This notebook provides a quick overview for getting started with the WriterPDFParserdocument loader.

Writer'sPDF Parser converts PDF documents into other formats like text or Markdown. This is particularly useful when you need to extract and process text content from PDF files for further analysis or integration into your workflow. Inlangchain-writer, we provide usage of Writer's PDF Parser as a LangChain document parser.

Overview​

Integration details​

Class	Package	Local	Serializable	JS support	Package downloads	Package latest
PDFParser	langchain-writer	❌	❌	❌

Setup​

ThePDFParser is available in thelangchain-writer package:

%pip install--quiet-U langchain-writer

Credentials​

Sign up forWriter AI Studio to generate an API key (you can follow thisQuickstart). Then, set the WRITER_API_KEY environment variable:

import getpass
import os

ifnot os.getenv("WRITER_API_KEY"):
    os.environ["WRITER_API_KEY"]= getpass.getpass("Enter your Writer API key: ")

It's also helpful (but not needed) to set upLangSmith for best-in-class observability. If you wish to do so, you can set theLANGSMITH_TRACING andLANGSMITH_API_KEY environment variables:

# os.environ["LANGSMITH_TRACING"] = "true"
# os.environ["LANGSMITH_API_KEY"] = getpass.getpass()

Instantiation​

Next, instantiate an instance of the Writer PDF Parser with the desired output format:

from langchain_writer.pdf_parserimport PDFParser

parser= PDFParser(format="markdown")

Usage​

There are two ways to use the PDF Parser, either synchronously or asynchronously. In either case, the PDF Parser will return a list ofDocument objects, each containing the parsed content of a page from the PDF file.

Synchronous usage​

To invoke the PDF Parser synchronously, pass aBlob object to theparse method referencing the PDF file you want to parse:

from langchain_core.documents.baseimport Blob

file= Blob.from_path("../example_data/layout-parser-paper.pdf")

parsed_pages= parser.parse(blob=file)
parsed_pages

Asynchronous usage​

To invoke the PDF Parser asynchronously, pass aBlob object to theaparse method referencing the PDF file you want to parse:

parsed_pages_async=await parser.aparse(blob=file)
parsed_pages_async

API reference​

For detailed documentation of allPDFParser features and configurations, head to theAPI reference.

Additional resources​

You can find information about Writer's models (including costs, context windows, and supported input types) and tools in theWriter docs.