Pypdfium2loader 集成

使用 LangChain Python 集成 Pypdfium2loader 文档加载器。

本指南提供了快速入门 PyPDF 文档加载器 的概述。有关所有 DocumentLoader 功能和配置的详细文档，请参阅 API 参考。

概述

集成详情

类	包	本地	可序列化	JS 支持
PyPDFLoader	langchain-community	✅	❌	❌

---

加载器特性

源	文档惰性加载	原生异步支持	提取图像	提取表格
PyPDFLoader	✅	❌	✅	❌

设置

凭证

使用 PyPDFLoader 无需凭证。

要启用模型调用的自动追踪，请设置您的 LangSmith API 密钥：

os.environ["LANGSMITH_API_KEY"] = getpass.getpass("输入您的 LangSmith API 密钥：")
os.environ["LANGSMITH_TRACING"] = "true"

安装

安装 langchain-community 和 pypdf。

pip install -qU langchain-community pypdfium2

初始化

现在我们可以实例化模型对象并加载文档：

from langchain_community.document_loaders import PyPDFium2Loader

file_path = "./example_data/layout-parser-paper.pdf"
loader = PyPDFium2Loader(file_path)

加载

docs = loader.load()
docs[0]

Document(metadata={'title': '', 'author': '', 'subject': '', 'keywords': '', 'creator': 'LaTeX with hyperref', 'producer': 'pdfTeX-1.40.21', 'creationdate': '2021-06-22T01:27:10+00:00', 'moddate': '2021-06-22T01:27:10+00:00', 'source': './example_data/layout-parser-paper.pdf', 'total_pages': 16, 'page': 0}, page_content='LayoutParser: A Unified Toolkit for Deep\nLearning Based Document Image Analysis\nZejiang Shen\n1\n(), Ruochen Zhang\n2\n, Melissa Dell\n3\n, Benjamin Charles Germain\nLee\n4\n, Jacob Carlson\n3\n, and Weining Li\n5\n1 Allen Institute for AI\[e-mail] 2 Brown University\nruochen [e-mail] 3 Harvard University\n{melissadell,jacob carlson\n}@fas.harvard.edu\n4 University of Washington\[e-mail] 5 University of Waterloo\[e-mail]\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\x02portant 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\x02tions. The core LayoutParser library comes with a set of simple and\nintuitive interfaces for applying and customizing DL models for layout de\x02tection, 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\x02zation 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\n')

import pprint

pprint.pp(docs[0].metadata)

{'title': '',
 'author': '',
 'subject': '',
 'keywords': '',
 'creator': 'LaTeX with hyperref',
 'producer': 'pdfTeX-1.40.21',
 'creationdate': '2021-06-22T01:27:10+00:00',
 'moddate': '2021-06-22T01:27:10+00:00',
 'source': './example_data/layout-parser-paper.pdf',
 'total_pages': 16,
 'page': 0}

惰性加载

pages = []
for doc in loader.lazy_load():
    pages.append(doc)
    if len(pages) >= 10:
        # 执行一些分页操作，例如：
        # 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
{'title': '',
 'author': '',
 'subject': '',
 'keywords': '',
 'creator': 'LaTeX with hyperref',
 'producer': 'pdfTeX-1.40.21',
 'creationdate': '2021-06-22T01:27:10+00:00',
 'moddate': '2021-06-22T01:27:10+00:00',
 'source': './example_data/layout-parser-paper.pdf',
 'total_pages': 16,
 'page': 10}

元数据属性至少包含以下键：

• source
• page（如果在 page 模式下）
• total_page
• creationdate
• creator
• producer

其他元数据特定于每个解析器。 这些信息可能很有用（例如，用于对 PDF 进行分类）。

分割模式与自定义页面分隔符

加载 PDF 文件时，可以通过两种不同的方式分割：

• 按页面
• 作为单个文本流

默认情况下，PyPDFLoader 会将 PDF 作为单个文本流分割。

按页面提取 PDF。每个页面被提取为一个 langchain 文档对象

loader = PyPDFium2Loader(
    "./example_data/layout-parser-paper.pdf",
    mode="page",
)
docs = loader.load()
print(len(docs))
pprint.pp(docs[0].metadata)

16
{'title': '',
 'author': '',
 'subject': '',
 'keywords': '',
 'creator': 'LaTeX with hyperref',
 'producer': 'pdfTeX-1.40.21',
 'creationdate': '2021-06-22T01:27:10+00:00',
 'moddate': '2021-06-22T01:27:10+00:00',
 'source': './example_data/layout-parser-paper.pdf',
 'total_pages': 16,
 'page': 0}

在此模式下，PDF 按页面分割，生成的文档元数据包含页码。但在某些情况下，我们可能希望将 PDF 作为单个文本流处理（以避免将某些段落截断）。在这种情况下，您可以使用 single 模式：

将整个 PDF 提取为单个 langchain 文档对象

loader = PyPDFium2Loader(
    "./example_data/layout-parser-paper.pdf",
    mode="single",
)
docs = loader.load()
print(len(docs))
pprint.pp(docs[0].metadata)

1
{'title': '',
 'author': '',
 'subject': '',
 'keywords': '',
 'creator': 'LaTeX with hyperref',
 'producer': 'pdfTeX-1.40.21',
 'creationdate': '2021-06-22T01:27:10+00:00',
 'moddate': '2021-06-22T01:27:10+00:00',
 'source': './example_data/layout-parser-paper.pdf',
 'total_pages': 16}

逻辑上，在此模式下，“page_number”元数据会消失。以下是如何在文本流中清晰标识页面结束位置：

添加自定义 pages_delimiter 以标识 single 模式下的页面结束位置

loader = PyPDFium2Loader(
    "./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 Shen
1
(), Ruochen Zhang
2
, Melissa Dell
3
, Benjamin Charles Germain
Lee
4
, Jacob Carlson
3
, and Weining Li
5
1 Allen Institute for AI
[e-mail] 2 Brown University
ruochen [e-mail] 3 Harvard University
{melissadell,jacob carlson
}@fas.harvard.edu
4 University of Washington
[e-mail] 5 University of Waterloo
[e-mail]
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 important 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 applications. The core LayoutParser library comes with a set of simple and
intuitive interfaces for applying and customizing DL models for layout detection, 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 digitization 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 recent advances in DL-based methods: 1) DL models are notoriously convoluted
for reuse and extension. Existing models are developed using distinct frameworks 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, distribution, 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 computer 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

这可以简单地是 \n，或 \f 来清晰指示页面更改，或 <!— PAGE BREAK —> 以便在 Markdown 查看器中无缝注入而不产生视觉影响。

从 PDF 中提取图像

您可以从 PDF 中提取图像，有三种不同的解决方案可供选择：

• rapidOCR（轻量级光学字符识别工具）
• Tesseract（高精度 OCR 工具）
• 多模态语言模型

您可以调整这些函数，以选择提取图像的输出格式，包括 html、markdown 或 text

结果将插入到页面文本的倒数第二段和最后一段之间。

使用 rapidOCR 从 PDF 中提取图像

pip install -qU rapidocr-onnxruntime

from langchain_community.document_loaders.parsers import RapidOCRBlobParser

loader = PyPDFium2Loader(
    "./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 coordinate 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](#)

请注意，RapidOCR 设计用于处理中文和英文，不支持其他语言。

使用 tesseract 从 PDF 中提取图像

pip install -qU pytesseract

from langchain_community.document_loaders.parsers import TesseractBlobParser

loader = PyPDFium2Loader(
    "./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 coordinate 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

[ coordinatel1 textblock1 |
&#x27;

“y textblock2 , layout1 ]

A list of the layout elements

The same transformation and operation APIs src="#" />

使用多模态模型从 PDF 中提取图像

pip install -qU langchain-openai

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 = PyPDFium2Loader(
    "./example_data/layout-parser-paper.pdf",
    mode="page",
    images_inner_format="markdown-img",
    images_parser=LLMImageBlobParser(model=ChatOpenAI(model="gpt-4.1", 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 coordinate 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 showing a data structure for layout elements including coordinates (intervals, rectangles, quadrilaterals) and text blocks with extra features (block text, type, reading order). It illustrates a hierarchy from coordinates to text blocks and a list of layout elements.

**Extracted Text**:
\`\`\`
Coordinate
Coordinate

x-interval
x1, y1
(x1, y1)
y-interval
(x2, y2)
(x2, y2)

Rectangle
Rectangle

Quadrilateral

textblock

Coordinate
Coordinate

+ +
Extra features
Extra features

Block Block Reading ...
Block Text
Block Type
Reading Order
...

layout

[coordinate1, textblock1, textblock2, layout1\\]
...

[\\]
A list of the layout elements
A list of the layout elements

The same transformation and operation APIs
The same transformation
and operation APIs
\`\`\`](#)

处理文件

许多文档加载器涉及解析文件。这些加载器之间的区别通常在于文件的解析方式，而不是文件的加载方式。例如，您可以使用 open 读取 PDF 或 Markdown 文件的二进制内容，但需要不同的解析逻辑将这些二进制数据转换为文本。

因此，将解析逻辑与加载逻辑解耦会很有帮助，这使得无论数据如何加载，都更容易重用给定的解析器。 您可以使用此策略来分析不同的文件，并使用相同的解析参数。

from langchain_community.document_loaders import FileSystemBlobLoader
from langchain_community.document_loaders.generic import GenericLoader
from langchain_community.document_loaders.parsers import PyPDFium2Parser

loader = GenericLoader(
    blob_loader=FileSystemBlobLoader(
        path="./example_data/",
        glob="*.pdf",
    ),
    blob_parser=PyPDFium2Parser(),
)
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 Shen
1
(), Ruochen Zhang
2
, Melissa Dell
3
, Benjamin Charles Germain
Lee
4
, Jacob Carlson
3
, and Weining Li
5
1 Allen Institute for AI
[e-mail] 2 Brown University
ruochen [e-mail] 3 Harvard University
{melissadell,jacob carlson
}@fas.harvard.edu
4 University of Washington
[e-mail] 5 University of Waterloo
[e-mail]
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 important 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 applications. The core LayoutParser library comes with a set of simple and
intuitive interfaces for applying and customizing DL models for layout detection, 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 digitization 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

{'title': '',
 'author': '',
 'subject': '',
 'keywords': '',
 'creator': 'LaTeX with hyperref',
 'producer': 'pdfTeX-1.40.21',
 'creationdate': '2021-06-22T01:27:10+00:00',
 'moddate': '2021-06-22T01:27:10+00:00',
 'source': 'example_data/layout-parser-paper.pdf',
 'total_pages': 16,
 'page': 0}

也可以处理来自云存储的文件。

from langchain_community.document_loaders import CloudBlobLoader
from langchain_community.document_loaders.generic import GenericLoader

loader = GenericLoader(
    blob_loader=CloudBlobLoader(
        url="s3://mybucket",  # 支持 s3://、az://、gs://、file:// 等协议。
        glob="*.pdf",
    ),
    blob_parser=PyPDFium2Parser(),
)
docs = loader.load()
print(docs[0].page_content)
pprint.pp(docs[0].metadata)

---

API 参考

有关所有 PyPDFium2Loader 功能和配置的详细文档，请参阅 API 参考

---

Edit this page on GitHub or file an issue.

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.