# os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ") # os.environ["LANGSMITH_TRACING"] = "true" 

%pip install -qU langchain-community pypdf 

Note: you may need to restart the kernel to use updated packages. 

from langchain_community.document_loaders import PyPDFLoader  file_path = "./example_data/layout-parser-paper.pdf" loader = PyPDFLoader(file_path) 

docs = loader.load() docs[0] 

Document(metadata={'producer': 'pdfTeX-1.40.21', 'creator': 'LaTeX with hyperref', 'creationdate': '2021-06-22T01:27:10+00:00', 'author': '', 'keywords': '', 'moddate': '2021-06-22T01:27:10+00:00', 'ptex.fullbanner': 'This is pdfTeX, Version 3.14159265-2.6-1.40.21 (TeX Live 2020) kpathsea version 6.3.2', 'subject': '', 'title': '', 'trapped': '/False', 'source': './example_data/layout-parser-paper.pdf', 'total_pages': 16, 'page': 0, 'page_label': '1'}, page_content='LayoutParser: A Unified Toolkit for Deep\nLearning Based Document Image Analysis\nZejiang Shen1 (\x00 ), Ruochen Zhang2, Melissa Dell3, Benjamin Charles Germain\nLee4, Jacob Carlson3, and Weining Li5\n1 Allen Institute for AI\nshannons@allenai.org\n2 Brown University\nruochen zhang@brown.edu\n3 Harvard University\n{melissadell,jacob carlson}@fas.harvard.edu\n4 University of Washington\nbcgl@cs.washington.edu\n5 University of Waterloo\nw422li@uwaterloo.ca\nAbstract. Recent advances in document image analysis (DIA) have been\nprimarily driven by the application of neural networks. Ideally, research\noutcomes could be easily deployed in production and extended for further\ninvestigation. However, various factors like loosely organized codebases\nand sophisticated model configurations complicate the easy reuse of im-\nportant innovations by a wide audience. Though there have been on-going\nefforts to improve reusability and simplify deep learning (DL) model\ndevelopment in disciplines like natural language processing and computer\nvision, none of them are optimized for challenges in the domain of DIA.\nThis represents a major gap in the existing toolkit, as DIA is central to\nacademic research across a wide range of disciplines in the social sciences\nand humanities. This paper introduces LayoutParser, an open-source\nlibrary for streamlining the usage of DL in DIA research and applica-\ntions. The core LayoutParser library comes with a set of simple and\nintuitive interfaces for applying and customizing DL models for layout de-\ntection, character recognition, and many other document processing tasks.\nTo promote extensibility, LayoutParser also incorporates a community\nplatform for sharing both pre-trained models and full document digiti-\nzation pipelines. We demonstrate that LayoutParser is helpful for both\nlightweight and large-scale digitization pipelines in real-word use cases.\nThe library is publicly available at https://layout-parser.github.io.\nKeywords: Document Image Analysis · Deep Learning · Layout Analysis\n· Character Recognition · Open Source library · Toolkit.\n1 Introduction\nDeep Learning(DL)-based approaches are the state-of-the-art for a wide range of\ndocument image analysis (DIA) tasks including document image classification [11,\narXiv:2103.15348v2 [cs.CV] 21 Jun 2021') 

import pprint  pprint.pp(docs[0].metadata) 

{'producer': 'pdfTeX-1.40.21',  'creator': 'LaTeX with hyperref',  'creationdate': '2021-06-22T01:27:10+00:00',  'author': '',  'keywords': '',  'moddate': '2021-06-22T01:27:10+00:00',  'ptex.fullbanner': 'This is pdfTeX, Version 3.14159265-2.6-1.40.21 (TeX Live '  '2020) kpathsea version 6.3.2',  'subject': '',  'title': '',  'trapped': '/False',  'source': './example_data/layout-parser-paper.pdf',  'total_pages': 16,  'page': 0,  'page_label': '1'} 

pages = [] for doc in loader.lazy_load():  pages.append(doc)  if len(pages) >= 10:  # do some paged operation, e.g.  # index.upsert(page)   pages = [] len(pages) 

6 

print(pages[0].page_content[:100]) pprint.pp(pages[0].metadata) 

LayoutParser: A Unified Toolkit for DL-Based DIA 11 focuses on precision, efficiency, and robustness. T {'producer': 'pdfTeX-1.40.21',  'creator': 'LaTeX with hyperref',  'creationdate': '2021-06-22T01:27:10+00:00',  'author': '',  'keywords': '',  'moddate': '2021-06-22T01:27:10+00:00',  'ptex.fullbanner': 'This is pdfTeX, Version 3.14159265-2.6-1.40.21 (TeX Live '  '2020) kpathsea version 6.3.2',  'subject': '',  'title': '',  'trapped': '/False',  'source': './example_data/layout-parser-paper.pdf',  'total_pages': 16,  'page': 10,  'page_label': '11'} 

loader = PyPDFLoader(  "./example_data/layout-parser-paper.pdf",  mode="page", ) docs = loader.load() print(len(docs)) pprint.pp(docs[0].metadata) 

16 {'producer': 'pdfTeX-1.40.21',  'creator': 'LaTeX with hyperref',  'creationdate': '2021-06-22T01:27:10+00:00',  'author': '',  'keywords': '',  'moddate': '2021-06-22T01:27:10+00:00',  'ptex.fullbanner': 'This is pdfTeX, Version 3.14159265-2.6-1.40.21 (TeX Live '  '2020) kpathsea version 6.3.2',  'subject': '',  'title': '',  'trapped': '/False',  'source': './example_data/layout-parser-paper.pdf',  'total_pages': 16,  'page': 0,  'page_label': '1'} 

loader = PyPDFLoader(  "./example_data/layout-parser-paper.pdf",  mode="single", ) docs = loader.load() print(len(docs)) pprint.pp(docs[0].metadata) 

1 {'producer': 'pdfTeX-1.40.21',  'creator': 'LaTeX with hyperref',  'creationdate': '2021-06-22T01:27:10+00:00',  'author': '',  'keywords': '',  'moddate': '2021-06-22T01:27:10+00:00',  'ptex.fullbanner': 'This is pdfTeX, Version 3.14159265-2.6-1.40.21 (TeX Live '  '2020) kpathsea version 6.3.2',  'subject': '',  'title': '',  'trapped': '/False',  'source': './example_data/layout-parser-paper.pdf',  'total_pages': 16} 

loader = PyPDFLoader(  "./example_data/layout-parser-paper.pdf",  mode="single",  pages_delimiter="\n-------THIS IS A CUSTOM END OF PAGE-------\n", ) docs = loader.load() print(docs[0].page_content[:5780]) 

LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis Zejiang Shen1 (� ), Ruochen Zhang2, Melissa Dell3, Benjamin Charles Germain Lee4, Jacob Carlson3, and Weining Li5 1 Allen Institute for AI shannons@allenai.org 2 Brown University ruochen zhang@brown.edu 3 Harvard University {melissadell,jacob carlson}@fas.harvard.edu 4 University of Washington bcgl@cs.washington.edu 5 University of Waterloo w422li@uwaterloo.ca Abstract. Recent advances in document image analysis (DIA) have been primarily driven by the application of neural networks. Ideally, research outcomes could be easily deployed in production and extended for further investigation. However, various factors like loosely organized codebases and sophisticated model configurations complicate the easy reuse of im- portant innovations by a wide audience. Though there have been on-going efforts to improve reusability and simplify deep learning (DL) model development in disciplines like natural language processing and computer vision, none of them are optimized for challenges in the domain of DIA. This represents a major gap in the existing toolkit, as DIA is central to academic research across a wide range of disciplines in the social sciences and humanities. This paper introduces LayoutParser, an open-source library for streamlining the usage of DL in DIA research and applica- tions. The core LayoutParser library comes with a set of simple and intuitive interfaces for applying and customizing DL models for layout de- tection, character recognition, and many other document processing tasks. To promote extensibility, LayoutParser also incorporates a community platform for sharing both pre-trained models and full document digiti- zation pipelines. We demonstrate that LayoutParser is helpful for both lightweight and large-scale digitization pipelines in real-word use cases. The library is publicly available at https://layout-parser.github.io. Keywords: Document Image Analysis · Deep Learning · Layout Analysis · Character Recognition · Open Source library · Toolkit. 1 Introduction Deep Learning(DL)-based approaches are the state-of-the-art for a wide range of document image analysis (DIA) tasks including document image classification [11, arXiv:2103.15348v2 [cs.CV] 21 Jun 2021 -------THIS IS A CUSTOM END OF PAGE------- 2 Z. Shen et al. 37], layout detection [38, 22], table detection [ 26], and scene text detection [ 4]. A generalized learning-based framework dramatically reduces the need for the manual specification of complicated rules, which is the status quo with traditional methods. DL has the potential to transform DIA pipelines and benefit a broad spectrum of large-scale document digitization projects. However, there are several practical difficulties for taking advantages of re- cent advances in DL-based methods: 1) DL models are notoriously convoluted for reuse and extension. Existing models are developed using distinct frame- works like TensorFlow [1] or PyTorch [ 24], and the high-level parameters can be obfuscated by implementation details [ 8]. It can be a time-consuming and frustrating experience to debug, reproduce, and adapt existing models for DIA, and many researchers who would benefit the most from using these methods lack the technical background to implement them from scratch. 2) Document images contain diverse and disparate patterns across domains, and customized training is often required to achieve a desirable detection accuracy. Currently there is no full-fledged infrastructure for easily curating the target document image datasets and fine-tuning or re-training the models. 3) DIA usually requires a sequence of models and other processing to obtain the final outputs. Often research teams use DL models and then perform further document analyses in separate processes, and these pipelines are not documented in any central location (and often not documented at all). This makes it difficult for research teams to learn about how full pipelines are implemented and leads them to invest significant resources in reinventing the DIA wheel . LayoutParser provides a unified toolkit to support DL-based document image analysis and processing. To address the aforementioned challenges,LayoutParser is built with the following components: 1. An off-the-shelf toolkit for applying DL models for layout detection, character recognition, and other DIA tasks (Section 3) 2. A rich repository of pre-trained neural network models (Model Zoo) that underlies the off-the-shelf usage 3. Comprehensive tools for efficient document image data annotation and model tuning to support different levels of customization 4. A DL model hub and community platform for the easy sharing, distribu- tion, and discussion of DIA models and pipelines, to promote reusability, reproducibility, and extensibility (Section 4) The library implements simple and intuitive Python APIs without sacrificing generalizability and versatility, and can be easily installed via pip. Its convenient functions for handling document image data can be seamlessly integrated with existing DIA pipelines. With detailed documentations and carefully curated tutorials, we hope this tool will benefit a variety of end-users, and will lead to advances in applications in both industry and academic research. LayoutParser is well aligned with recent efforts for improving DL model reusability in other disciplines like natural language processing [ 8, 34] and com- puter vision [ 35], but with a focus on unique challenges in DIA. We show LayoutParser can be applied in sophisticated and large-scale digitization projects -------THIS IS A CUSTOM END OF PAGE------- LayoutParser: A Unified Toolkit for DL-Based DIA 3 that require precision, efficiency, and robustness, as well as simple and light 

%pip install -qU rapidocr-onnxruntime 

Note: you may need to restart the kernel to use updated packages. 

from langchain_community.document_loaders.parsers import RapidOCRBlobParser  loader = PyPDFLoader(  "./example_data/layout-parser-paper.pdf",  mode="page",  images_inner_format="markdown-img",  images_parser=RapidOCRBlobParser(), ) docs = loader.load()  print(docs[5].page_content) 

6 Z. Shen et al. Fig. 2: The relationship between the three types of layout data structures. Coordinate supports three kinds of variation; TextBlock consists of the co- ordinate information and extra features like block text, types, and reading orders; a Layout object is a list of all possible layout elements, including other Layout objects. They all support the same set of transformation and operation APIs for maximum flexibility. Shown in Table 1, LayoutParser currently hosts 9 pre-trained models trained on 5 different datasets. Description of the training dataset is provided alongside with the trained models such that users can quickly identify the most suitable models for their tasks. Additionally, when such a model is not readily available, LayoutParser also supports training customized layout models and community sharing of the models (detailed in Section 3.5). 3.2 Layout Data Structures A critical feature of LayoutParser is the implementation of a series of data structures and operations that can be used to efficiently process and manipulate the layout elements. In document image analysis pipelines, various post-processing on the layout analysis model outputs is usually required to obtain the final outputs. Traditionally, this requires exporting DL model outputs and then loading the results into other pipelines. All model outputs from LayoutParser will be stored in carefully engineered data types optimized for further processing, which makes it possible to build an end-to-end document digitization pipeline within LayoutParser. There are three key components in the data structure, namely the Coordinate system, the TextBlock, and the Layout. They provide different levels of abstraction for the layout data, and a set of APIs are supported for transformations or operations on these classes.    ![Coordinate (x1, y1) (X1, y1) (x2,y2) APIS x-interval tart end Quadrilateral operation Rectangle y-interval ena (x2, y2) (x4, y4) (x3, y3) and textblock Coordinate transformation + Block Block Reading Extra features Text Type Order coordinatel textblockl layout  same textblock2 layoutl The A list of the layout elements](#) 

%pip install -qU pytesseract 

Note: you may need to restart the kernel to use updated packages. 

from langchain_community.document_loaders.parsers import TesseractBlobParser  loader = PyPDFLoader(  "./example_data/layout-parser-paper.pdf",  mode="page",  images_inner_format="html-img",  images_parser=TesseractBlobParser(), ) docs = loader.load() print(docs[5].page_content) 

6 Z. Shen et al. Fig. 2: The relationship between the three types of layout data structures. Coordinate supports three kinds of variation; TextBlock consists of the co- ordinate information and extra features like block text, types, and reading orders; a Layout object is a list of all possible layout elements, including other Layout objects. They all support the same set of transformation and operation APIs for maximum flexibility. Shown in Table 1, LayoutParser currently hosts 9 pre-trained models trained on 5 different datasets. Description of the training dataset is provided alongside with the trained models such that users can quickly identify the most suitable models for their tasks. Additionally, when such a model is not readily available, LayoutParser also supports training customized layout models and community sharing of the models (detailed in Section 3.5). 3.2 Layout Data Structures A critical feature of LayoutParser is the implementation of a series of data structures and operations that can be used to efficiently process and manipulate the layout elements. In document image analysis pipelines, various post-processing on the layout analysis model outputs is usually required to obtain the final outputs. Traditionally, this requires exporting DL model outputs and then loading the results into other pipelines. All model outputs from LayoutParser will be stored in carefully engineered data types optimized for further processing, which makes it possible to build an end-to-end document digitization pipeline within LayoutParser. There are three key components in the data structure, namely the Coordinate system, the TextBlock, and the Layout. They provide different levels of abstraction for the layout data, and a set of APIs are supported for transformations or operations on these classes.    <img alt="Coordinate  textblock  x-interval  JeAsaqul-A  Coordinate +  Extra features  Rectangle  Quadrilateral  Block Text  Block Type  Reading Order  layout  [ coordinatel textblock1 | &#x27;  “y textblock2 , layout1 ]  A list of the layout elements  The same transformation and operation APIs src="#" /> 

%pip install -qU langchain-openai 

Note: you may need to restart the kernel to use updated packages. 

import os  from dotenv import load_dotenv  load_dotenv() 

True 

from getpass import getpass  if not os.environ.get("OPENAI_API_KEY"):  os.environ["OPENAI_API_KEY"] = getpass("OpenAI API key =") 

from langchain_community.document_loaders.parsers import LLMImageBlobParser from langchain_openai import ChatOpenAI  loader = PyPDFLoader(  "./example_data/layout-parser-paper.pdf",  mode="page",  images_inner_format="markdown-img",  images_parser=LLMImageBlobParser(model=ChatOpenAI(model="gpt-4o", max_tokens=1024)), ) docs = loader.load() print(docs[5].page_content) 

6 Z. Shen et al. Fig. 2: The relationship between the three types of layout data structures. Coordinate supports three kinds of variation; TextBlock consists of the co- ordinate information and extra features like block text, types, and reading orders; a Layout object is a list of all possible layout elements, including other Layout objects. They all support the same set of transformation and operation APIs for maximum flexibility. Shown in Table 1, LayoutParser currently hosts 9 pre-trained models trained on 5 different datasets. Description of the training dataset is provided alongside with the trained models such that users can quickly identify the most suitable models for their tasks. Additionally, when such a model is not readily available, LayoutParser also supports training customized layout models and community sharing of the models (detailed in Section 3.5). 3.2 Layout Data Structures A critical feature of LayoutParser is the implementation of a series of data structures and operations that can be used to efficiently process and manipulate the layout elements. In document image analysis pipelines, various post-processing on the layout analysis model outputs is usually required to obtain the final outputs. Traditionally, this requires exporting DL model outputs and then loading the results into other pipelines. All model outputs from LayoutParser will be stored in carefully engineered data types optimized for further processing, which makes it possible to build an end-to-end document digitization pipeline within LayoutParser. There are three key components in the data structure, namely the Coordinate system, the TextBlock, and the Layout. They provide different levels of abstraction for the layout data, and a set of APIs are supported for transformations or operations on these classes.    ![**Image Summary:** Diagram explaining coordinate systems and layout elements with labels for coordinate intervals, rectangle, quadrilateral, textblock with extra features, and layout list. Includes transformation and operation APIs.  **Extracted Text:** Coordinate coordinate start start x-interval end y-interval end (x1, y1) Rectangle (x2, y2) (x1, y1) Quadrilateral (x2, y2) (x4, y4) (x3, y3) The same transformation and operation APIs textblock Coordinate Extra features Block Text Block Type Reading Order ... layout coordinate1, textblock1, ... ..., textblock2, layout1 A list of the layout elements ](#) 

from langchain_community.document_loaders import FileSystemBlobLoader from langchain_community.document_loaders.generic import GenericLoader from langchain_community.document_loaders.parsers import PyPDFParser  loader = GenericLoader(  blob_loader=FileSystemBlobLoader(  path="./example_data/",  glob="*.pdf",  ),  blob_parser=PyPDFParser(), ) docs = loader.load() print(docs[0].page_content) pprint.pp(docs[0].metadata) 

LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis Zejiang Shen1 (� ), Ruochen Zhang2, Melissa Dell3, Benjamin Charles Germain Lee4, Jacob Carlson3, and Weining Li5 1 Allen Institute for AI shannons@allenai.org 2 Brown University ruochen zhang@brown.edu 3 Harvard University {melissadell,jacob carlson}@fas.harvard.edu 4 University of Washington bcgl@cs.washington.edu 5 University of Waterloo w422li@uwaterloo.ca Abstract. Recent advances in document image analysis (DIA) have been primarily driven by the application of neural networks. Ideally, research outcomes could be easily deployed in production and extended for further investigation. However, various factors like loosely organized codebases and sophisticated model configurations complicate the easy reuse of im- portant innovations by a wide audience. Though there have been on-going efforts to improve reusability and simplify deep learning (DL) model development in disciplines like natural language processing and computer vision, none of them are optimized for challenges in the domain of DIA. This represents a major gap in the existing toolkit, as DIA is central to academic research across a wide range of disciplines in the social sciences and humanities. This paper introduces LayoutParser, an open-source library for streamlining the usage of DL in DIA research and applica- tions. The core LayoutParser library comes with a set of simple and intuitive interfaces for applying and customizing DL models for layout de- tection, character recognition, and many other document processing tasks. To promote extensibility, LayoutParser also incorporates a community platform for sharing both pre-trained models and full document digiti- zation pipelines. We demonstrate that LayoutParser is helpful for both lightweight and large-scale digitization pipelines in real-word use cases. The library is publicly available at https://layout-parser.github.io. Keywords: Document Image Analysis · Deep Learning · Layout Analysis · Character Recognition · Open Source library · Toolkit. 1 Introduction Deep Learning(DL)-based approaches are the state-of-the-art for a wide range of document image analysis (DIA) tasks including document image classification [11, arXiv:2103.15348v2 [cs.CV] 21 Jun 2021 {'producer': 'pdfTeX-1.40.21',  'creator': 'LaTeX with hyperref',  'creationdate': '2021-06-22T01:27:10+00:00',  'author': '',  'keywords': '',  'moddate': '2021-06-22T01:27:10+00:00',  'ptex.fullbanner': 'This is pdfTeX, Version 3.14159265-2.6-1.40.21 (TeX Live '  '2020) kpathsea version 6.3.2',  'subject': '',  'title': '',  'trapped': '/False',  'source': 'example_data/layout-parser-paper.pdf',  'total_pages': 16,  'page': 0,  'page_label': '1'} 

from langchain_community.document_loaders import CloudBlobLoader from langchain_community.document_loaders.generic import GenericLoader  loader = GenericLoader(  blob_loader=CloudBlobLoader(  url="s3://mybucket", # Supports s3://, az://, gs://, file:// schemes.  glob="*.pdf",  ),  blob_parser=PyPDFParser(), ) docs = loader.load() print(docs[0].page_content) pprint.pp(docs[0].metadata)