Update app.py

app.py

@@ -38,21 +38,26 @@ def extract_text_from_txt(file_path):
         return txt_file.read()
     # return text
     
-def extract_text_from_doc(file_path):
-    # text = ""
-    # doc = docx.Document(file_path)
-    # for texts in doc.paragraphs:
-    #     text+= texts.text + "\n"
+# def extract_text_from_doc(file_path):
+#     doc = docx.Document(file_path)
+#     fullText = []
+#     for para in doc.paragraphs:
+#         fullText.append(para.text)
+#     return '\n'.join(fullText)
+    
+def extract_text_from_paragraph(para):
+    return para.text
 
-    # return texts 
+
+def extract_text_from_doc(file_path):
     doc = docx.Document(file_path)
-    fullText = []
-    for para in doc.paragraphs:
-        fullText.append(para.text)
-    return '\n'.join(fullText)
+    with concurrent.futures.ThreadPoolExecutor() as executor:
+        results = list(executor.map(extract_text_from_paragraph, doc.paragraphs))
     
-
+    return '\n'.join(results)
     
+
+
 def model(model_name):
   tokenizer = AutoTokenizer.from_pretrained(model_name)
   model = AutoModelForQuestionAnswering.from_pretrained(model_name,return_dict = False)