Update app.py

app.py

@@ -1,64 +1,107 @@
+# import gradio as gr
+# from transformers import AutoProcessor, AutoModelForImageTextToText
+# from PIL import Image
+# import re
+
+# # Load SmolDocling model & processor once
+# processor = AutoProcessor.from_pretrained("ds4sd/SmolDocling-256M-preview")
+# model = AutoModelForImageTextToText.from_pretrained("ds4sd/SmolDocling-256M-preview")
+
+# def extract_fcel_values_from_image(image, prompt_text):
+#     """Run SmolDocling on an image and return numeric values inside <fcel> tags."""
+#     # Prepare prompt for the model
+#     messages = [
+#         {"role": "user", "content": [{"type": "image"}, {"type": "text", "text": prompt_text}]}
+#     ]
+#     prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
+#     inputs = processor(text=prompt, images=[image], return_tensors="pt")
+
+#     # Generate output
+#     outputs = model.generate(**inputs, max_new_tokens=2048)
+#     prompt_length = inputs.input_ids.shape[1]
+#     generated = outputs[:, prompt_length:]
+#     result = processor.batch_decode(generated, skip_special_tokens=False)[0]
+#     clean_text = result.replace("<end_of_utterance>", "").strip()
+
+#     # Extract only <fcel> values
+#     values = re.findall(r"<fcel>([\d.]+)", clean_text)
+#     values = [float(v) for v in values]  # convert to floats
+
+#     return values, clean_text
+
+# def compare_images(image1, image2, prompt_text):
+#     # Extract fcel values from both images
+#     values1, raw1 = extract_fcel_values_from_image(image1, prompt_text)
+#     values2, raw2 = extract_fcel_values_from_image(image2, prompt_text)
+
+#     # Calculate accuracy
+#     if len(values1) == len(values2) and values1 == values2:
+#         accuracy = 100.0
+#     else:
+#         matches = sum(1 for a, b in zip(values1, values2) if a == b)
+#         total = max(len(values1), len(values2))
+#         accuracy = (matches / total) * 100 if total > 0 else 0
+
+#     return {
+#         "Extracted Values 1": values1,
+#         "Extracted Values 2": values2,
+#         "Accuracy (%)": accuracy
+#     }
+
+# # Gradio UI
+# demo = gr.Interface(
+#     fn=compare_images,
+#     inputs=[
+#         gr.Image(type="pil", label="Upload First Table Image"),
+#         gr.Image(type="pil", label="Upload Second Table Image"),
+#         gr.Textbox(lines=1, placeholder="Enter prompt (e.g. Extract table as OTSL)", label="Prompt")
+#     ],
+#     outputs="json",
+#     title="Table Data Accuracy Checker (SmolDocling)",
+#     description="Uploads two table images, extracts only <fcel> values from OTSL output, and compares them for accuracy."
+# )
+
+# demo.launch()
+
 import gradio as gr
 from transformers import AutoProcessor, AutoModelForImageTextToText
 from PIL import Image
-import re
+import json
 
-# Load SmolDocling model & processor once
+# Load model & processor once at startup
 processor = AutoProcessor.from_pretrained("ds4sd/SmolDocling-256M-preview")
 model = AutoModelForImageTextToText.from_pretrained("ds4sd/SmolDocling-256M-preview")
 
-def extract_fcel_values_from_image(image, prompt_text):
-    """Run SmolDocling on an image and return numeric values inside <fcel> tags."""
-    # Prepare prompt for the model
+def smoldocling_readimage(image, prompt_text):
     messages = [
         {"role": "user", "content": [{"type": "image"}, {"type": "text", "text": prompt_text}]}
     ]
     prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
     inputs = processor(text=prompt, images=[image], return_tensors="pt")
-
-    # Generate output
-    outputs = model.generate(**inputs, max_new_tokens=2048)
+    outputs = model.generate(**inputs, max_new_tokens=1024)
     prompt_length = inputs.input_ids.shape[1]
     generated = outputs[:, prompt_length:]
     result = processor.batch_decode(generated, skip_special_tokens=False)[0]
-    clean_text = result.replace("<end_of_utterance>", "").strip()
-
-    # Extract only <fcel> values
-    values = re.findall(r"<fcel>([\d.]+)", clean_text)
-    values = [float(v) for v in values]  # convert to floats
+    clean_result = result.replace("<end_of_utterance>", "").strip()
 
-    return values, clean_text
-
-def compare_images(image1, image2, prompt_text):
-    # Extract fcel values from both images
-    values1, raw1 = extract_fcel_values_from_image(image1, prompt_text)
-    values2, raw2 = extract_fcel_values_from_image(image2, prompt_text)
-
-    # Calculate accuracy
-    if len(values1) == len(values2) and values1 == values2:
-        accuracy = 100.0
-    else:
-        matches = sum(1 for a, b in zip(values1, values2) if a == b)
-        total = max(len(values1), len(values2))
-        accuracy = (matches / total) * 100 if total > 0 else 0
-
-    return {
-        "Extracted Values 1": values1,
-        "Extracted Values 2": values2,
-        "Accuracy (%)": accuracy
-    }
+    # Try to parse as JSON
+    try:
+        json_result = json.loads(clean_result)
+        return json_result
+    except json.JSONDecodeError:
+        return {"error": "Output is not valid JSON", "raw_output": clean_result}
 
 # Gradio UI
 demo = gr.Interface(
-    fn=compare_images,
+    fn=smoldocling_readimage,
     inputs=[
-        gr.Image(type="pil", label="Upload First Table Image"),
-        gr.Image(type="pil", label="Upload Second Table Image"),
-        gr.Textbox(lines=1, placeholder="Enter prompt (e.g. Extract table as OTSL)", label="Prompt")
+        gr.Image(type="pil", label="Upload Image"),
+        gr.Textbox(lines=1, placeholder="Enter prompt (e.g. Convert to docling)", label="Prompt"),
     ],
-    outputs="json",
-    title="Table Data Accuracy Checker (SmolDocling)",
-    description="Uploads two table images, extracts only <fcel> values from OTSL output, and compares them for accuracy."
+    outputs=gr.JSON(),
+    title="SmolDocling Web App",
+    description="Upload a document image and convert it to structured docling format."
 )
 
 demo.launch()
+