跳到主要内容
Amazon Textract 是一种机器学习 (ML) 服务，可自动从扫描文档中提取文本、手写内容和数据。 它超越了简单的光学字符识别 (OCR)，能够识别、理解并从表格和表单中提取数据。如今，许多公司手动从 PDF、图像、表格和表单等扫描文档中提取数据，或者通过需要手动配置（并且在表单更改时通常必须更新）的简单 OCR 软件进行提取。为了克服这些手动且昂贵的过程，Textract 利用机器学习来读取和处理任何类型的文档，无需人工干预即可准确提取文本、手写内容、表格和其他数据。
Textract 支持 JPEG、PNG、PDF 和 TIFF 文件格式；更多信息可在文档中找到。 以下示例演示了 Amazon Textract 与 LangChain 结合作为 DocumentLoader 的用法。
pip install -qU  boto3 langchain-openai tiktoken python-dotenv

pip install -qU  "amazon-textract-caller>=0.2.0"

​
示例 1：从本地文件加载

第一个示例使用本地文件，该文件将在内部发送到 Amazon Textract 同步 API DetectDocumentText。 本地文件或 HTTP:// 等 URL 端点仅限于 Textract 的单页文档。多页文档必须驻留在 S3 上。这个示例文件是一个 jpeg。
from langchain_community.document_loaders import AmazonTextractPDFLoader

loader = AmazonTextractPDFLoader("example_data/alejandro_rosalez_sample-small.jpeg")
documents = loader.load()
文件的输出 
documents

[Document(page_content='Patient Information First Name: ALEJANDRO Last Name: ROSALEZ Date of Birth: 10/10/1982 Sex: M Marital Status: MARRIED Email Address: Address: 123 ANY STREET City: ANYTOWN State: CA Zip Code: 12345 Phone: 646-555-0111 Emergency Contact 1: First Name: CARLOS Last Name: SALAZAR Phone: 212-555-0150 Relationship to Patient: BROTHER Emergency Contact 2: First Name: JANE Last Name: DOE Phone: 650-555-0123 Relationship FRIEND to Patient: Did you feel fever or feverish lately? Yes No Are you having shortness of breath? Yes No Do you have a cough? Yes No Did you experience loss of taste or smell? Yes No Where you in contact with any confirmed COVID-19 positive patients? Yes No Did you travel in the past 14 days to any regions affected by COVID-19? Yes No Patient Information First Name: ALEJANDRO Last Name: ROSALEZ Date of Birth: 10/10/1982 Sex: M Marital Status: MARRIED Email Address: Address: 123 ANY STREET City: ANYTOWN State: CA Zip Code: 12345 Phone: 646-555-0111 Emergency Contact 1: First Name: CARLOS Last Name: SALAZAR Phone: 212-555-0150 Relationship to Patient: BROTHER Emergency Contact 2: First Name: JANE Last Name: DOE Phone: 650-555-0123 Relationship FRIEND to Patient: Did you feel fever or feverish lately? Yes No Are you having shortness of breath? Yes No Do you have a cough? Yes No Did you experience loss of taste or smell? Yes No Where you in contact with any confirmed COVID-19 positive patients? Yes No Did you travel in the past 14 days to any regions affected by COVID-19? Yes No ', metadata={'source': 'example_data/alejandro_rosalez_sample-small.jpeg', 'page': 1})]

​
示例 2：从 URL 加载

下一个示例从 HTTPS 端点加载文件。它必须是单页的，因为 Amazon Textract 要求所有多页文档都存储在 S3 上。 
from langchain_community.document_loaders import AmazonTextractPDFLoader

loader = AmazonTextractPDFLoader(
    "https://amazon-textract-public-content.s3.us-east-2.amazonaws.com/langchain/alejandro_rosalez_sample_1.jpg"
)
documents = loader.load()

documents

[Document(page_content='Patient Information First Name: ALEJANDRO Last Name: ROSALEZ Date of Birth: 10/10/1982 Sex: M Marital Status: MARRIED Email Address: Address: 123 ANY STREET City: ANYTOWN State: CA Zip Code: 12345 Phone: 646-555-0111 Emergency Contact 1: First Name: CARLOS Last Name: SALAZAR Phone: 212-555-0150 Relationship to Patient: BROTHER Emergency Contact 2: First Name: JANE Last Name: DOE Phone: 650-555-0123 Relationship FRIEND to Patient: Did you feel fever or feverish lately? Yes No Are you having shortness of breath? Yes No Do you have a cough? Yes No Did you experience loss of taste or smell? Yes No Where you in contact with any confirmed COVID-19 positive patients? Yes No Did you travel in the past 14 days to any regions affected by COVID-19? Yes No Patient Information First Name: ALEJANDRO Last Name: ROSALEZ Date of Birth: 10/10/1982 Sex: M Marital Status: MARRIED Email Address: Address: 123 ANY STREET City: ANYTOWN State: CA Zip Code: 12345 Phone: 646-555-0111 Emergency Contact 1: First Name: CARLOS Last Name: SALAZAR Phone: 212-555-0150 Relationship to Patient: BROTHER Emergency Contact 2: First Name: JANE Last Name: DOE Phone: 650-555-0123 Relationship FRIEND to Patient: Did you feel fever or feverish lately? Yes No Are you having shortness of breath? Yes No Do you have a cough? Yes No Did you experience loss of taste or smell? Yes No Where you in contact with any confirmed COVID-19 positive patients? Yes No Did you travel in the past 14 days to any regions affected by COVID-19? Yes No ', metadata={'source': 'example_data/alejandro_rosalez_sample-small.jpeg', 'page': 1})]

​
示例 3：加载多页 PDF 文档

处理多页文档需要文档位于 S3 上。示例文档位于 us-east-2 的存储桶中，并且 Textract 需要在该同一区域中调用才能成功，因此我们在客户端上设置了 region_name 并将其传递给加载器，以确保 Textract 是从 us-east-2 调用的。您也可以让您的笔记本在 us-east-2 中运行，将 AWS_DEFAULT_REGION 设置为 us-east-2，或者在不同环境中运行时，传递一个带有该区域名称的 boto3 Textract 客户端，如下面的单元格所示。 
import boto3

textract_client = boto3.client("textract", region_name="us-east-2")

file_path = "s3://amazon-textract-public-content/langchain/layout-parser-paper.pdf"
loader = AmazonTextractPDFLoader(file_path, client=textract_client)
documents = loader.load()
现在获取页数以验证响应（打印完整响应会很长……）。我们预计有 16 页。 
len(documents)

16

​
示例 4：自定义输出格式

当 Amazon Textract 处理 PDF 时，它会提取所有文本，包括页眉、页脚和页码等元素。这些额外的信息可能产生“噪音”，降低输出的有效性。 将文档的二维布局转换为干净的一维文本字符串的过程称为线性化。 AmazonTextractPDFLoader 通过 linearization_config 参数为您提供了对该过程的精确控制。您可以使用它来指定从最终输出中排除哪些元素。 以下示例展示了如何隐藏页眉、页脚和图片，从而获得更清晰的文本块；如需更高级的用例，请参阅此AWS 博客文章。
from langchain_community.document_loaders import AmazonTextractPDFLoader
from textractor.data.text_linearization_config import TextLinearizationConfig

loader = AmazonTextractPDFLoader(
    "s3://amazon-textract-public-content/langchain/layout-parser-paper.pdf",
    linearization_config=TextLinearizationConfig(
        hide_header_layout=True,
        hide_footer_layout=True,
        hide_figure_layout=True,
    ),
)
documents = loader.load()

​
在 LangChain 链中使用 AmazonTextractPDFLoader（例如 OpenAI）

AmazonTextractPDFLoader 可以像其他加载器一样在链中使用。Textract 本身有一个查询功能，它提供了与此示例中的 QA 链类似的功能，也值得一试。 
# You can store your OPENAI_API_KEY in a .env file as well
# import os
# from dotenv import load_dotenv

# load_dotenv()

# Or set the OpenAI key in the environment directly
import os

os.environ["OPENAI_API_KEY"] = "your-OpenAI-API-key"

from langchain.chains.question_answering import load_qa_chain
from langchain_openai import OpenAI

chain = load_qa_chain(llm=OpenAI(), chain_type="map_reduce")
query = ["Who are the authors?"]

chain.run(input_documents=documents, question=query)

' The authors are Zejiang Shen, Ruochen Zhang, Melissa Dell, Benjamin Charles Germain Lee, Jacob Carlson, Weining Li, Gardner, M., Grus, J., Neumann, M., Tafjord, O., Dasigi, P., Liu, N., Peters, M., Schmitz, M., Zettlemoyer, L., Lukasz Garncarek, Powalski, R., Stanislawek, T., Topolski, B., Halama, P., Gralinski, F., Graves, A., Fernández, S., Gomez, F., Schmidhuber, J., Harley, A.W., Ufkes, A., Derpanis, K.G., He, K., Gkioxari, G., Dollár, P., Girshick, R., He, K., Zhang, X., Ren, S., Sun, J., Kay, A., Lamiroy, B., Lopresti, D., Mears, J., Jakeway, E., Ferriter, M., Adams, C., Yarasavage, N., Thomas, D., Zwaard, K., Li, M., Cui, L., Huang,'
在 GitHub 上编辑此页面源文件。
以编程方式连接这些文档到 Claude、VSCode 等，通过 MCP 获取实时答案。
© . This site is unofficial and not affiliated with LangChain, Inc.