Extract equations, tables, and LaTeX from academic PDFs
Paddle OCR loader reads equations, symbols, and tables from PDFs for LlamaIndex document processing pipelines.
Why it matters
Parse academic PDF documents to extract mathematical equations, symbols, and tables in a structured format that can be indexed and processed by downstream AI systems.
Outcomes
What it gets done
Read equations and LaTeX math notation from PDF documents
Extract tables from academic papers with structure preserved
Parse mathematical symbols and formulas for indexing
Generate markdown output files with extracted content
Install
Add it to your toolbox
Run in your project directory:
curl -fsSL https://spark.entire.vc/get/li-reader-readers-paddle-ocr | bash Overview
Paddle OCR loader
Paddle OCR loader is a LlamaIndex document reader that reads equations, symbols, and tables included in PDFs. This OCR understands LaTeX math and tables. An output folder will be created with the same name as the PDF and `.mmd` extension. Use this loader when you need to read equations, symbols, and tables from PDF documents where LaTeX math understanding is required.
What it does
Paddle OCR loader is a document reader for LlamaIndex that reads equations, symbols, and tables included in PDFs. According to the documentation, this OCR understands LaTeX math and tables. An output folder will be created with the same name as the PDF and .mmd extension.
Inputs and outputs
You provide the file path to a PDF document. The loader returns LlamaIndex documents. An output folder will be created with the same name as the PDF and .mmd extension.
Usage
Install the package:
pip install llama-index-readers-paddle-ocr
Load documents from a PDF:
from llama_index.readers.paddle_ocr import PDFPaddleOCR
reader = PDFPaddleOCR()
pdf_path = Path("/path/to/pdf")
documents = reader.load_data(pdf_path)
Who it's for
This loader is for users who need to parse PDF documents containing equations, symbols, and tables with LaTeX math support.
Source README
Paddle OCR loader
pip install llama-index-readers-paddle-ocr
This loader reads the equations, symbols, and tables included in the PDF.
Users can input the path of the academic PDF document file which they want to parse. This OCR understands LaTeX math and tables.
Usage
Here's an example usage of the PDFPaddleOCR.
from llama_index.readers.paddle_ocr import PDFPaddleOCR
reader = PDFPaddleOCR()
pdf_path = Path("/path/to/pdf")
documents = reader.load_data(pdf_path)
Miscellaneous
An output folder will be created with the same name as the pdf and .mmd extension.
Discussion
Questions & comments · 0
Sign In Sign in to leave a comment.