法律文件摘要

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])

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

    # 移除多餘的空白
    text = re.sub(r"\s+", " ", text)

    return text


# 從 GitHub 儲存庫建立完整的 URL
url = "https://raw.githubusercontent.com/anthropics/claude-cookbooks/main/capabilities/summarization/data/Sample Sublease Agreement.pdf"
url = url.replace(" ", "%20")

# 將 PDF 檔案下載至記憶體中
response = requests.get(url)

# 從記憶體載入 PDF
pdf_file = BytesIO(response.content)

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

# 初始化 Anthropic 用戶端
client = anthropic.Anthropic()


def summarize_document(
    text, details_to_extract, model="claude-opus-5-5", max_tokens=1000
):
    # 格式化要擷取的細節，以便放入提示的上下文中
    details_to_extract_str = "\n".join(details_to_extract)

    # 提示模型摘要轉租合約
    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 next(block.text for block in response.content if block.type == "text")


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

# 初始化 Anthropic 用戶端
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-5-5", max_tokens=1000
):
    # 格式化要擷取的細節，以便放入提示的上下文中
    details_to_extract_str = "\n".join(details_to_extract)

    # 逐一處理各個區塊並分別摘要
    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 next(block.text for block in response.content if block.type == "text")


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