Skip to main content
Open In ColabOpen on GitHub

Amazon Textract

Amazon Textract 是一项机器学习 (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、理解并从表单和表格中提取数据。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（当表单更改时通常需要更新）的简单 OCR 软件进行提取。为了克服这些手动且成本高昂的过程，Textract 利用 ML 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；更多信息请参见 文档。

以下示例演示了如何将 Amazon Textract 与 LangChain 结合作为 DocumentLoader 使用。

%pip install --upgrade --quiet  boto3 langchain-openai tiktoken python-dotenv
%pip install --upgrade --quiet  "amazon-textract-caller>=0.2.0"

示例 1​

第一个示例使用本地文件，该文件内部将发送到 Amazon Textract 同步 API DetectDocumentText。

本地文件或像 HTTP:// 这样的 URL 端点对于 Textract 仅限于单页文档。 多页文档必须存储在 S3 中。此示例文件是一个 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​

下一个示例从 HTTPS 端点加载文件。 它必须是单页文件，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​

处理多页文档需要该文档位于 S3 上。示例文档位于 us-east-2 存储桶中，并且 Textract 需要在该相同区域进行调用才能成功。因此，我们在客户端设置了 region_name，并将其传递给加载器，以确保 Textract 从 us-east-2 调用。你也可以让你的 notebook 运行在 us-east-2 区域，将 AWS_DEFAULT_REGION 设置为 us-east-2；或者当在不同环境中运行时，传入一个具有该区域名称的 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()

现在获取页数来验证响应（打印完整响应会很长……）。我们预计有 16 页。

len(documents)
16

示例 4​

你可以选择向 AmazonTextractPDFLoader 传递一个名为 linearization_config 的附加参数，该参数将决定 Textract 运行后解析器如何线性化文本输出。

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 的使用方式与其他加载器在链中的使用方式相同。 Textract 本身确实有一个 Query 功能，它提供了与本示例中 QA 链类似的功能，也值得了解一下。

# 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 autors?"]

chain.run(input_documents=documents, question=query)
API Reference:load_qa_chain | OpenAI
' 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,'