MathpixPDFLoader 集成

import getpass
import os

if "MATHPIX_API_KEY" not in os.environ:
    os.environ["MATHPIX_API_KEY"] = getpass.getpass("Enter your Mathpix API key: ")

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 MathpixPDFLoader

file_path = "./example_data/layout-parser-paper.pdf"
loader = MathpixPDFLoader(file_path)

docs = loader.load()
docs[0]

print(docs[0].metadata)

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 = []