Skip to main content
本笔记本介绍如何使用 Unstructured 文档加载器 加载多种类型的文件。Unstructured 当前支持加载文本文件、PowerPoint、HTML、PDF、图像等更多类型。 请参阅 Unstructured 获取更多关于在本地设置 Unstructured 的说明，包括设置所需的系统依赖项。

​
概述

​
集成详情

类包本地可序列化JS 支持
UnstructuredLoaderlangchain-unstructured✅❌✅

​
加载器特性

来源文档延迟加载原生异步支持
UnstructuredLoader✅❌

​
设置

​
凭证

默认情况下，langchain-unstructured 安装一个较小的版本，需要将分区逻辑卸载到 Unstructured API，这需要一个 API 密钥。如果您使用本地安装，则不需要 API 密钥。要获取您的 API 密钥，请访问 此网站 获取 API 密钥，然后在下面的单元格中设置它： 
import getpass
import os

if "UNSTRUCTURED_API_KEY" not in os.environ:
    os.environ["UNSTRUCTURED_API_KEY"] = getpass.getpass(
        "Enter your Unstructured API key: "
    )

​
安装

​
正常安装

运行本笔记本的其余部分需要以下包。 
# 安装包，与 API 分区兼容
pip install -qU langchain-unstructured unstructured-client unstructured "unstructured[pdf]" python-magic

​
本地安装

如果您希望在本地运行分区逻辑，则需要安装一系列系统依赖项，如 Unstructured 文档此处 所述。 例如，在 Mac 上，您可以使用以下命令安装所需的依赖项： 
# 基础依赖项
brew install libmagic poppler tesseract

# 如果解析 XML / HTML 文档：
brew install libxml2 libxslt
您可以使用以下命令安装本地所需的 pip 依赖项： 
pip install "langchain-unstructured[local]"

​
初始化

UnstructuredLoader 允许从多种不同的文件类型加载。要全面了解 unstructured 包，请参阅其 文档/。在此示例中，我们展示从文本文件和 PDF 文件加载。 
from langchain_unstructured import UnstructuredLoader

file_paths = [
    "./example_data/layout-parser-paper.pdf",
    "./example_data/state_of_the_union.txt",
]


loader = UnstructuredLoader(file_paths)

​
加载

docs = loader.load()

docs[0]

INFO: pikepdf C++ to Python logger bridge initialized

Document(metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((16.34, 213.36), (16.34, 253.36), (36.34, 253.36), (36.34, 213.36)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2024-02-27T15:49:27', 'page_number': 1, 'filetype': 'application/pdf', 'category': 'UncategorizedText', 'element_id': 'd3ce55f220dfb75891b4394a18bcb973'}, page_content='1 2 0 2')

print(docs[0].metadata)

{'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((16.34, 213.36), (16.34, 253.36), (36.34, 253.36), (36.34, 213.36)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2024-02-27T15:49:27', 'page_number': 1, 'filetype': 'application/pdf', 'category': 'UncategorizedText', 'element_id': 'd3ce55f220dfb75891b4394a18bcb973'}

​
延迟加载

pages = []
for doc in loader.lazy_load():
    pages.append(doc)

pages[0]

Document(metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((16.34, 213.36), (16.34, 253.36), (36.34, 253.36), (36.34, 213.36)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2024-02-27T15:49:27', 'page_number': 1, 'filetype': 'application/pdf', 'category': 'UncategorizedText', 'element_id': 'd3ce55f220dfb75891b4394a18bcb973'}, page_content='1 2 0 2')

​
后处理

如果您需要在提取后对 unstructured 元素进行后处理，可以在实例化 UnstructuredLoader 时向 post_processors kwarg 传入一个 str -> str 函数列表。这同样适用于其他 Unstructured 加载器。下面是一个示例。 
from langchain_unstructured import UnstructuredLoader
from unstructured.cleaners.core import clean_extra_whitespace

loader = UnstructuredLoader(
    "./example_data/layout-parser-paper.pdf",
    post_processors=[clean_extra_whitespace],
)

docs = loader.load()

docs[5:10]

[Document(metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((16.34, 393.9), (16.34, 560.0), (36.34, 560.0), (36.34, 393.9)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2024-02-27T15:49:27', 'page_number': 1, 'parent_id': '89565df026a24279aaea20dc08cedbec', 'filetype': 'application/pdf', 'category': 'UncategorizedText', 'element_id': 'e9fa370aef7ee5c05744eb7bb7d9981b'}, page_content='2 v 8 4 3 5 1 . 3 0 1 2 : v i X r a'),
 Document(metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((157.62199999999999, 114.23496279999995), (157.62199999999999, 146.5141628), (457.7358962799999, 146.5141628), (457.7358962799999, 114.23496279999995)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2024-02-27T15:49:27', 'page_number': 1, 'filetype': 'application/pdf', 'category': 'Title', 'element_id': 'bde0b230a1aa488e3ce837d33015181b'}, page_content='LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis'),
 Document(metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((134.809, 168.64029940800003), (134.809, 192.2517444), (480.5464199080001, 192.2517444), (480.5464199080001, 168.64029940800003)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2024-02-27T15:49:27', 'page_number': 1, 'parent_id': 'bde0b230a1aa488e3ce837d33015181b', 'filetype': 'application/pdf', 'category': 'UncategorizedText', 'element_id': '54700f902899f0c8c90488fa8d825bce'}, page_content='Zejiang Shen1 ((cid:0)), Ruochen Zhang2, Melissa Dell3, Benjamin Charles Germain Lee4, Jacob Carlson3, and Weining Li5'),
 Document(metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((207.23000000000002, 202.57205439999996), (207.23000000000002, 311.8195408), (408.12676, 311.8195408), (408.12676, 202.57205439999996)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2024-02-27T15:49:27', 'page_number': 1, 'parent_id': 'bde0b230a1aa488e3ce837d33015181b', 'filetype': 'application/pdf', 'category': 'UncategorizedText', 'element_id': 'b650f5867bad9bb4e30384282c79bcfe'}, page_content='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'),
 Document(metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((162.779, 338.45008160000003), (162.779, 566.8455408), (454.0372021523199, 566.8455408), (454.0372021523199, 338.45008160000003)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2024-02-27T15:49:27', 'links': [{'text': ':// layout - parser . github . io', 'url': 'https://layout-parser.github.io', 'start_index': 1477}], 'page_number': 1, 'parent_id': 'bde0b230a1aa488e3ce837d33015181b', 'filetype': 'application/pdf', 'category': 'NarrativeText', 'element_id': 'cfc957c94fe63c8fd7c7f4bcb56e75a7'}, page_content='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.')]

​
Unstructured API

如果您想使用更小的包并获取最新的分区功能，可以 pip install unstructured-client 和 pip install langchain-unstructured。有关 UnstructuredLoader 的更多信息，请参阅 Unstructured 提供程序页面。 当您传入 api_key 并设置 partition_via_api=True 时，加载器将使用托管的 Unstructured 无服务器 API 处理您的文档。您可以 生成免费的 Unstructured API 密钥。 如果您想自托管 Unstructured API 或在本地运行，请查看 自托管 Unstructured API 的 Docker 镜像说明。 
from langchain_unstructured import UnstructuredLoader

loader = UnstructuredLoader(
    file_path="example_data/fake.docx",
    api_key=os.getenv("UNSTRUCTURED_API_KEY"),
    partition_via_api=True,
)

docs = loader.load()
docs[0]

INFO: Preparing to split document for partition.
INFO: Given file doesn't have '.pdf' extension, so splitting is not enabled.
INFO: Partitioning without split.
INFO: Successfully partitioned the document.

Document(metadata={'source': 'example_data/fake.docx', 'category_depth': 0, 'filename': 'fake.docx', 'languages': ['por', 'cat'], 'filetype': 'application/vnd.openxmlformats-officedocument.wordprocessingml.document', 'category': 'Title', 'element_id': '56d531394823d81787d77a04462ed096'}, page_content='Lorem ipsum dolor sit amet.')
您还可以通过 Unstructured API 使用 UnstructuredLoader 批量处理多个文件。 
loader = UnstructuredLoader(
    file_path=["example_data/fake.docx", "example_data/fake-email.eml"],
    api_key=os.getenv("UNSTRUCTURED_API_KEY"),
    partition_via_api=True,
)

docs = loader.load()

print(docs[0].metadata["filename"], ": ", docs[0].page_content[:100])
print(docs[-1].metadata["filename"], ": ", docs[-1].page_content[:100])

INFO: Preparing to split document for partition.
INFO: Given file doesn't have '.pdf' extension, so splitting is not enabled.
INFO: Partitioning without split.
INFO: Successfully partitioned the document.
INFO: Preparing to split document for partition.
INFO: Given file doesn't have '.pdf' extension, so splitting is not enabled.
INFO: Partitioning without split.
INFO: Successfully partitioned the document.

fake.docx :  Lorem ipsum dolor sit amet.
fake-email.eml :  Violets are blue

​
Unstructured SDK 客户端

使用 Unstructured API 进行分区依赖于 Unstructured SDK 客户端。 如果您想自定义客户端，则必须将 UnstructuredClient 实例传递给 UnstructuredLoader。下面是一个示例，展示如何自定义客户端的功能，例如使用您自己的 requests.Session()、传递替代的 server_url 以及自定义 RetryConfig 对象。有关自定义客户端或 sdk 客户端接受的其他参数的更多信息，请参阅 Unstructured Python SDK 文档和 API 参数 文档的客户端部分。请注意，所有 API 参数都应传递给 UnstructuredLoader。
警告：下面的示例可能未使用最新版本的 UnstructuredClient，并且在未来的版本中可能会有破坏性更改。有关最新示例，请参阅 Unstructured Python SDK 文档。
import requests
from langchain_unstructured import UnstructuredLoader
from unstructured_client import UnstructuredClient
from unstructured_client.utils import BackoffStrategy, RetryConfig

client = UnstructuredClient(
        api_key_auth=os.getenv(
        "UNSTRUCTURED_API_KEY"
    ),  # 注意：客户端 API 参数是 "api_key_auth" 而不是 "api_key"
        client=requests.Session(),  # 定义您自己的请求会话
        server_url="https://api.unstructuredapp.io/general/v0/general",  # 定义您自己的 API URL
        retry_config=RetryConfig(
                strategy="backoff",
                retry_connection_errors=True,
                backoff=BackoffStrategy(
                        initial_interval=500,
                        max_interval=60000,
                        exponent=1.5,
                        max_elapsed_time=900000,
        ),
    ),  # 定义您自己的重试配置
)

loader = UnstructuredLoader(
    "./example_data/layout-parser-paper.pdf",
        partition_via_api=True,
        client=client,
        split_pdf_page=True,
        split_pdf_page_range=[1, 10],
)

docs = loader.load()

print(docs[0].metadata["filename"], ": ", docs[0].page_content[:100])

INFO: Preparing to split document for partition.
INFO: Concurrency level set to 5
INFO: Splitting pages 1 to 10 (10 total)
INFO: Determined optimal split size of 2 pages.
INFO: Partitioning 5 files with 2 page(s) each.
INFO: Partitioning set #1 (pages 1-2).
INFO: Partitioning set #2 (pages 3-4).
INFO: Partitioning set #3 (pages 5-6).
INFO: Partitioning set #4 (pages 7-8).
INFO: Partitioning set #5 (pages 9-10).
INFO: HTTP Request: POST https://api.unstructuredapp.io/general/v0/general "HTTP/1.1 200 OK"
INFO: HTTP Request: POST https://api.unstructuredapp.io/general/v0/general "HTTP/1.1 200 OK"
INFO: HTTP Request: POST https://api.unstructuredapp.io/general/v0/general "HTTP/1.1 200 OK"
INFO: HTTP Request: POST https://api.unstructuredapp.io/general/v0/general "HTTP/1.1 200 OK"
INFO: Successfully partitioned set #1, elements added to the final result.
INFO: Successfully partitioned set #2, elements added to the final result.
INFO: Successfully partitioned set #3, elements added to the final result.
INFO: Successfully partitioned set #4, elements added to the final result.
INFO: Successfully partitioned set #5, elements added to the final result.
INFO: Successfully partitioned the document.

layout-parser-paper.pdf :  LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis

​
分块

UnstructuredLoader 不支持像旧加载器 UnstructuredFileLoader 和其他加载器那样使用 mode 参数来分组文本。相反，它支持“分块”。Unstructured 中的分块不同于您可能熟悉的其他分块机制，后者基于纯文本特征（如 “\n\n” 或 “\n” 等可能表示段落边界或列表项边界的字符序列）形成块。相反，所有文档都使用关于每种文档格式的特定知识进行拆分，将文档划分为语义单元（文档元素），我们只需要在单个元素超过所需的最大块大小时才诉诸文本拆分。通常，分块会组合连续的元素以形成尽可能大的块，而不超过最大块大小。分块会产生一个 CompositeElement、Table 或 TableChunk 元素序列。每个“块”是这三种类型之一的实例。 有关分块选项的更多详细信息，请参阅此 页面，但要重现与 mode="single" 相同的行为，您可以设置 chunking_strategy="basic"、max_characters=<某个非常大的数字> 和 include_orig_elements=False。 
from langchain_unstructured import UnstructuredLoader

loader = UnstructuredLoader(
    "./example_data/layout-parser-paper.pdf",
    chunking_strategy="basic",
    max_characters=1000000,
    include_orig_elements=False,
)

docs = loader.load()

print("Number of LangChain documents:", len(docs))
print("Length of text in the document:", len(docs[0].page_content))

Number of LangChain documents: 1
Length of text in the document: 42772

​
加载网页

UnstructuredLoader 在本地运行时接受 web_url kwarg，该 kwarg 会填充底层 Unstructured 分区 的 url 参数。这允许解析远程托管的文档，例如 HTML 网页。 用法示例： 
from langchain_unstructured import UnstructuredLoader

loader = UnstructuredLoader(web_url="https://www.example.com")
docs = loader.load()

for doc in docs:
    print(f"{doc}\n")

page_content='Example Domain' metadata={'category_depth': 0, 'languages': ['eng'], 'filetype': 'text/html', 'url': 'https://www.example.com', 'category': 'Title', 'element_id': 'fdaa78d856f9d143aeeed85bf23f58f8'}

page_content='This domain is for use in illustrative examples in documents. You may use this domain in literature without prior coordination or asking for permission.' metadata={'languages': ['eng'], 'parent_id': 'fdaa78d856f9d143aeeed85bf23f58f8', 'filetype': 'text/html', 'url': 'https://www.example.com', 'category': 'NarrativeText', 'element_id': '3652b8458b0688639f973fe36253c992'}

page_content='More information...' metadata={'category_depth': 0, 'link_texts': ['More information...'], 'link_urls': ['https://www.iana.org/domains/example'], 'languages': ['eng'], 'filetype': 'text/html', 'url': 'https://www.example.com', 'category': 'Title', 'element_id': '793ab98565d6f6d6f3a6d614e3ace2a9'}

​
API 参考

有关所有 UnstructuredLoader 功能和配置的详细文档，请前往 API 参考
在 GitHub 上编辑此页面 或 提交问题。
通过 MCP 将这些文档连接到 Claude、VSCode 等 以获取实时答案。