Skip to main content
Open In Colab在 GitHub 上打开

PyMuPDF4LLMLoader

这个笔记本为开始使用PyMuPDF4LLM文档加载器提供了一个快速的概述。有关所有 PyMuPDF4LLMLoader 功能和配置的详细文档,请访问 GitHub 存储库

概述

集成详细信息

本地化序列 化JS 支持
PyMuPDF4LLMLoaderlangchain_pymupdf4llm

Loader 功能

文档延迟加载原生异步支持提取图像提取表
PyMuPDF4LLMLoader

设置

要访问 PyMuPDF4LLM 文档加载器,您需要安装langchain-pymupdf4llm集成包。

凭据

使用 PyMuPDF4LLMLoader 不需要凭据。

要启用模型调用的自动跟踪,请设置您的 LangSmith API 密钥:

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

安装

安装 langchain_communitylangchain-pymupdf4llm

%pip install -qU langchain_community langchain-pymupdf4llm
Note: you may need to restart the kernel to use updated packages.

初始化

现在我们可以实例化我们的模型对象并加载文档:

from langchain_pymupdf4llm import PyMuPDF4LLMLoader

file_path = "./example_data/layout-parser-paper.pdf"
loader = PyMuPDF4LLMLoader(file_path)

负荷

docs = loader.load()
docs[0]
Document(metadata={'producer': 'pdfTeX-1.40.21', 'creator': 'LaTeX with hyperref', 'creationdate': '2021-06-22T01:27:10+00:00', 'source': './example_data/layout-parser-paper.pdf', 'file_path': './example_data/layout-parser-paper.pdf', 'total_pages': 16, 'format': 'PDF 1.5', 'title': '', 'author': '', 'subject': '', 'keywords': '', 'moddate': '2021-06-22T01:27:10+00:00', 'trapped': '', 'modDate': 'D:20210622012710Z', 'creationDate': 'D:20210622012710Z', 'page': 0}, page_content='\`\`\`\nLayoutParser: A Unified Toolkit for Deep\n\n## Learning Based Document Image Analysis\n\n\`\`\`\n\nZejiang Shen[1] (�), Ruochen Zhang[2], Melissa Dell[3], Benjamin Charles Germain\nLee[4], Jacob Carlson[3], and Weining Li[5]\n\n1 Allen Institute for AI\n\`\`\`\n              shannons@allenai.org\n\n\`\`\`\n2 Brown University\n\`\`\`\n             ruochen zhang@brown.edu\n\n\`\`\`\n3 Harvard University\n_{melissadell,jacob carlson}@fas.harvard.edu_\n4 University of Washington\n\`\`\`\n              bcgl@cs.washington.edu\n\n\`\`\`\n5 University of Waterloo\n\`\`\`\n              w422li@uwaterloo.ca\n\n\`\`\`\n\n**Abstract. 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 important 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 applications. The core LayoutParser library comes with a set of simple and\nintuitive interfaces for applying and customizing DL models for layout detection, 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 digitization pipelines. We demonstrate that LayoutParser is helpful for both\nlightweight and large-scale digitization pipelines in real-word use cases.\n[The library is publicly available at https://layout-parser.github.io.](https://layout-parser.github.io)\n\n**Keywords: Document Image Analysis · Deep Learning · Layout Analysis**\n\n    - Character Recognition · Open Source library · Toolkit.\n\n### 1 Introduction\n\n\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,\n\n')
import pprint

pprint.pp(docs[0].metadata)
{'producer': 'pdfTeX-1.40.21',
'creator': 'LaTeX with hyperref',
'creationdate': '2021-06-22T01:27:10+00:00',
'source': './example_data/layout-parser-paper.pdf',
'file_path': './example_data/layout-parser-paper.pdf',
'total_pages': 16,
'format': 'PDF 1.5',
'title': '',
'author': '',
'subject': '',
'keywords': '',
'moddate': '2021-06-22T01:27:10+00:00',
'trapped': '',
'modDate': 'D:20210622012710Z',
'creationDate': 'D:20210622012710Z',
'page': 0}

延迟加载

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
from IPython.display import Markdown, display

part = pages[0].page_content[778:1189]
print(part)
# Markdown rendering
display(Markdown(part))
pprint.pp(pages[0].metadata)
{'producer': 'pdfTeX-1.40.21',
'creator': 'LaTeX with hyperref',
'creationdate': '2021-06-22T01:27:10+00:00',
'source': './example_data/layout-parser-paper.pdf',
'file_path': './example_data/layout-parser-paper.pdf',
'total_pages': 16,
'format': 'PDF 1.5',
'title': '',
'author': '',
'subject': '',
'keywords': '',
'moddate': '2021-06-22T01:27:10+00:00',
'trapped': '',
'modDate': 'D:20210622012710Z',
'creationDate': 'D:20210622012710Z',
'page': 10}

metadata 属性至少包含以下键:

  • page (如果处于 page 模式)
  • total_page
  • 创建日期
  • 造物主
  • 制作人

其他元数据特定于每个解析器。 这些信息可能会有所帮助(例如,对您的 PDF 进行分类)。

拆分模式和自定义页面分隔符

加载 PDF 文件时,您可以通过两种不同的方式进行拆分:

  • 按页面
  • 作为单个文本流

默认情况下,PyMuPDF4LLMLoader 将按页面拆分 PDF。

按页提取 PDF。每个页面都被提取为 langchain Document 对象:

loader = PyMuPDF4LLMLoader(
"./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',
'source': './example_data/layout-parser-paper.pdf',
'file_path': './example_data/layout-parser-paper.pdf',
'total_pages': 16,
'format': 'PDF 1.5',
'title': '',
'author': '',
'subject': '',
'keywords': '',
'moddate': '2021-06-22T01:27:10+00:00',
'trapped': '',
'modDate': 'D:20210622012710Z',
'creationDate': 'D:20210622012710Z',
'page': 0}

在此模式下,PDF 按页面拆分,生成的 Documents 元数据包含page(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(这样我们就不会将某些段落切成两半)。在这种情况下,您可以使用 single 模式:

将整个 PDF 提取为单个 langchain Document 对象:

loader = PyMuPDF4LLMLoader(
"./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',
'source': './example_data/layout-parser-paper.pdf',
'file_path': './example_data/layout-parser-paper.pdf',
'total_pages': 16,
'format': 'PDF 1.5',
'title': '',
'author': '',
'subject': '',
'keywords': '',
'moddate': '2021-06-22T01:27:10+00:00',
'trapped': '',
'modDate': 'D:20210622012710Z',
'creationDate': 'D:20210622012710Z'}

从逻辑上讲,在这种模式下,page(page_number) 元数据消失。以下是如何清楚地识别页面在文本流中的结束位置:

添加自定义pages_delimiter以识别单个模式下页面的结束位置:

loader = PyMuPDF4LLMLoader(
"./example_data/layout-parser-paper.pdf",
mode="single",
pages_delimiter="\n-------THIS IS A CUSTOM END OF PAGE-------\n\n",
)
docs = loader.load()

part = docs[0].page_content[10663:11317]
print(part)
display(Markdown(part))

默认的pages_delimiter是 \n-----\n\n。 但这可以简单地是 \n,或者 \f 来清楚地指示页面更改,或者<!-- PAGE BREAK --> 用于在 Markdown 查看器中无缝注入,而没有视觉效果。

从 PDF 中提取图像

您可以从 PDF 中提取图像(以文本形式),并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

结果将插入到页面文本的末尾。

使用 rapidOCR 从 PDF 中提取图像:

%pip install -qU rapidocr-onnxruntime pillow
Note: you may need to restart the kernel to use updated packages.
from langchain_community.document_loaders.parsers import RapidOCRBlobParser

loader = PyMuPDF4LLMLoader(
"./example_data/layout-parser-paper.pdf",
mode="page",
extract_images=True,
images_parser=RapidOCRBlobParser(),
)
docs = loader.load()

part = docs[5].page_content[1863:]
print(part)
display(Markdown(part))
API 参考:RapidOCRBlobParser

请注意,RapidOCR 旨在处理中文和英文,而不是其他语言。

使用 Tesseract 从 PDF 中提取图像:

%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 = PyMuPDF4LLMLoader(
"./example_data/layout-parser-paper.pdf",
mode="page",
extract_images=True,
images_parser=TesseractBlobParser(),
)
docs = loader.load()

print(docs[5].page_content[1863:])
API 参考:TesseractBlobParser

使用多模态模型从 PDF 中提取图像:

%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 = PyMuPDF4LLMLoader(
"./example_data/layout-parser-paper.pdf",
mode="page",
extract_images=True,
images_parser=LLMImageBlobParser(
model=ChatOpenAI(model="gpt-4o-mini", max_tokens=1024)
),
)
docs = loader.load()

print(docs[5].page_content[1863:])

从 PDF 中提取表格

使用 PyMUPDF4LLM,您可以从 PDF 中提取 markdown 格式的表格:

loader = PyMuPDF4LLMLoader(
"./example_data/layout-parser-paper.pdf",
mode="page",
# "lines_strict" is the default strategy and
# is the most accurate for tables with column and row lines,
# but may not work well with all documents.
# "lines" is a less strict strategy that may work better with
# some documents.
# "text" is the least strict strategy and may work better
# with documents that do not have tables with lines.
table_strategy="lines",
)
docs = loader.load()

part = docs[4].page_content[3210:]
print(part)
display(Markdown(part))

使用文件

许多文档加载程序都涉及解析文件。此类加载器之间的区别通常源于文件的解析方式,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,但您需要不同的解析逻辑来将该二进制数据转换为文本。

因此,将解析逻辑与加载逻辑分离可能会有所帮助,这样可以更轻松地重用给定的解析器,而不管数据是如何加载的。 您可以使用此策略来分析具有相同解析参数的不同文件。

from langchain_community.document_loaders import FileSystemBlobLoader
from langchain_community.document_loaders.generic import GenericLoader
from langchain_pymupdf4llm import PyMuPDF4LLMParser

loader = GenericLoader(
blob_loader=FileSystemBlobLoader(
path="./example_data/",
glob="*.pdf",
),
blob_parser=PyMuPDF4LLMParser(),
)
docs = loader.load()

part = docs[0].page_content[:562]
print(part)
display(Markdown(part))

API 参考

有关所有 PyMuPDF4LLMLoader 功能和配置的详细文档,请访问 GitHub 存储库:https://github.com/lakinduboteju/langchain-pymupdf4llm