Update app.py

app.py

@@ -93,7 +93,7 @@ def deidentify_doc(pdftext="", prompt="", maxtokens=600, temperature=1.2, top_pr
         output = replace_words_with_asterisk(pdfcontent, wordstoremove.split(','))
         return output
 
-    iterations=2
+    iterations=1
     output = pdftext
     for iter in range(0,iterations):
         output = get_output(output)
@@ -108,16 +108,18 @@ def mkdir(dir):
 @spaces.GPU(duration=120)
 def pdf_to_text(files, output_folder, prompt, maxtokens=600, temperature=1.2, top_probability=0.95):
     output_folder = output_folder.replace('\\', '/')
+    files=[files]#remove later
     for file in files:
-        file_name = os.path.basename(file)
-        file_name_splt = file_name.split('.')
-        print('File name is ', file_name)
-        print('output folder is ', output_folder)
-        if (len(file_name_splt) > 1 and file_name_splt[1] == 'pdf'):
-            page2content = process_document(file, page_ids=[0])
-            pdftext = page2content[1]
-            if (pdftext):
-                anonymized_text = deidentify_doc(pdftext, prompt, maxtokens, temperature, top_probability)
+        # file_name = os.path.basename(file)
+        # file_name_splt = file_name.split('.')
+        # print('File name is ', file_name)
+        # print('output folder is ', output_folder)
+        # if (len(file_name_splt) > 1 and file_name_splt[1] == 'pdf'):
+            # page2content = process_document(file, page_ids=[0])
+            # pdftext = page2content[1]
+        pdftext = file # remove later
+        if (pdftext): #shift this if block to right later
+            anonymized_text = deidentify_doc(pdftext, prompt, maxtokens, temperature, top_probability)
     return anonymized_text
 
 
@@ -134,7 +136,8 @@ output_text = gr.Textbox()
 output_path_component = gr.File(label="Select Output Path")
 iface = gr.Interface(
     fn=pdf_to_text,
-    inputs=['files', input_folder_text, "textbox", max_tokens, temp_slider, prob_slider],
+    # inputs=['files', input_folder_text, "textbox", max_tokens, temp_slider, prob_slider],
+    inputs=["textbox", input_folder_text, "textbox", max_tokens, temp_slider, prob_slider],
     outputs=output_text,
     title='COBIx Endoscopy Report De-Identification',
     description="This application assists to remove personal information from the uploaded clinical report",