Inspired by Daniel Gross’s snippet here: https://gist.github.com/danielgross/3ab4104e14faccc12b49200843adab21

​
Overview

​
Integration details

ClassPackageLocalSerializableJS support
MathPixPDFLoaderlangchain-community✅❌❌

​
Loader features

SourceDocument Lazy LoadingNative Async Support
MathPixPDFLoader✅❌

​
Setup

​
Credentials

Sign up for Mathpix and create an API key to set the MATHPIX_API_KEY variables in your environment 
import getpass
import os

if "MATHPIX_API_KEY" not in os.environ:
    os.environ["MATHPIX_API_KEY"] = getpass.getpass("Enter your Mathpix API key: ")
To enable automated tracing of your model calls, set your LangSmith API key: 
# os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")
# os.environ["LANGSMITH_TRACING"] = "true"

​
Installation

Install langchain-community. 
%pip install -qU langchain-community

​
Initialization

Now we are ready to initialize our loader: 
from langchain_community.document_loaders import MathpixPDFLoader

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

​
Load

docs = loader.load()
docs[0]

print(docs[0].metadata)

​
Lazy Load

page = []
for doc in loader.lazy_load():
    page.append(doc)
    if len(page) >= 10:
        # do some paged operation, e.g.
        # index.upsert(page)

        page = []

​
API reference

For detailed documentation of all MathpixPDFLoader features and configurations head to the API reference: https://python.langchain.com/api_reference/community/document_loaders/langchain_community.document_loaders.pdf.MathpixPDFLoader.html