Parser Router

ParserRouter is designed to identify the appropriate ParserType for loaded elements, accepting either a JSON file path or an in-memory list of element dictionaries.

It identifies the parser type by inspecting the source_type field in the metadata of the first element, and returns the result as a dictionary keyed by ParserType.KEY, or marks it as uncategorized if no match is found.

Prerequisites

If you want to try the snippet code in this page:

• 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"

Windows Powershell

Windows Command Prompt

You can use the following as a sample file: pymupdfloader-output.json

Running the Router

1

Create a script called main.py:

Using a path to a JSON file

from gllm_docproc.dpo_router.parser_router import ParserRouter
from gllm_docproc.model.parser_type import ParserType

# Example source: path to loaded elements JSON file
source = "./loaded_elements.json"

# Initialize ParserRouter
router = ParserRouter()

# Route the file to get the parser type
result = router.route(source)

# Access the detected parser type
print(f"Detected parser type: {result[ParserType.KEY]}")

Using list of element dictionaries

2

Run the script:

python main.py

3

Example output:

Detected parser type: pdf_parser

The returned dictionary has:

• Key: ParserType.KEY ("parser_type")

• Value: one of the values defined in ParserType, such as "pdf_parser", "docx_parser", "audio_parser", etc.