法律文档摘要

details_to_extract = [
    "Parties involved (sublessor, sublessee, and original lessor)",
    "Property details (address, description, and permitted use)",
    "Term and rent (start date, end date, monthly rent, and security deposit)",
    "Responsibilities (utilities, maintenance, and repairs)",
    "Consent and notices (landlord's consent, and notice requirements)",
    "Special provisions (furniture, parking, and subletting restrictions)",
]

from io import BytesIO
import re

import pypdf
import requests


def get_llm_text(pdf_file):
    reader = pypdf.PdfReader(pdf_file)
    text = "\n".join([page.extract_text() for page in reader.pages])

    # 移除页码
    text = re.sub(r"\n\s*\d+\s*\n", "\n", text)

    # 移除多余的空白字符
    text = re.sub(r"\s+", " ", text)

    return text


# 根据 GitHub 仓库创建完整 URL
url = "https://raw.githubusercontent.com/anthropics/anthropic-cookbook/main/skills/summarization/data/Sample Sublease Agreement.pdf"
url = url.replace(" ", "%20")

# 将 PDF 文件下载到内存中
response = requests.get(url)

# 从内存加载 PDF
pdf_file = BytesIO(response.content)

document_text = get_llm_text(pdf_file)
print(document_text[:50000])

# 初始化 Anthropic 客户端
client = anthropic.Anthropic()


def summarize_document(
    text, details_to_extract, model="claude-opus-4-8", max_tokens=1000
):
    # 格式化待提取的详细信息，以便放入提示的上下文中
    details_to_extract_str = "\n".join(details_to_extract)

    # 提示模型对转租协议进行总结
    prompt = f"""Summarize the following sublease agreement. Focus on these key aspects:

    {details_to_extract_str}

    Provide the summary in bullet points nested within the XML header for each section. For example:

    <parties involved>
    - Sublessor: [Name]
    // Add more details as needed
    </parties involved>

    If any information is not explicitly stated in the document, note it as "Not specified". Do not preamble.

    Sublease agreement text:
    {text}
    """

    response = client.messages.create(
        model=model,
        max_tokens=max_tokens,
        system="You are a legal analyst specializing in real estate law, known for highly accurate and detailed summaries of sublease agreements.",
        messages=[
            {"role": "user", "content": prompt},
        ],
    )

    return response.content[0].text


sublease_summary = summarize_document(document_text, details_to_extract)
print(sublease_summary)

# 初始化 Anthropic 客户端
client = anthropic.Anthropic()


def chunk_text(text, chunk_size=20000):
    return [text[i : i + chunk_size] for i in range(0, len(text), chunk_size)]


def summarize_long_document(
    text, details_to_extract, model="claude-opus-4-8", max_tokens=1000
):
    # 格式化要提取的详细信息，以便放入提示的上下文中
    details_to_extract_str = "\n".join(details_to_extract)

    # 遍历各个分块并对每个分块进行总结
    chunk_summaries = [
        summarize_document(
            chunk, details_to_extract, model=model, max_tokens=max_tokens
        )
        for chunk in chunk_text(text)
    ]

    final_summary_prompt = f"""

    You are looking at the chunked summaries of multiple documents that are all related.
    Combine the following summaries of the document from different truthful sources into a coherent overall summary:

    <chunked_summaries>
    {"".join(chunk_summaries)}
    </chunked_summaries>

    Focus on these key aspects:
    {details_to_extract_str}

    Provide the summary in bullet points nested within the XML header for each section. For example:

    <parties involved>
    - Sublessor: [Name]
    // Add more details as needed
    </parties involved>

    If any information is not explicitly stated in the document, note it as "Not specified". Do not preamble.
    """

    response = client.messages.create(
        model=model,
        max_tokens=max_tokens,
        system="You are a legal expert that summarizes notes on one document.",
        messages=[
            {"role": "user", "content": final_summary_prompt},
        ],
    )

    return response.content[0].text


long_summary = summarize_long_document(document_text, details_to_extract)
print(long_summary)