not found", "Not found", "Not found"
-
     pageurl = page.fullurl
     pagetitle = page.title
     pagesummary = page.summary[0:60]
     pagetext = get_pagetext(page.text)
-
     backlinks = page.backlinks
     linklist = ""
     for link in backlinks.items():
       pui = link[0]
       linklist += pui + " ,  "
       a=1 
-      
     categories = page.categories
     categorylist = ""
     for category in categories.items():
       pui = category[0]
       categorylist += pui + " ,  "
       a=1     
-    
     links = page.links
     linklist2 = ""
     for link in links.items():
       pui = link[0]
       linklist2 += pui + " ,  "
       a=1 
-      
     sections = page.sections
-    
-    
     ex_dic = {
       'Entity' : ["URL","Title","Summary", "Text", "Backlinks", "Links", "Categories"],
       'Value': [pageurl, pagetitle, pagesummary, pagetext, linklist,linklist2, categorylist ]
     }
-    
-    #columns = [pageurl,pagetitle]
-    #index = [pagesummary,pagetext]
-    #df = pd.DataFrame(page, columns=columns, index=index)
-    #df = pd.DataFrame(ex_dic, columns=columns, index=index)
     df = pd.DataFrame(ex_dic)
-    
     return df
-      
     
 def search(question):
   concepts = get_concepts(question)
@@ -184,11 +168,9 @@ def search(question):
   query_embeddings = extracted_query_embeddings([question])
   faiss_index = faiss.IndexFlatL2(128)
   faiss_index.add(passage_embeddings.pooler_output)
-#  prob, index = faiss_index.search(query_embeddings.pooler_output, k=1000)
   prob, index = faiss_index.search(query_embeddings.pooler_output, k=lendicts)
   return pd.DataFrame([dicts[i] for i in index[0]])
 
-
 # AI UI SOTA - radio blocks with UI formatting, and event driven UI
 with gr.Blocks() as demo:     # Block documentation on event listeners, start here:  https://gradio.app/blocks_and_event_listeners/
   gr.Markdown("<h1><center>🍰 Ultimate Wikipedia AI 🎨</center></h1>")
@@ -205,5 +187,4 @@ with gr.Blocks() as demo:     # Block documentation on event listeners, start he
     inp.submit(fn=get_wiki_summary, inputs=inp, outputs=out_DF)
   b3.click(fn=search, inputs=inp, outputs=out)
   b4.click(fn=get_wiki_summary, inputs=inp, outputs=out_DF )
-demo.launch(debug=True, show_error=True) 
-
+demo.launch(debug=True, show_error=True)