Update app.py

app.py

@@ -62,7 +62,9 @@
 # )
 
 # demo.launch()
+
 import re
+import numpy as np
 import gradio as gr
 from transformers import AutoProcessor, AutoModelForImageTextToText
 from PIL import Image
@@ -82,12 +84,11 @@ def extract_values(docling_text):
             continue
         # Extract numbers inside <fcel> tags
         values = re.findall(r"<fcel>(.*?)<fcel>", row)
-        # Convert to float list
         float_values = [float(v) for v in values]
         result.append(float_values)
     return result
 
-def smoldocling_readimage(image, prompt_text):
+def get_array_from_image(image, prompt_text):
     messages = [
         {"role": "user", "content": [{"type": "image"}, {"type": "text", "text": prompt_text}]}
     ]
@@ -97,20 +98,50 @@ def smoldocling_readimage(image, prompt_text):
     prompt_length = inputs.input_ids.shape[1]
     generated = outputs[:, prompt_length:]
     raw_result = processor.batch_decode(generated, skip_special_tokens=False)[0]
-    # Clean and extract numeric values
-    values_array = extract_values(raw_result)
-    return str(values_array)
+    return extract_values(raw_result)
+
+def compare_arrays(arr1, arr2):
+    # Flatten both arrays (assumes 2D list)
+    flat1 = np.array(arr1).flatten()
+    flat2 = np.array(arr2).flatten()
+    
+    # If shapes differ, compare only overlapping parts
+    min_len = min(len(flat1), len(flat2))
+    if min_len == 0:
+        return 0.0  # no data to compare
+    
+    flat1 = flat1[:min_len]
+    flat2 = flat2[:min_len]
+    
+    # Calculate similarity as 1 - normalized mean absolute error
+    mae = np.mean(np.abs(flat1 - flat2))
+    max_val = max(np.max(flat1), np.max(flat2), 1e-6)  # avoid zero division
+    similarity = 1 - (mae / max_val)
+    similarity_percent = max(0, similarity) * 100  # clamp to >=0
+    
+    return round(similarity_percent, 2)
+
+def process_two_images(image1, image2, prompt_text):
+    arr1 = get_array_from_image(image1, prompt_text)
+    arr2 = get_array_from_image(image2, prompt_text)
+    similarity = compare_arrays(arr1, arr2)
+    
+    return (
+        f"Extracted values from Image 1:\n{arr1}\n\n"
+        f"Extracted values from Image 2:\n{arr2}\n\n"
+        f"Similarity Accuracy: {similarity} %"
+    )
 
-# Gradio UI
 demo = gr.Interface(
-    fn=smoldocling_readimage,
+    fn=process_two_images,
     inputs=[
-        gr.Image(type="pil", label="Upload Image"),
+        gr.Image(type="pil", label="Upload Image 1"),
+        gr.Image(type="pil", label="Upload Image 2"),
         gr.Textbox(lines=1, placeholder="Enter prompt (e.g. Convert to docling)", label="Prompt"),
     ],
     outputs="text",
-    title="SmolDocling Web App",
-    description="Upload a document image and convert it to structured docling format."
+    title="SmolDocling Image Comparison",
+    description="Upload two document images, extract numeric arrays, and compare their similarity."
 )
 
 demo.launch()