databricks-unstructured-pdf-generation

Generate synthetic PDF documents with JSON metadata for RAG workflows.

27|9|Updated Feb 3, 2026
One-click install
npx skills add https://github.com/datasciencemonkey/coding-agents-databricks-apps --skill databricks-unstructured-pdf-generation
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: databricks-unstructured-pdf-generation
Source: https://github.com/datasciencemonkey/coding-agents-databricks-apps/tree/main/.claude/skills/databricks-unstructured-pdf-generation
Command: npx skills add https://github.com/datasciencemonkey/coding-agents-databricks-apps --skill databricks-unstructured-pdf-generation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Generate realistic synthetic PDF documents to support Retrieval-Augmented Generation (RAG) pipelines and unstructured data use cases, enabling robust testing and demonstrations without relying on real data.

Core Features & Use Cases

  • Generate LLM-created PDFs with accompanying JSON metadata for RAG evaluation.
  • Support configurable catalogs, schemas, and target counts to produce diverse datasets.
  • Automatically stage PDFs for indexing or upload to Unity Catalog volumes.

Quick Start

Call the generate_pdf_documents MCP tool with catalog, schema, description, and count to generate synthetic 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 PDF documents for RAG testing in Databricks?

To generate synthetic PDFs for RAG testing in Databricks, call the generate_pdf_documents tool with your target catalog, schema, description, and count to produce PDFs with accompanying JSON metadata.

What types of unstructured PDF documents can I create for test datasets?

You can create synthetic PDF test datasets across technical manuals, API docs, policies, and product guides by specifying the desired description and volume when generating documents.

Can I stage generated PDFs directly into Unity Catalog volumes?

Yes, generated synthetic PDFs can be automatically staged for indexing or upload to Unity Catalog volumes by configuring the folder and volume parameters during document generation.

Do I need to provide a specific schema to generate synthetic PDFs with metadata?

Yes, you need to specify a catalog, schema, description, and count to generate synthetic PDFs with accompanying JSON metadata for your RAG evaluation workflows.

How many synthetic PDFs can I generate at once for a RAG pipeline evaluation?

You can configure the target count parameter to generate a specific volume of synthetic PDFs at once, enabling robust RAG pipeline testing and demonstrations without relying on real data.

What limitations exist when generating synthetic PDFs for unstructured data testing?

Synthetic PDF generation for unstructured data testing is limited to configurable volume and folder targets, producing LLM-created documents with JSON metadata rather than real-world data.