Update app.py

app.py

@@ -36,6 +36,12 @@ titles = [
 st.write("Fetching Wikipedia articles...")
 corpus = fetch_wikipedia_articles(titles)
 
+# Check if corpus is populated
+if not corpus:
+    st.write("No articles found. Please check the titles.")
+else:
+    st.write("Articles fetched successfully.")
+
 # Generate embeddings for the corpus
 st.write("Generating embeddings...")
 embeddings = embedder.encode(corpus, convert_to_tensor=True)
@@ -68,19 +74,23 @@ if st.button("Generate Humanized Text"):
 
         context = retrieve_documents(top_k_indices)
         
-        # Concatenate user input and context for model input
-        input_text = f"{user_input} {context}"
-        
-        # Tokenize input and handle truncation
-        inputs = tokenizer(input_text, return_tensors="pt", max_length=1024, truncation=True)
+        # Check if context is empty
+        if not context:
+            st.write("No relevant context found. Please try a different query.")
+        else:
+            # Concatenate user input and context for model input
+            input_text = f"{user_input} {context}"
+
+            # Tokenize input and handle truncation
+            inputs = tokenizer(input_text, return_tensors="pt", max_length=1024, truncation=True)
 
-        # Generate output
-        outputs = model.generate(inputs.input_ids, max_length=2000, num_return_sequences=1)
+            # Generate output
+            outputs = model.generate(inputs.input_ids, max_length=2000, num_return_sequences=1)
 
-        # Decode the generated text
-        generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+            # Decode the generated text
+            generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-        # Display the generated text
-        st.write(generated_text)
+            # Display the generated text
+            st.write(generated_text)
     else:
         st.write("Please enter a valid query.")