Update main.py

main.py

@@ -62,10 +62,7 @@ def process(image_input: Image.Image, box_threshold: float, iou_threshold: float
     image_save_path = "imgs/saved_image_demo.png"
     os.makedirs(os.path.dirname(image_save_path), exist_ok=True)
     image_input.save(image_save_path)
-
-    logger.info(f"Saved image for processing: {image_save_path}")
-
-    # Open image and prepare it for further processing
+    
     image = Image.open(image_save_path)
     box_overlay_ratio = image.size[0] / 3200
     draw_bbox_config = {
@@ -75,7 +72,6 @@ def process(image_input: Image.Image, box_threshold: float, iou_threshold: float
         "thickness": max(int(3 * box_overlay_ratio), 1),
     }
 
-    # OCR and YOLO box processing
     ocr_bbox_rslt, is_goal_filtered = check_ocr_box(
         image_save_path,
         display_img=False,
@@ -86,29 +82,28 @@ def process(image_input: Image.Image, box_threshold: float, iou_threshold: float
     )
     text, ocr_bbox = ocr_bbox_rslt
 
-    # Process image and get result
-    try:
-        dino_labled_img, label_coordinates, parsed_content_list = get_som_labeled_img(
-            image_save_path,
-            yolo_model,
-            BOX_TRESHOLD=box_threshold,
-            output_coord_in_ratio=True,
-            ocr_bbox=ocr_bbox,
-            draw_bbox_config=draw_bbox_config,
-            caption_model_processor=caption_model_processor,
-            ocr_text=text,
-            iou_threshold=iou_threshold,
-        )
-    except Exception as e:
-        logger.error(f"Error during labeling and captioning: {e}")
-        raise
+    dino_labled_img, label_coordinates, parsed_content_list = get_som_labeled_img(
+        image_save_path,
+        yolo_model,
+        BOX_TRESHOLD=box_threshold,
+        output_coord_in_ratio=True,
+        ocr_bbox=ocr_bbox,
+        draw_bbox_config=draw_bbox_config,
+        caption_model_processor=caption_model_processor,
+        ocr_text=text,
+        iou_threshold=iou_threshold,
+    )
 
-    logger.info("Finished processing image with YOLO and captioning.")
+    # Log parsed_content_list to inspect its structure before joining
+    logger.info(f"Parsed content list before join: {parsed_content_list}")
+    
+    # Ensure parsed_content_list is a list of strings, not dictionaries
+    parsed_content_list_str = "\n".join([str(item) for item in parsed_content_list])
 
-    # Convert the image to base64 string
     image = Image.open(io.BytesIO(base64.b64decode(dino_labled_img)))
-    parsed_content_list_str = "\n".join(parsed_content_list)
+    print("Finish processing")
 
+    # Convert the image to base64
     buffered = io.BytesIO()
     image.save(buffered, format="PNG")
     img_str = base64.b64encode(buffered.getvalue()).decode("utf-8")
@@ -119,6 +114,7 @@ def process(image_input: Image.Image, box_threshold: float, iou_threshold: float
         label_coordinates=str(label_coordinates),
     )
 
+
 @app.post("/process_image", response_model=ProcessResponse)
 async def process_image(
     image_file: UploadFile = File(...),