Update app.py

app.py

@@ -33,12 +33,17 @@ def pdf_to_text(path, start_page=1, end_page=None):
     doc.close()
     return text_list
 
-def text_to_chunks(texts, word_length=150, start_page=1):
+def text_to_chunks(texts, file_names, word_length=150, start_page=1):
     text_toks = [t.split(' ') for t in texts]
     page_nums = []
     chunks = []
     
+    current_file_idx = 0
+
     for idx, words in enumerate(text_toks):
+        if idx > 0 and idx % len(file_names) == 0:
+            current_file_idx += 1
+
         for i in range(0, len(words), word_length):
             chunk = words[i:i+word_length]
             if (i+word_length) > len(words) and (len(chunk) < word_length) and (
@@ -46,10 +51,11 @@ def text_to_chunks(texts, word_length=150, start_page=1):
                 text_toks[idx+1] = chunk + text_toks[idx+1]
                 continue
             chunk = ' '.join(chunk).strip()
-            chunk = f'[Page no. {idx+start_page}]' + ' ' + '"' + chunk + '"'
+            chunk = f'[{file_names[current_file_idx]}, Page no. {idx+start_page}]' + ' ' + '"' + chunk + '"'
             chunks.append(chunk)
     return chunks
 
+
 class SemanticSearch:
     
     def __init__(self):