pipeline_name: PaddleOCR-VL-1.5

batch_size: 64

use_queues: True

use_doc_preprocessor: False
use_layout_detection: True
use_chart_recognition: False
use_seal_recognition: False
format_block_content: False
merge_layout_blocks: True
markdown_ignore_labels:
  - number
  - footnote
  - header
  - header_image
  - footer
  - footer_image
  - aside_text

SubModules:
  LayoutDetection:
    module_name: layout_detection
    model_name: PP-DocLayoutV3
    model_dir: null
    batch_size: 8
    threshold: 0.3
    layout_nms: True
    layout_unclip_ratio: [1.0, 1.0] 
    layout_merge_bboxes_mode: 
      0: "union" # abstract
      1: "union" # algorithm
      2: "union" # aside_text
      3: "large" # chart
      4: "union" # content
      5: "large" # display_formula
      6: "large" # doc_title
      7: "union" # figure_title
      8: "union" # footer
      9: "union" # footer
      10: "union" # footnote
      11: "union" # formula_number
      12: "union" # header
      13: "union" # header
      14: "union" # image
      15: "large" # inline_formula
      16: "union" # number
      17: "large" # paragraph_title
      18: "union" # reference
      19: "union" # reference_content
      20: "union" # seal
      21: "union" # table
      22: "union" # text
      23: "union" # text
      24: "union" # vision_footnote
  VLRecognition:
    module_name: vl_recognition
    model_name: PaddleOCR-VL-1.5-0.9B
    model_dir: null
    batch_size: 4096
    genai_config:
      backend: native

SubPipelines:
  DocPreprocessor:
    pipeline_name: doc_preprocessor
    batch_size: 8
    use_doc_orientation_classify: True
    use_doc_unwarping: True
    SubModules:
      DocOrientationClassify:
        module_name: doc_text_orientation
        model_name: PP-LCNet_x1_0_doc_ori
        model_dir: null
        batch_size: 8
      DocUnwarping:
        module_name: image_unwarping
        model_name: UVDoc
        model_dir: null

Serving:
  extra:
    max_num_input_imgs: null