Update app.py

app.py

@@ -106,60 +106,7 @@ def id_extractor(image: Image.Image) -> Dict:
         generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
 
     )
-    resp = output_text[-1].replace("```json", "").replace("```", "").strip()
-    return json.loads(resp)
-
-
-import torch
-from PIL import Image
-from transformers import AutoProcessor, AutoModelForVision2Seq
-from transformers.image_utils import load_image
-
-DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
-
-
-
-def id_details(image: Image.Image) -> Dict:
-    
-    if image is None:
-        # Return empty dictionary and make the output invisible
-        return {}, gr.update(visible=False)
-    
-    
-    # Initialize processor and model
-    processor = AutoProcessor.from_pretrained("HuggingFaceTB/SmolVLM-500M-Instruct")
-    model = AutoModelForVision2Seq.from_pretrained(
-        "HuggingFaceTB/SmolVLM-500M-Instruct",
-        torch_dtype=torch.bfloat16,
-        _attn_implementation="flash_attention_2" if DEVICE == "cuda" else "eager",
-    ).to(DEVICE)
-    
-    # Create input messages
-    messages = [
-        {
-            "role": "user",
-            "content": [
-                {"type": "image"},
-                {"type": "text", "text": "Can you describe this image?"}
-            ]
-        },
-    ]
-    
-    # Prepare inputs
-    prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
-    inputs = processor(text=prompt, images=[image], return_tensors="pt")
-    inputs = inputs.to(DEVICE)
-    
-    # Generate outputs
-    generated_ids = model.generate(**inputs, max_new_tokens=500)
-    generated_texts = processor.batch_decode(
-        generated_ids,
-        skip_special_tokens=True,
-    )
-    return generated_texts
-
-
-
+    return output_text
 
 # Define the Gradio interface for the ID extractor
 id_interface = gr.Interface(