Create app.py

app.py

@@ -0,0 +1,76 @@
+import gradio as gr
+import logging
+import os
+import json
+from PIL import Image, ImageDraw
+import torch
+from surya.ocr import run_ocr
+from surya.detection import batch_text_detection
+from surya.layout import batch_layout_detection
+from surya.ordering import batch_ordering
+from surya.model.detection.model import load_model as load_det_model, load_processor as load_det_processor
+from surya.model.recognition.model import load_model as load_rec_model
+from surya.model.recognition.processor import load_processor as load_rec_processor
+from surya.settings import settings
+
+# Configuração de logging
+logging.basicConfig(level=logging.DEBUG, format='%(asctime)s - %(levelname)s - %(message)s')
+logger = logging.getLogger(__name__)
+
+# Carregamento de modelos
+det_processor, det_model = load_det_processor(), load_det_model()
+rec_model, rec_processor = load_rec_model(), load_rec_processor()
+
+class CustomJSONEncoder(json.JSONEncoder):
+    def default(self, obj):
+        if isinstance(obj, Image.Image):
+            return "Image object (not serializable)"
+        return str(obj)
+
+def serialize_result(result):
+    return json.dumps(result, cls=CustomJSONEncoder, indent=2)
+
+def save_metadata(results):
+    output_file = "/mnt/data/ocr_metadata.json"  # Caminho de armazenamento persistente
+    with open(output_file, "w") as f:
+        json.dump(results, f, cls=CustomJSONEncoder, indent=2)
+    return output_file
+
+def ocr_workflow(images, langs):
+    logger.info(f"Iniciando workflow OCR para {len(images)} imagens com idiomas: {langs}")
+    results = []
+    for image_file in images:
+        try:
+            image = Image.open(image_file.name)
+            predictions = run_ocr([image], [langs.split(',')], det_model, det_processor, rec_model, rec_processor)
+            formatted_text = "\n".join([line.text for line in predictions[0].text_lines])
+            results.append({
+                "image": image_file.name,
+                "text": formatted_text,
+                "predictions": predictions[0].text_lines  # Assuming text_lines is serializable
+            })
+        except Exception as e:
+            logger.error(f"Erro com {image_file.name}: {e}")
+            results.append({"image": image_file.name, "error": str(e)})
+    
+    metadata_file = save_metadata(results)
+    return serialize_result(results), metadata_file
+
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown("# Análise de Documentos com Surya")
+    
+    with gr.Tab("OCR"):
+        gr.Markdown("## Reconhecimento Óptico de Caracteres para Múltiplas Imagens")
+        with gr.Row():
+            ocr_input = gr.Files(label="Carregar Imagens ou PDFs (até 100)")
+            ocr_langs = gr.Textbox(label="Idiomas (separados por vírgula)", value="en")
+        ocr_button = gr.Button("Executar OCR")
+        ocr_output = gr.JSON(label="Resultados OCR")
+        ocr_file = gr.File(label="Baixar Metadata OCR")
+        
+        # Executa a função OCR e salva o arquivo de metadata para download
+        ocr_button.click(ocr_workflow, inputs=[ocr_input, ocr_langs], outputs=[ocr_output, ocr_file])
+
+if __name__ == "__main__":
+    logger.info("Iniciando aplicativo Gradio...")
+    demo.launch()