Update app.py

app.py

@@ -10,12 +10,19 @@ import wikipediaapi
 from b import b
 
 nltk.download('punkt')
+nltk.download('stopwords')
+nltk.download('brown')
 from nltk.tokenize import sent_tokenize
 
 # Load spaCy model
 nlp = spacy.load("en_core_web_sm")
 # wiki_wiki = wikipediaapi.Wikipedia('en')
 
+# Initialize Wikipedia API with a user agent
+user_agent = 'QGen/1.0 ([email protected])'
+wiki_wiki = wikipediaapi.Wikipedia(user_agent= user_agent,language='en')
+
+
 # Load T5 model and tokenizer
 model_name = "DevBM/t5-large-squad"
 model = T5ForConditionalGeneration.from_pretrained(model_name)
@@ -61,11 +68,11 @@ def map_keywords_to_sentences(text, keywords, context_window_size):
     return keyword_sentence_mapping
 
 # Function to perform entity linking using Wikipedia API
-# def entity_linking(keyword):
-#     page = wiki_wiki.page(keyword)
-#     if page.exists():
-#         return page.fullurl
-#     return None
+def entity_linking(keyword):
+    page = wiki_wiki.page(keyword)
+    if page.exists():
+        return page.fullurl
+    return None
 
 # Function to generate questions using beam search
 def generate_question(context, answer, num_beams=5):
@@ -114,13 +121,13 @@ if st.button("Generate Questions"):
         for i, (keyword, context) in enumerate(keyword_sentence_mapping.items()):
             if i >= num_questions:
                 break
-            # linked_entity = entity_linking(keyword)
+            linked_entity = entity_linking(keyword)
             question = generate_question(context, keyword, num_beams=num_beams)
             st.write(f"**Context:** {context}")
             st.write(f"**Answer:** {keyword}")
             st.write(f"**Question:** {question}")
-            # if linked_entity:
-            #     st.write(f"**Entity Link:** {linked_entity}")
+            if linked_entity:
+                st.write(f"**Entity Link:** {linked_entity}")
             st.write("---")
             data.append((context, keyword, question))