refactor: Update PaddleOCR-VL model to 1.5 in configuration generation and remove the default.yaml file.

app.py

@@ -77,7 +77,7 @@ def setup_pipeline():
             logger.info(f"⚠️ {CONFIG_FILE} not found. Generating default configuration via paddlex CLI...")
             try:
                 subprocess.run(
-                    ["paddlex", "--get_pipeline_config", "PaddleOCR-VL", "--save_path", "./"],
+                    ["paddlex", "--get_pipeline_config", "PaddleOCR-VL-1.5", "--save_path", "./"],
                     capture_output=True, text=True, check=True
                 )
                 if os.path.exists(GENERATED_CONFIG):

default.yaml

@@ -1,104 +0,0 @@
-Serving:
-  extra:
-    max_num_input_imgs: null
-SubModules:
-  LayoutDetection:
-    batch_size: 8
-    layout_merge_bboxes_mode:
-      0: union
-      1: union
-      2: union
-      3: large
-      4: union
-      5: large
-      6: large
-      7: union
-      8: union
-      9: union
-      10: union
-      11: union
-      12: union
-      13: union
-      14: union
-      15: large
-      16: union
-      17: large
-      18: union
-      19: union
-      20: union
-      21: union
-      22: union
-      23: union
-      24: union
-    layout_nms: true
-    layout_unclip_ratio:
-    - 1.0
-    - 1.0
-    model_dir: null
-    model_name: PP-DocLayoutV2
-    module_name: layout_detection
-    threshold:
-      0: 0.5
-      1: 0.5
-      2: 0.5
-      3: 0.5
-      4: 0.5
-      5: 0.4
-      6: 0.4
-      7: 0.5
-      8: 0.5
-      9: 0.5
-      10: 0.5
-      11: 0.5
-      12: 0.5
-      13: 0.5
-      14: 0.5
-      15: 0.4
-      16: 0.5
-      17: 0.4
-      18: 0.5
-      19: 0.5
-      20: 0.45
-      21: 0.5
-      22: 0.4
-      23: 0.4
-      24: 0.5
-  VLRecognition:
-    batch_size: -1
-    genai_config:
-      backend: native
-    model_dir: tachiwin/Tachiwin-OCR-1.5
-    model_name: PaddleOCR-VL-1.5-0.9B
-    module_name: vl_recognition
-SubPipelines:
-  DocPreprocessor:
-    SubModules:
-      DocOrientationClassify:
-        batch_size: 8
-        model_dir: null
-        model_name: PP-LCNet_x1_0_doc_ori
-        module_name: doc_text_orientation
-      DocUnwarping:
-        model_dir: null
-        model_name: UVDoc
-        module_name: image_unwarping
-    batch_size: 8
-    pipeline_name: doc_preprocessor
-    use_doc_orientation_classify: true
-    use_doc_unwarping: true
-batch_size: 64
-format_block_content: false
-markdown_ignore_labels:
-- number
-- footnote
-- header
-- header_image
-- footer
-- footer_image
-- aside_text
-merge_layout_blocks: true
-pipeline_name: PaddleOCR-VL
-use_chart_recognition: false
-use_doc_preprocessor: false
-use_layout_detection: true
-use_queues: true