PPTX

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

PPTX Parser is responsible for parsing the shape structure within PPTX documents. It maps loaded elements from the PPTX Loader into structures such as title, paragraph, and footer, based on their placeholder types.

This page provides guide to use PPTX 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[pptx]"

Windows Powershell

Windows Command Prompt

You can use the following as a sample file: pptx-example.pptx.

1

Create a script called main.py:

from gllm_docproc.loader.pptx import PythonPPTXLoader
from gllm_docproc.parser.document import PPTXParser

source = "./data/source/pptx-example.pptx"

# initialize the PPTX Loader
loader = PythonPPTXLoader()

# load source
loaded_elements = loader.load(source)

# initialize the PPTX Parser
parser = PPTXParser()

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

2

Run the script:

python main.py

3

The loader & parser will generate the following: output JSON.