Create app.py

app.py

@@ -0,0 +1,35 @@
+import gradio as gr
+from transformers import AutoModel, AutoTokenizer
+from PIL import Image
+
+# Load the tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained('ucaslcl/GOT-OCR2_0', trust_remote_code=True)
+model = AutoModel.from_pretrained('ucaslcl/GOT-OCR2_0', trust_remote_code=True, low_cpu_mem_usage=True, device_map='cuda', use_safetensors=True, pad_token_id=tokenizer.eos_token_id)
+model = model.eval().cuda()
+
+# Define the OCR function
+def perform_ocr(image):
+    # Convert PIL image to RGB format (if necessary)
+    if image.mode != "RGB":
+        image = image.convert("RGB")
+
+    # Save the image to a temporary path
+    image_file_path = 'temp_image.jpg'
+    image.save(image_file_path)
+
+    # Perform OCR using the model
+    res = model.chat(tokenizer, image_file_path, ocr_type='ocr')
+
+    return res
+
+# Define the Gradio interface
+interface = gr.Interface(
+    fn=perform_ocr,
+    inputs=gr.Image(type="pil", label="Upload Image"),
+    outputs=gr.Textbox(label="Extracted Text"),
+    title="OCR and Document Search Web Application",
+    description="Upload an image to extract text using the GOT-OCR2_0 model."
+)
+
+# Launch the Gradio app
+interface.launch()