Unstructured PDF Generation

Generate realistic synthetic PDF documents using LLM for RAG (Retrieval-Augmented Generation) and unstructured data use cases.

Overview

This skill uses the generate_pdf_documents MCP tool to create professional PDF documents with:

• LLM-generated content based on your description
• Accompanying JSON files with questions and evaluation guidelines (for RAG testing)
• Automatic upload to Unity Catalog Volumes

Quick Start

Use the generate_pdf_documents MCP tool:

• catalog: "my_catalog"
• schema: "my_schema"
• description: "Technical documentation for a cloud infrastructure platform including setup guides, troubleshooting procedures, and API references."
• count: 10