two op

app.py

@@ -47,11 +47,10 @@ tax_deductions = '''Extract the following information in the given format:
 
 
 def process_document(image):
-    # Save the uploaded image to a temporary file
     with tempfile.NamedTemporaryFile(delete=False, suffix=".jpg") as tmp_file:
-        image = Image.fromarray(image)  # Convert NumPy array to PIL Image
-        image.save(tmp_file.name)  # Save the image to the temporary file
-        image_path = tmp_file.name  # Get the path of the saved file
+        image = Image.fromarray(image)  
+        image.save(tmp_file.name) 
+        image_path = tmp_file.name  
 
 
         messages = [
@@ -60,7 +59,7 @@ def process_document(image):
             "content": [
                 {
                     "type": "image",
-                    "image": image_path,  # Use the file path here
+                    "image": image_path, 
                 },
                 {"type": "text", "text":  '''Extract the following information in the given format:
                 {
@@ -72,8 +71,7 @@ def process_document(image):
                     'california:': {
                         'withholding tax:': {'Amount':'', 'Year-To_Date':""},
                         'ee disability tax:': {'Amount':'', 'Year-To-Date':""}}},
-                }
-'''},
+                }'''},
             ],
         }
     ]
@@ -89,7 +87,6 @@ def process_document(image):
         return_tensors="pt",
     )
     inputs = inputs.to("cuda")
-    # Inference: Generation of the output
     generated_ids = model.generate(**inputs, max_new_tokens=1500)
     generated_ids_trimmed = [
         out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
@@ -97,15 +94,12 @@ def process_document(image):
     output_text = processor.batch_decode(
         generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
     )
-    # Handle output text to convert it into JSON
     try:
-        # almost_json = output_text[0].replace('```\n', '').replace('\n```', '')
         almost_json = output_text[0].split('```\n')[-1].split('\n```')[0]
 
         json = literal_eval(almost_json)
     except:
         try:
-            # almost_json = output_text[0].replace('```json\n', '').replace('\n```', '')
             almost_json = output_text[0].split('```json\n')[-1].split('\n```')[0]
             json = literal_eval(almost_json)
         except:
@@ -117,7 +111,7 @@ def process_document(image):
             "content": [
                 {
                     "type": "image",
-                    "image": image_path,  # Use the file path here
+                    "image": image_path,  
                 },
                 {"type": "text", "text":  '''Extract the following information in the given format:
         {'other_benefits_and_information': {
@@ -129,8 +123,7 @@ def process_document(image):
                             }
             'payment method': 'eg. Direct payment',
             'Amount': 'eg. 12.99'
-                            }
-'''},
+                            }'''},
             ],
         }
     ]
@@ -165,20 +158,20 @@ def process_document(image):
         except:
             json_2 = output_text[0]
 
-    json_op = {
-        "tax_deductions": json,
-        "other_benifits": json_2
-    }
-    # Optionally, you can delete the temporary file after use
+    # json_op = {
+    #     "tax_deductions": json,
+    #     "other_benifits": json_2
+    # }
+    # # Optionally, you can delete the temporary file after use
     os.remove(image_path)
 
-    return json_op
+    return json, json_2
 
 # Create Gradio interface
 demo = gr.Interface(
     fn=process_document,
     inputs="image",  # Gradio will handle the image input
-    outputs="json",
+    outputs=["json", "json"],
     title="PaySlip_Demo_Model",
     examples=[["Slip_1.jpg"], ["Slip_2.jpg"]],
     cache_examples=False