PDF

gllm-docproc | Tutorial : PDF Parser | Use Case: Advanced DPO Pipeline | API Reference

PDF Parser is responsible for parsing the text structure within PDF documents. It maps loaded elements from the PDF Loader into structures such as header, title, footer, heading, and paragraph, based on their metadata (font size, font family, coordinates, etc.).

This page provides guide to use PDF Parser in Document Processing Orchestrator (DPO).

Prerequisites

This example specifically requires completion of all setup steps listed on the Prerequisites page.

Installation

Linux, macOS, or Windows WSL

# you can use a Conda environment
pip install --extra-index-url https://oauth2accesstoken:$(gcloud auth print-access-token)@glsdk.gdplabs.id/gen-ai-internal/simple/ "gllm-docproc[pdf]"

Windows Powershell

Windows Command Prompt

You can use the following as a sample file: loaded_elements.json.

1

Create a script called main.py:

import json

from gllm_docproc.parser.document import PDFParser

# loaded_elements (input) that you want to Parse
with open('./data/source/loaded_elements.json', 'r') as file:
    loaded_elements = json.load(file)

# initialize the PDF Parser
parser = PDFParser()

# parse loaded elements
parsed_elements = parser.parse(loaded_elements)

2

Run the script:

python main.py

3

The parser will generate the following: output JSON.