skills.rest
databrickslabs
databrickslabsOFFICIAL
Explore all skills by this author →
WebsiteGitHub

databricks-unstructured-pdf-generation

Generate synthetic PDF and JSON documents for RAG evaluation with Databricks Unity Catalog uploads.

38|12|Updated Apr 24, 2026
Search Tags:#document evaluation#unstructured data#rag testing#synthetic pdf generation#databricks volumes#synthetic documents
One-click install
npx skills add https://github.com/databrickslabs/coding-agents-databricks-apps --skill databricks-unstructured-pdf-generation-databrickslabs
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: databricks-unstructured-pdf-generation
Source: https://github.com/databrickslabs/coding-agents-databricks-apps/tree/main/.claude/skills/databricks-unstructured-pdf-generation
Command: npx skills add https://github.com/databrickslabs/coding-agents-databricks-apps --skill databricks-unstructured-pdf-generation-databrickslabs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the manual effort of creating consistent, realistic test and demo PDF documents for retrieval-augmented generation (RAG) systems, unstructured data processing pipelines, and model evaluation workflows, which is typically time-consuming and prone to inconsistent quality when done manually.

Core Features & Use Cases

  • LLM-Powered Realistic Content: Generates contextually relevant, professional PDF documents based on your custom description, with support for small, medium, and large document sizes.
  • Built-in RAG Evaluation Support: Automatically creates accompanying JSON files with pre-written questions and answer guidelines to test and evaluate your retrieval systems.
  • Seamless Databricks Integration: Automatically uploads generated documents directly to Unity Catalog Volumes for immediate use in your Databricks workflows.
  • Use Case Example: Generate 20 technical documentation PDFs for your SaaS product to test your RAG system's ability to retrieve accurate API reference information.

Quick Start

Use the generate_pdf_documents tool to create 12 financial report PDFs for your retail company and save them to the reports folder in your finance_demo schema.

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?▼

To generate synthetic PDFs for RAG testing, you can use this tool to create realistic documents with custom descriptions and sizes. It automatically uploads the paired PDF and JSON files to Unity Catalog Volumes for immediate Databricks workflow integration.

How do I create evaluation datasets for unstructured data retrieval systems?▼

Creating evaluation datasets for unstructured data retrieval systems is done by generating synthetic PDFs and paired JSON files. These accompanying JSON files contain pre-written questions and answer guidelines to test and evaluate your document retrieval accuracy.

Can I use synthetic documents for Databricks Unity Catalog Volumes?▼

Yes, you can use synthetic documents for Databricks Unity Catalog Volumes. The tool automatically uploads generated PDF and JSON files directly to your specified Volumes location for immediate use in your Databricks workflows.

What is the best way to create test documents for a retrieval-augmented generation system?▼

The best way to create test documents for a retrieval-augmented generation system is using LLM-powered synthetic PDF generation. This ensures consistent, realistic content across small, medium, and large sizes while automatically providing evaluation question-guideline pairs.

Do I need to manually configure document count and size for synthetic PDF generation?▼

No, you do not need to manually configure document count and size for synthetic PDF generation beyond specifying your requirements. The tool is configurable via parameters for document count, size, custom descriptions, and output location to automate the process.

Related Skills

Explore More Data & Analytics Skills→
alessandro9110alessandro9110
4

databricks-unstructured-pdf-generation

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

Community
Intermediate
PaldomPaldom
1

unstructured-pdf-generation

Generate synthetic PDF documents with JSON evaluation files for RAG systems.

Community
Intermediate
slysikslysik

databricks-parsing

Parse PDF, DOCX, PPTX, and images into structured text with ai_parse_document.

Community
Advanced
thbehthbeh

databricks-unstructured-pdf-generation

Generate synthetic PDF documents with structured JSON metadata for RAG testing.

Community
Intermediate