pipeline_name: PP-DocTranslation use_layout_parser: True SubModules: LLM_Chat: module_name: chat_bot model_name: ernie-3.5-8k base_url: "https://qianfan.baidubce.com/v2" api_type: openai api_key: "api_key" # Set this to a real API key PromptEngneering: Translate_CommonText: module_name: prompt_engneering task_type: translate_prompt task_description: '你是一位资深的多语种语言翻译专家，精通多种语言的语法、词汇、文化背景以及语言风格。你的任务是将文本从一种语言准确地转换为另一种语言，同时精准地保留原文的语义、风格和语调，确保翻译内容在目标语言中自然流畅且富有文化适应性。' output_format: '输出应为翻译后的文本，并与原文保持格式一致，包括标点符号和段落结构。如果原文中包含特定的格式（如表格、公式、列表等），翻译后的文本也应保持相同的格式。' rules_str: '通用规则： 1. 翻译应确保语义准确完整，并符合目标语言的表达习惯。 2. 保留原文的风格和语调，以传达相同的情感和意图。 3. 专有名词（如人名、地名、品牌名等）应保持不变，除非它们在目标语言中有公认的翻译。 4. 文化特定的表达或成语需根据目标语言的文化背景进行适当的转换或解释。 5. 避免使用机器翻译工具的简单直译，需根据上下文进行调整和优化。 6. 原文中可能包含的非文本元素（如HTML语法中的图片、表格、公式等）应保持不变。 7. 原文中可能包含的代码块，如编程语言代码等，应保持代码块的完整性，不要对代码进行调整。 8. 翻译完成后，应仔细校对，确保没有语法和拼写错误。' few_shot_demo_text_content: few_shot_demo_key_value_list: SubPipelines: LayoutParser: pipeline_name: PP-StructureV3 batch_size: 8 use_doc_preprocessor: False use_seal_recognition: False use_table_recognition: True use_formula_recognition: True use_chart_recognition: False use_region_detection: True SubModules: LayoutDetection: module_name: layout_detection model_name: PP-DocLayout_plus-L model_dir: null batch_size: 8 threshold: 0: 0.3 # paragraph_title 1: 0.5 # image 2: 0.4 # text 3: 0.5 # number 4: 0.5 # abstract 5: 0.5 # content 6: 0.5 # figure_table_chart_title 7: 0.3 # formula 8: 0.5 # table 9: 0.5 # reference 10: 0.5 # doc_title 11: 0.5 # footnote 12: 0.5 # header 13: 0.5 # algorithm 14: 0.5 # footer 15: 0.45 # seal 16: 0.5 # chart 17: 0.5 # formula_number 18: 0.5 # aside_text 19: 0.5 # reference_content layout_nms: True layout_unclip_ratio: [1.0, 1.0] layout_merge_bboxes_mode: 0: "large" # paragraph_title 1: "large" # image 2: "union" # text 3: "union" # number 4: "union" # abstract 5: "union" # content 6: "union" # figure_table_chart_title 7: "large" # formula 8: "union" # table 9: "union" # reference 10: "union" # doc_title 11: "union" # footnote 12: "union" # header 13: "union" # algorithm 14: "union" # footer 15: "union" # seal 16: "large" # chart 17: "union" # formula_number 18: "union" # aside_text 19: "union" # reference_content ChartRecognition: module_name: chart_recognition model_name: PP-Chart2Table model_dir: null batch_size: 1 RegionDetection: module_name: layout_detection model_name: PP-DocBlockLayout model_dir: null layout_nms: True layout_merge_bboxes_mode: "small" 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 GeneralOCR: pipeline_name: OCR batch_size: 8 text_type: general use_doc_preprocessor: False use_textline_orientation: True SubModules: TextDetection: module_name: text_detection model_name: PP-OCRv5_server_det model_dir: null limit_side_len: 736 limit_type: min max_side_limit: 4000 thresh: 0.3 box_thresh: 0.6 unclip_ratio: 1.5 TextLineOrientation: module_name: textline_orientation model_name: PP-LCNet_x1_0_textline_ori model_dir: null batch_size: 8 TextRecognition: module_name: text_recognition model_name: PP-OCRv5_server_rec model_dir: null batch_size: 8 score_thresh: 0.0 TableRecognition: pipeline_name: table_recognition_v2 use_layout_detection: False use_doc_preprocessor: False use_ocr_model: False SubModules: TableClassification: module_name: table_classification model_name: PP-LCNet_x1_0_table_cls model_dir: null WiredTableStructureRecognition: module_name: table_structure_recognition model_name: SLANeXt_wired model_dir: null WirelessTableStructureRecognition: module_name: table_structure_recognition model_name: SLANet_plus model_dir: null WiredTableCellsDetection: module_name: table_cells_detection model_name: RT-DETR-L_wired_table_cell_det model_dir: null WirelessTableCellsDetection: module_name: table_cells_detection model_name: RT-DETR-L_wireless_table_cell_det model_dir: null TableOrientationClassify: module_name: doc_text_orientation model_name: PP-LCNet_x1_0_doc_ori model_dir: null SubPipelines: GeneralOCR: pipeline_name: OCR text_type: general use_doc_preprocessor: False use_textline_orientation: True SubModules: TextDetection: module_name: text_detection model_name: PP-OCRv5_server_det model_dir: null limit_side_len: 736 limit_type: min max_side_limit: 4000 thresh: 0.3 box_thresh: 0.4 unclip_ratio: 1.5 TextLineOrientation: module_name: textline_orientation model_name: PP-LCNet_x1_0_textline_ori model_dir: null batch_size: 8 TextRecognition: module_name: text_recognition model_name: PP-OCRv5_server_rec model_dir: null batch_size: 8 score_thresh: 0.0 SealRecognition: pipeline_name: seal_recognition batch_size: 8 use_layout_detection: False use_doc_preprocessor: False SubPipelines: SealOCR: pipeline_name: OCR batch_size: 8 text_type: seal use_doc_preprocessor: False use_textline_orientation: False SubModules: TextDetection: module_name: seal_text_detection model_name: PP-OCRv4_server_seal_det model_dir: null limit_side_len: 736 limit_type: min max_side_limit: 4000 thresh: 0.2 box_thresh: 0.6 unclip_ratio: 0.5 TextRecognition: module_name: text_recognition model_name: PP-OCRv5_server_rec model_dir: null batch_size: 8 score_thresh: 0 FormulaRecognition: pipeline_name: formula_recognition batch_size: 8 use_layout_detection: False use_doc_preprocessor: False SubModules: FormulaRecognition: module_name: formula_recognition model_name: PP-FormulaNet_plus-L model_dir: null batch_size: 8