Update app.py

app.py

@@ -84,6 +84,10 @@ def txt_to_html(text):
 @spaces.GPU(duration=80)
 def deidentify_doc(pdftext, maxtokens, temperature, top_probability):
 
+    print('-----------------------------------------------------------')
+    print(pdftext)
+    print('-----------------------------------------------------------')
+
     llm = Llama(
         model_path="models/Meta-Llama-3-8B-Instruct.Q8_0.gguf",
         flash_attn=True,
@@ -107,11 +111,19 @@ def deidentify_doc(pdftext, maxtokens, temperature, top_probability):
     )
     output = output['choices'][0]['message']['content']
 
+    print('-----------------------------------------------------------')
+    print(output)
+    print('-----------------------------------------------------------')
+    
     # Remove starting header string in output
     find_index = output.find(' '.join(pdftext.split()[:3]))
     if find_index != -1:
         output = output[find_index:].strip()
 
+    print('-----------------------------------------------------------')
+    print(output)
+    print('-----------------------------------------------------------')
+    
     # print('---------------Remove Dates-----------------------')
     # print(output)
 
@@ -130,11 +142,19 @@ def deidentify_doc(pdftext, maxtokens, temperature, top_probability):
     )
     output = output['choices'][0]['message']['content']
 
+    print('-----------------------------------------------------------')
+    print(output)
+    print('-----------------------------------------------------------')
+    
     # Remove starting header string in output
     find_index = output.find(' '.join(pdftext.split()[:3]))
     if find_index != -1:
         output = output[find_index:].strip()
 
+    print('-----------------------------------------------------------')
+    print(output)
+    print('-----------------------------------------------------------')
+
     # print('---------------Remove Addresses-----------------------')
     # print(output)
 
@@ -153,11 +173,19 @@ def deidentify_doc(pdftext, maxtokens, temperature, top_probability):
     )
     output = output['choices'][0]['message']['content']
 
+    print('-----------------------------------------------------------')
+    print(output)
+    print('-----------------------------------------------------------')
+    
     # Remove starting header string in output
     find_index = output.find(' '.join(pdftext.split()[:3]))
     if find_index != -1:
         output = output[find_index:].strip()
 
+    print('-----------------------------------------------------------')
+    print(output)
+    print('-----------------------------------------------------------')
+
     # print('---------------Remove Names-----------------------')
     # print(output)
 
@@ -178,11 +206,19 @@ def deidentify_doc(pdftext, maxtokens, temperature, top_probability):
     )
     output = output['choices'][0]['message']['content']
 
+    print('-----------------------------------------------------------')
+    print(output)
+    print('-----------------------------------------------------------')
+    
     # Remove starting header string in output
     find_index = output.find(' '.join(pdftext.split()[:3]))
     if find_index != -1:
         output = output[find_index:].strip()
 
+    print('-----------------------------------------------------------')
+    print(output)
+    print('-----------------------------------------------------------')
+
     # print('---------------Remove Registration Numbers-----------------------')
     # print(output)