跳至主要內容

PyPDFium2Loader

這個筆記本提供了一個快速入門指南，以開始使用 PyPDFium2 文件載入器。 有關所有 __ModuleName__Loader 功能和配置的詳細文檔，請前往API 參考文檔。

總覽​

整合細節​

類別套件本地可序列化JS 支援
PyPDFium2Loaderlangchain_community✅❌❌

載入器功能​

來源文件延遲載入原生非同步支援
PyPDFium2Loader✅❌

設定​

要使用 PyPDFium2 文件載入器，您需要安裝 langchain-community 整合套件。

憑證​

不需要憑證。

如果您想要自動獲得一流的模型呼叫追蹤，您也可以通過取消註釋下方內容來設定您的LangSmith API 金鑰

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

安裝​

安裝 langchain_community。

%pip install -qU langchain_community

初始化​

現在我們可以實例化我們的模型物件並載入文件

from langchain_community.document_loaders import PyPDFium2Loader

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

載入​

docs = loader.load()
docs[0]
Document(metadata={'source': './example_data/layout-parser-paper.pdf', 'page': 0}, page_content='LayoutParser: A Unified Toolkit for Deep\r\nLearning Based Document Image Analysis\r\nZejiang Shen\r\n1\r\n(), Ruochen Zhang\r\n2\r\n, Melissa Dell\r\n3\r\n, Benjamin Charles Germain\r\nLee\r\n4\r\n, Jacob Carlson\r\n3\r\n, and Weining Li\r\n5\r\n1 Allen Institute for AI\r\nshannons@allenai.org 2 Brown University\r\nruochen zhang@brown.edu 3 Harvard University\r\n{melissadell,jacob carlson}@fas.harvard.edu\r\n4 University of Washington\r\nbcgl@cs.washington.edu 5 University of Waterloo\r\nw422li@uwaterloo.ca\r\nAbstract. Recent advances in document image analysis (DIA) have been\r\nprimarily driven by the application of neural networks. Ideally, research\r\noutcomes could be easily deployed in production and extended for further\r\ninvestigation. However, various factors like loosely organized codebases\r\nand sophisticated model configurations complicate the easy reuse of im\x02portant innovations by a wide audience. Though there have been on-going\r\nefforts to improve reusability and simplify deep learning (DL) model\r\ndevelopment in disciplines like natural language processing and computer\r\nvision, none of them are optimized for challenges in the domain of DIA.\r\nThis represents a major gap in the existing toolkit, as DIA is central to\r\nacademic research across a wide range of disciplines in the social sciences\r\nand humanities. This paper introduces LayoutParser, an open-source\r\nlibrary for streamlining the usage of DL in DIA research and applica\x02tions. The core LayoutParser library comes with a set of simple and\r\nintuitive interfaces for applying and customizing DL models for layout de\x02tection, character recognition, and many other document processing tasks.\r\nTo promote extensibility, LayoutParser also incorporates a community\r\nplatform for sharing both pre-trained models and full document digiti\x02zation pipelines. We demonstrate that LayoutParser is helpful for both\r\nlightweight and large-scale digitization pipelines in real-word use cases.\r\nThe library is publicly available at https://layout-parser.github.io.\r\nKeywords: Document Image Analysis· Deep Learning· Layout Analysis\r\n· Character Recognition· Open Source library· Toolkit.\r\n1 Introduction\r\nDeep Learning(DL)-based approaches are the state-of-the-art for a wide range of\r\ndocument image analysis (DIA) tasks including document image classification [11,\r\narXiv:2103.15348v2 [cs.CV] 21 Jun 2021\n')
print(docs[0].metadata)
{'source': './example_data/layout-parser-paper.pdf', 'page': 0}

延遲載入​

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

        page = []

API 參考文檔​

有關所有 PyPDFium2Loader 功能和配置的詳細文檔，請前往 API 參考文檔： https://langchain-python.dev.org.tw/api_reference/community/document_loaders/langchain_community.document_loaders.pdf.PyPDFium2Loader.html

此頁面是否對您有幫助？