翻訳待ち：Building an End-to-End Document Intelligence Pipeline with deepDoctection

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。

In this tutorial, we implement a document intelligence pipeline with deepDoctection 1.2.x that combines layout detection, table structure recognition, OCR, reading-order reconstruction, annotation linking, and structured export in a single workflow. We configure the analyzer explicitly with DocLayNet-based layout detection, Table Transformer structure recognition, and DocTR OCR, then inspect the resulting Page objects to understand how deepDoctection represents text, figures, tables, relationships, provenance, and reading order. We also extend the framework by registering custom object types and implementing our own PipelineComponent for extracting monetary and date entities while classifying documents by their tabular characteristics. Finally, we assemble a custom pipeline manually with ServiceFactory, explore filtering and service rollback, serialize processed pages, and transform document annotations into ordered JSONL chunks suitable for downstream RAG and retrieval systems. Copy CodeCopiedUse a different Browser !pip install -q "deepdoctection" "transformers>=5.2.0" "timm" "python-doctr" "pdfplumber" "networkx" "lxml" import os os.environ["DD_USE_TORCH"] = "True" os.environ["DPI"] = "200" os.environ["LOG_LEVEL"] = "INFO" os.environ["ENABLE_DYNAMIC_OBJECT_TYPES"] = "False" import json, re, textwrap from pathlib import Path from collections import Counter import numpy as np import matplotlib.pyplot as plt from IPython.display import HTML, display import deepdoctection as dd print("deepdoctection:", dd.version) import transformers.integrations.peft as _hf_peft if _hf_peft.is_peft_available(): _hf_peft.is_peft_available = lambda: False print("patched: PEFT adapter lookup disabled for from_pretrained") !mkdir -p /content/docs /content/imgs !wget -q -O /content/docs/paper.pdf \ Click to access 2312.13560.pdf !wget -q -O /content/imgs/finance.png \ https://raw.githubusercontent.com/deepdoctection/notebooks/main/sample/finance/1bcac3899c9cb1c0b0f650b1431d3d52_7.png PDF = Path("/content/docs/paper.pdf") PNG = Path("/content/imgs/finance.png") OUT = Path("/content/out"); OUT.mkdir(exist_ok=True) def show(img, w=16): if img is None: return plt.figure(figsize=(w, w * 1.3)); plt.axis("off"); plt.imshow(img); plt.show() def analyze_any(pipe, path, kw): """ Dispatch correctly for a directory, a PDF, or a single image file. DoctectionPipe can stream a directory or a PDF from disk, but a *single* image has no reader — path= only supplies the file name / provenance, and the pixels must be handed in via bytes=. Without this you get: ValueError: When passing a path to a single image, bytes of the image must be passed """ path = Path(path) if path.is_dir(): kw.setdefault("file_type", [".jpg", ".png", ".jpeg", ".tif"]) return pipe.analyze(path=path, kw) if path.suffix.lower() == ".pdf": return pipe.analyze(path=path, kw) if path.suffix.lower() in (".png", ".jpg", ".jpeg", ".tif"): return pipe.analyze(path=path, bytes=path.read_bytes(), kw) raise ValueError(f"unsupported input: {path}") We install the required deepDoctection dependencies, configure its runtime environment, and apply a compatibility patch for Transformers and PEFT. We download the sample PDF and image files that we use throughout the tutorial and prepare our output directory. We also define helper functions to visualize images and consistently analyze directories, PDFs, and individual image files. Copy CodeCopiedUse a different Browser dd.print_model_infos(add_description=False, add_config=False, add_categories=False) profile = dd.ModelCatalog.get_profile("Aryn/deformable-detr-DocLayNet/model.safetensors") print("\nlayout model categories:", profile.categories) print("is registered:", dd.ModelCatalog.is_registered("Aryn/deformable-detr-DocLayNet/model.safetensors")) config_overwrite = [ "USE_ROTATOR=False", "USE_LAYOUT=True", "USE_LAYOUT_NMS=True", "USE_TABLE_SEGMENTATION=True", "USE_TABLE_REFINEMENT=False", "USE_PDF_MINER=False", "USE_OCR=True", "USE_LAYOUT_LINK=True", "LAYOUT.WEIGHTS=Aryn/deformable-detr-DocLayNet/model.safetensors", "ITEM.WEIGHTS=deepdoctection/tatr_tab_struct_v2/model.safetensors", "ITEM.FILTER=['table']", "OCR.USE_DOCTR=True", "OCR.USE_TESSERACT=False", "OCR.USE_TEXTRACT=False", "OCR.WEIGHTS.DOCTR_WORD=doctr/db_resnet50/db_resnet50-ac60cadc.pt", "OCR.WEIGHTS.DOCTR_RECOGNITION=doctr/crnn_vgg16_bn/crnn_vgg16_bn-0417f351.pt", "SEGMENTATION.THRESHOLD_ROWS=0.4", "SEGMENTATION.THRESHOLD_COLS=0.4", "SEGMENTATION.FULL_TABLE_TILING=True", "WORD_MATCHING.RULE=ioa", "WORD_MATCHING.THRESHOLD=0.3", "WORD_MATCHING.MAX_PARENT_ONLY=True", "TEXT_ORDERING.INCLUDE_RESIDUAL_TEXT_CONTAINER=True", "TEXT_ORDERING.PARAGRAPH_BREAK=0.035", "TEXT_ORDERING.BROKEN_LINE_TOLERANCE=0.003", "LAYOUT_LINK.PARENTAL_CATEGORIES=['figure','table']", "LAYOUT_LINK.CHILD_CATEGORIES=['caption']", ] analyzer = dd.get_dd_analyzer(config_overwrite=config_overwrite) print("\n--- pipeline ---") for sid, name in analyzer.get_pipeline_info().items(): print(f"{sid} {name}") print("\n--- what this pipeline produces ---") print(analyzer.get_meta_annotation()) We inspect deepDoctection’s model registry to verify the layout model and its supported document categories. We explicitly configure the analyzer to combine layout detection, table segmentation, DocTR OCR, word matching, reading-order reconstruction, and layout linking. We then initialize the analyzer and inspect its pipeline components and the annotation types that it produces. Copy CodeCopiedUse a different Browser df = analyze_any(analyzer, PDF, session_id="tutorial01", max_datapoints=3) df.reset_state() pages = list(df) print(f"\nparsed {len(pages)} pages") page = pages[0] show(page.viz(show_figures=True, show_residual_layouts=True, show_table_structure=True)) print("== narrative text ==") print(textwrap.fill(page.text[:900], 110)) print("\n== layout blocks in reading order ==") for doc_id, img_id, pno, ann_id, order, cat, txt in page.chunks[:12]: print(f"[{order:>3}] {str(cat): caption ids:", [i[:8] for i in linked]) if page.words: w = page.words[0] print("\nword:", w.characters, "| service:", w.service_id, "| model:", w.model_id, "| bbox:", [round(x) for x in w.bbox]) tbl_pages = [p for p in pages if p.tables] if tbl_pages: t = tbl_pages[0].tables[0] print(f"table {t.number_of_rows}x{t.number_of_columns}, " f"max_row_span={t.max_row_span}, max_col_span={t.max_col_span}") display(HTML(t.html)) for row in t.csv[:5]: print([c[:22] for c in row]) for c in t.cells[:5]: print(f" r{c.row_number} c{c.column_number} " f"(span {c.row_span}x{c.column_span}) {c.text[:40]!r}") else: print("no table on these pages — the finance.png sample below has one") We run the configured analyzer on the sample PDF and materialize the resulting pages from the lazy data flow. We inspect narrative text, reading-order chunks, annotation categories, figure-caption relationships, word provenance, and bounding boxes. We also access detected tables through HTML, CSV, and individual cell representations to examine their structured output. Copy CodeCopiedUse a different Browser @dd.object_types_registry.register("CustomKey") class CustomKey(dd.ObjectTypes): """Custom summary keys — must be registered to be serialisable.""" MONEY_MENTIONS = "money_mentions" DATE_MENTIONS = "date_mentions" DOC_FLAVOUR = "doc_flavour" @dd.object_types_registry.register("FlavourLabel") class FlavourLabel(dd.ObjectTypes): TABULAR = "tabular" NARRATIVE = "narrative" MIXED = "mixed" MONEY = re.compile(r"(?:[$€£]\s?\d[\d,.]*|\d[\d,.]*\s?(?:USD|EUR|GBP|million|bn))") DATE = re.compile(r"\b(?:\d{1,2}[/-]\d{1,2}[/-]\d{2,4}|\d{4}-\d{2}-\d{2}|" r"(?:Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)\w*\s+\d{1,2},?\s+\d{4})\b") class EntityAndFlavourService(dd.PipelineComponent): def init(self, name="entity_flavour", tabular_ratio=0.25): self.tabular_ratio = tabular_ratio super().init(name) def serve(self, dp: dd.Image) -> None: page = dd.Page.from_image(dp, text_container=dd.LayoutLabel.WORD) text = page.text_no_line_break money = sorted(set(MONEY.findall(text))) dates = sorted(set(DATE.findall(text))) tables = page.tables table_area = sum((b[2] - b[0]) * (b[3] - b[1]) for b in (t.bbox for t in tables)) ratio = table_area / float(page.width * page.height or 1) flavor = (FlavourLabel.TABULAR if ratio > self.tabular_ratio else FlavourLabel.NARRATIVE if not tables else FlavourLabel.MIXED) self.dp_manager.set_summary_annotation( summary_key=CustomKey.MONEY_MENTIONS, summary_name=CustomKey.MONEY_MENTIONS, summary_value=money) self.dp_manager.set_summary_annotation( summary_key=CustomKey.DATE_MENTIONS, summary_name=CustomKey.DATE_MENTIONS, summary_value=dates) self.dp_manager.set_summary_annotation( summary_key=CustomKey.DOC_FLAVOUR, summary_name=flavour, summary_score=round(ratio, 4)) def clone(self): return self.class(self.name, self.tabular_ratio) def get_meta_annotation(self) -> dd.MetaAnnotation: return dd.MetaAnnotation( image_annotations=(), sub_categories={}, relationships={}, summaries=(CustomKey.MONEY_MENTIONS, CustomKey.DATE_MENTIONS, CustomKey.DOC_FLAVOUR), ) for k in (CustomKey.MONEY_MENTIONS, CustomKey.DATE_MENTIONS, CustomKey.DOC_FLAVOUR): dd.Page.add_attribute_name(k) We register custom object types for extracted monetary mentions, date mentions, and document flavor classifications. We implement a custom deepDoctection pipeline component that analyzes page text and table coverage to generate these page-level summaries. We then expose the custom summary fields as Page attributes so that we can access them directly from processed documents. Copy CodeCopiedUse a different Browser from deepdoctection.analyzer import cfg, ServiceFactory cfg.freeze(False) cfg.USE_TABLE_SEGMENTATION = True cfg.freeze(True) components = [] layout_detector = ServiceFactory.build_layout_detector(cfg, mode="LAYOUT") components.append(ServiceFactory.build_layout_service(cfg, detector=layout_detector, mode="LAYOUT")) components.append(ServiceFactory.build_layout_nms_service(cfg)) item_detector = ServiceFactory.build_layout_detector(cfg, mode="ITEM") components.append(ServiceFactory.build_sub_image_service(cfg, detector=item_detector, mode="ITEM")) components.append(ServiceFactory.build_table_segmentation_service(cfg, detector=item_detector)) word_detector = ServiceFactory.build_doctr_word_detector(cfg) components.append(ServiceFactory.build_doctr_word_detector_service(word_detector)) components.append(ServiceFactory.build_text_extraction_service(cfg, ServiceFactory.build_ocr_detector(cfg))) components.append(ServiceFactory.build_word_matching_service(cfg)) components.append(ServiceFactory.build_text_order_service(cfg)) components.append(EntityAndFlavourService()) custom_pipe = dd.DoctectionPipe(pipeline_component_list=components) print("\ncustom pipeline:", list(custom_pipe.get_pipeline_info().values())) df2 = analyze_any(custom_pipe, PNG) df2.reset_state() fin_page = next(iter(df2)) print("flavour :", fin_page.doc_flavour) print("money :", fin_page.money_mentions[:10]) print("dates :", fin_page.date_mentions[:10]) show(fin_page.viz(show_table_structure=True), w=13) def skip_if_no_table(dp: dd.Image) -> bool: return "table" not in {a.category_name for a in dp.get_annotation()} components[-1].set_inbound_filter(skip_if_no_table) det_sid = next(sid for sid, n in analyzer.get_pipeline_info().items() if n.startswith("image_doctr")) det_comp = analyzer.get_pipeline_component(service_id=det_sid) df_undo = det_comp.undo(dd.DataFromList([p.base_image for p in pages])) df_undo.reset_state() undone = list(df_undo) print("annotations before/after undo:", len(pages[0].get_annotation()), len(dd.Page.from_image(undone[0]).get_annotation())) We manually assemble a deepDoctection pipeline with ServiceFactory, combining layout analysis, table processing, OCR, text ordering, and our custom component. We execute this custom pipeline on the financial document image and inspect the detected flavor, monetary values, dates, and [truncated for AI cost control]