Is Parxy suitable for RAG pipelines?

Absolutely. Its ability to extract structured text at the block or span level makes it ideal for preparing high-quality data for retrieval-augmented generation.

Can I optimize PDF file sizes with this skill?

Yes, the skill includes tools to compress images, subset fonts, and scrub metadata to significantly reduce PDF file sizes.

Which document parsers does Parxy support?

Parxy supports multiple drivers including PyMuPDF, LlamaParse, Unstructured, PdfAct, and LLMWhisperer through a unified model.

Can I use Parxy to convert PDFs to Markdown?

Yes, Parxy includes built-in commands and methods to convert documents to Markdown, which is ideal for LLM contexts.

Does Parxy support batch processing?

Yes, it provides a batch processing engine with multi-worker support and streaming results for handling large document sets efficiently.

Parxy Document Processing

Name: Parxy Document Processing
Author: OneOffTech

byOneOffTech

•

데이터 과학 및 ML

Parses, converts, and manipulates documents through a unified interface supporting multiple engines like LlamaParse and PyMuPDF.

Parxy is a document processing gateway designed to streamline the extraction of structured data from PDFs and other document formats. By providing a consistent API for various parsing engines—including PyMuPDF for speed, LlamaParse for complex OCR, and Unstructured for multi-format support—it eliminates the complexity of managing disparate libraries. Beyond parsing, it offers robust PDF manipulation capabilities such as merging, splitting, and optimization, making it an essential tool for developers building RAG pipelines, document management systems, or data extraction workflows.

주요 기능

01Unified API for multiple parsing drivers including LlamaParse, PyMuPDF, and Unstructured.

02Advanced PDF manipulation including merging, splitting, and file optimization.

03Granular text extraction at page, block, line, span, or character levels.

04Batch processing with support for multi-worker streaming and per-file configuration.

058 GitHub stars

06Embedded attachment management for adding, extracting, or removing PDF files.

사용 사례

01Converting complex PDFs into Markdown for LLM ingestion and RAG pipelines.

02Optimizing and cleaning PDF files by scrubbing metadata and compressing images.

03Automating batch document processing with high-performance multi-threading.

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add oneofftech/parxy skills

For use in Claude.ai and ChatGPT

Download Skill