UnstructuredXMLLoader 集成

os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")
os.environ["LANGSMITH_TRACING"] = "true"

pip install -qU langchain_community

from langchain_community.document_loaders import UnstructuredXMLLoader

loader = UnstructuredXMLLoader(
    "./example_data/factbook.xml",
)

docs = loader.load()
docs[0]

Document(metadata={'source': './example_data/factbook.xml'}, page_content='United States\n\nWashington, DC\n\nJoe Biden\n\nBaseball\n\nCanada\n\nOttawa\n\nJustin Trudeau\n\nHockey\n\nFrance\n\nParis\n\nEmmanuel Macron\n\nSoccer\n\nTrinidad & Tobado\n\nPort of Spain\n\nKeith Rowley\n\nTrack & Field')

print(docs[0].metadata)

{'source': './example_data/factbook.xml'}

page = []
for doc in loader.lazy_load():
    page.append(doc)
    if len(page) >= 10:
        # 执行一些分页操作，例如
        # index.upsert(page)

        page = []