databricks-unstructured-pdf-generation

Generate synthetic PDF documents with JSON metadata for RAG evaluation in Databricks Unity Catalog Volumes.

4|2|Updated Feb 16, 2026
One-click install
npx skills add https://github.com/alessandro9110/Speech-To-Text-With-Databricks --skill databricks-unstructured-pdf-generation-alessandro9110
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: databricks-unstructured-pdf-generation
Source: https://github.com/alessandro9110/Speech-To-Text-With-Databricks/tree/main/.claude/skills/databricks-unstructured-pdf-generation
Command: npx skills add https://github.com/alessandro9110/Speech-To-Text-With-Databricks --skill databricks-unstructured-pdf-generation-alessandro9110

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill automates the creation of realistic synthetic PDF documents, streamlining the process of generating test data for Retrieval-Augmented Generation (RAG) systems and unstructured data use cases.

Core Features & Use Cases

  • LLM-Generated Content: Creates professional PDF documents with content tailored to your descriptions.
  • RAG Evaluation Data: Generates accompanying JSON files with questions and evaluation guidelines for testing retrieval systems.
  • Unity Catalog Integration: Automatically uploads generated PDFs and metadata to Databricks Unity Catalog Volumes.
  • Use Case: Generate 10 technical documentation PDFs for a cloud platform to test a RAG system's ability to answer setup and API reference questions.

Quick Start

Use the generate_pdf_documents MCP tool to create 10 technical documentation PDFs in the 'ai_dev_kit' catalog and 'tech_docs' schema, saving them to the 'product_docs' folder.

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 evaluation?

It creates synthetic PDF documents and accompanying JSON metadata containing questions and evaluation guidelines. By defining content descriptions and document counts, you get realistic unstructured data tailored for testing retrieval systems.

How do I create test data for unstructured data use cases in Databricks?

By invoking the generate_pdf_documents tool, you create tailored PDFs and JSON metadata. It automatically uploads the generated files to your specified Databricks Unity Catalog Volumes for immediate access.

Does generating synthetic PDFs require a specific Databricks environment?

Yes, generating synthetic PDFs requires Databricks Unity Catalog Volumes. You must specify a target catalog, schema, and folder path to successfully store the LLM-generated documents and JSON metadata.

Can I customize the content of generated PDF documents?

Yes, you can customize PDF document content by providing specific content descriptions. The LLM-driven generation process uses your descriptions to create professional documents tailored to your specific testing requirements.

What is the best way to test a RAG system's ability to answer technical questions?

The best way is generating synthetic technical PDFs with accompanying JSON metadata. This metadata includes specific questions and evaluation guidelines designed to assess retrieval accuracy against your unstructured documents.

What limitations exist when using LLMs for synthetic PDF generation?

Limitations of LLM-driven synthetic PDF generation include reliance on your provided content descriptions for realism. The generated unstructured data requires manual validation to ensure it accurately reflects your specific RAG evaluation scenarios.