Update app.py

app.py

@@ -1,6 +1,5 @@
 import gradio as gr
 from transformers import AutoModelForConditionalGeneration, AutoProcessor
-from huggingface_hub import hf_api
 import torch
 import pandas as pd
 import pytesseract
@@ -51,8 +50,9 @@ def process_image(image_path):
         }]
 
         text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-        image_inputs, video_inputs = process_vision_info(messages)
-        inputs = processor(text=[text], images=image_inputs, videos=video_inputs, padding=True, return_tensors="pt")
+        
+        # Removed process_vision_info and used the processor directly
+        inputs = processor(text=[text], padding=True, return_tensors="pt")
         inputs = inputs.to(model.device)
 
         generated_ids = model.generate(**inputs, max_new_tokens=128)