databricks-unstructured-pdf-generation

Generate synthetic PDFs and metadata for RAG evaluation using the generate_pdf_documents MCP tool.

1|1|Updated Oct 1, 2025
One-click install
npx skills add https://github.com/mkgs-databricks-demos/synthea-on-fhir --skill databricks-unstructured-pdf-generation-mkgs-databricks-demos
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: databricks-unstructured-pdf-generation
Source: https://github.com/mkgs-databricks-demos/synthea-on-fhir/tree/main/.cursor/skills/databricks-unstructured-pdf-generation
Command: npx skills add https://github.com/mkgs-databricks-demos/synthea-on-fhir --skill databricks-unstructured-pdf-generation-mkgs-databricks-demos

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The skill automates the creation of synthetic PDF documents and associated metadata for RAG pipelines and unstructured data testing, enabling fast evaluation and reproducible datasets.

Core Features & Use Cases

  • Uses the generate_pdf_documents MCP tool to create professional PDFs with LLM-generated content
  • Produces accompanying JSON files with questions and evaluation guidelines for RAG testing
  • Automatically uploads generated documents to Unity Catalog volumes for seamless data management

Quick Start

Call the generate_pdf_documents MCP tool with catalog, schema, description, and count to generate 10 PDFs

Frequently Asked Questions about databricks-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 testing?

Yes, alongside generating synthetic PDFs, the skill produces accompanying JSON files containing questions and evaluation guidelines to support reproducible RAG testing and unstructured data workflows.

Can I generate evaluation metadata alongside test PDFs for RAG pipelines?

Yes, alongside generating synthetic PDFs, the skill produces accompanying JSON files containing questions and evaluation guidelines to support reproducible RAG testing and unstructured data workflows.

What do I need to configure to save synthetic PDFs to Unity Catalog volumes?

To save synthetic PDFs to Unity Catalog volumes, you need to provide the catalog and schema parameters, with optional configurations for volume, folder, and description to tailor the storage location and generated content.

Is there a way to control how many synthetic PDF documents are created for my evaluation dataset?

Yes, you can control the number of synthetic PDF documents created by specifying the count parameter when calling the generate_pdf_documents MCP tool, allowing you to scale your evaluation dataset as needed.

Does synthetic data generation work for unstructured data workflows without manual document creation?

Yes, synthetic data generation automates the creation of unstructured PDF documents and metadata, eliminating manual document creation and enabling fast evaluation of RAG pipelines and unstructured data workflows.