unstructured-pdf-generation

Generate synthetic PDFs with JSON evaluation files for RAG use cases.

Updated Mar 10, 2026

Search Tags:#llm #rag #pdf generation #synthetic data #unstructured data #unity catalog

Ready to run

npx skills add https://github.com/slysik/databricks-claude-coding --skill unstructured-pdf-generation-slysik

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: unstructured-pdf-generation
Source: https://github.com/slysik/databricks-claude-coding/tree/main/.agents/skills/unstructured-pdf-generation
Command: npx skills add https://github.com/slysik/databricks-claude-coding --skill unstructured-pdf-generation-slysik

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates the creation of realistic synthetic PDF documents, complete with evaluation data, to streamline the development and testing of RAG systems and unstructured data applications.

Core Features & Use Cases

Synthetic PDF Generation: Creates LLM-generated PDF content based on detailed descriptions.
RAG Evaluation Data: Includes companion JSON files with questions and guidelines for automated RAG pipeline evaluation.
Unity Catalog Integration: Automatically uploads generated PDFs and JSON files to specified Unity Catalog Volumes.
Use Case: Generate 15 technical documentation PDFs for a new SaaS platform, including setup guides and API references, and have them automatically uploaded to a Unity Catalog Volume for immediate use in a RAG system.

Quick Start

Use the generate_pdf_documents MCP tool to create 10 technical documentation PDFs for a cloud infrastructure platform, saving them to the 'my_catalog' catalog and 'my_schema' schema.

Frequently Asked Questions about unstructured-pdf-generation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I generate synthetic PDFs for RAG evaluation?▼

To generate synthetic PDFs for RAG evaluation, provide a content description to the generation tool, which creates the PDF documents alongside companion JSON files containing evaluation questions and uploads them to Unity Catalog Volumes.

How does synthetic data generation work for unstructured PDF documents?▼

Synthetic data generation for unstructured PDFs uses an LLM to create realistic document content based on your detailed descriptions, producing both the PDF files and JSON evaluation guidelines for testing unstructured data pipelines.

Can I use Unity Catalog Volumes to store generated PDF documents?▼

Yes, you can store generated PDF documents in Unity Catalog Volumes by specifying your target catalog and schema during generation, which automatically uploads the synthetic PDFs and JSON evaluation files to the specified location.

What is the best way to create test PDFs for a RAG pipeline?▼

The best way to create test PDFs for a RAG pipeline is to generate synthetic documents with companion JSON evaluation files, allowing you to test retrieval accuracy using pre-defined questions and guidelines stored directly in Unity Catalog.

Do I need to manually configure document size when generating synthetic PDFs?▼

You do not need to manually configure document size as a fixed value, because the synthetic PDF generation process supports configurable document sizes based on your provided descriptions and use case requirements.