Amazon Textract
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)，可以识别、理解和提取表单和表格中的数据。如今，许多公司手动从扫描文档（如 PDF、图像、表格和表单）中提取数据，或通过需要手动配置的简单 OCR 软件提取数据（当表单发生更改时，通常必须更新这些配置）。为了克服这些手动且昂贵的过程，
Textract使用 ML 读取和处理任何类型的文档，准确地提取文本、手写内容、表格和其他数据，无需任何手动操作。
此示例演示了将Amazon Textract 与 LangChain 结合用作 DocumentLoader。
Textract 支持PDF、TIFF、PNG 和JPEG 格式。
Textract 支持这些文档大小、语言和字符。
%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，该文件将在内部发送到 Amazon Textract 同步 API DetectDocumentText。
对于 Textract，本地文件或 HTTP:// 等 URL 端点限于单页文档。多页文档必须位于 S3 上。此示例文件为 jpeg。
from langchain_community.document_loaders import AmazonTextractPDFLoader
loader = AmazonTextractPDFLoader("example_data/alejandro_rosalez_sample-small.jpeg")
documents = loader.load()
API 参考：AmazonTextractPDFLoader
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()
API 参考：AmazonTextractPDFLoader
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
处理多页文档需要文档位于 S3 上。示例文档位于 us-east-2 中的一个存储桶中，并且 Textract 需要在同一区域中调用才能成功，因此我们在客户端上设置 region_name 并将其传递给加载程序以确保从 us-east-2 调用 Textract。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，或者在不同的环境中运行时，传入具有该区域名称的 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()
现在获取页面数以验证响应（打印完整响应将非常长……）。我们预计有 16 页。
len(documents)
16
示例 4
您可以选择将名为linearization_config 的附加参数传递给 AmazonTextractPDFLoader，这将确定 Textract 运行后解析器如何对文本输出进行线性化。
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()
API 参考：AmazonTextractPDFLoader
在 LangChain 链（例如 OpenAI）中使用 AmazonTextractPDFLoader
AmazonTextractPDFLoader 可以像使用其他加载程序一样在链中使用。Textract 本身确实有一个查询功能，它提供了与本示例中 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 autors?"]
chain.run(input_documents=documents, question=query)
API 参考：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,'