skills.rest
leary-poken
leary-pokenCOMMUNITY
Explore all skills by this author →
GitHub

databricks-unstructured-pdf-generation

Generates realistic PDFs and JSON metadata for ML-formatting purposes.

1|Updated Mar 17, 2026
Search Tags:#pdf#rag#generate#data-generation#document-processing#databricks#unstructured-data
One-click install
npx skills add https://github.com/leary-poken/ai-dev-kit --skill databricks-unstructured-pdf-generation-leary-poken
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: databricks-unstructured-pdf-generation
Source: https://github.com/leary-poken/ai-dev-kit/tree/main/databricks-skills/databricks-unstructured-pdf-generation
Command: npx skills add https://github.com/leary-poken/ai-dev-kit --skill databricks-unstructured-pdf-generation-leary-poken

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Generate synthetic PDF documents for RAG and unstructured data use cases, enabling quick creation of realistic test data, evaluation datasets, and demo materials.

Core Features & Use Cases

  • LLM-generated PDFs: Create realistic documents with contextually relevant content.
  • Metadata JSON: Produce accompanying JSON files with questions and evaluation guidelines for RAG testing.
  • Unity Catalog Output: Automatically upload PDFs to Unity Catalog volumes for integrated data pipelines.
  • Use Case Examples: Build RAG pipelines, QA datasets, and demonstration datasets with minimal setup.

Quick Start

Generate 10 PDFs with accompanying JSON metadata and save them to the designated Unity Catalog volume.

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 datasets?▼

You can generate synthetic PDFs for RAG datasets by specifying parameters like count, description, and doc_size. The tool outputs realistic PDF documents alongside companion JSON files containing questions and evaluation guidelines for testing unstructured data pipelines.

What is the best way to create unstructured data for Unity Catalog volumes?▼

The best way to create unstructured data for Unity Catalog volumes is to use configurable parameters like catalog, schema, volume, and folder. This tool automatically uploads generated PDFs and metadata JSON directly into Unity Catalog for organized storage.

Can I generate PDF documents and evaluation guidelines together for RAG pipelines?▼

Yes, you can generate PDF documents alongside evaluation guidelines. The tool produces a companion JSON file containing questions and evaluation guidelines alongside each PDF, enabling immediate testing of RAG pipelines and QA datasets.

How do I configure document size and count when generating synthetic PDFs?▼

You configure document size and count when generating synthetic PDFs by adjusting the doc_size and count parameters. These configurable options allow you to tailor the generated PDF outputs to fit different data-generation scenarios and testing scales.

Does this synthetic PDF generation tool work without external dependencies?▼

Yes, the synthetic PDF generation tool works without external dependencies. It requires no additional components or libraries to function, streamlining the process of creating unstructured data for RAG testing and demo materials.

Related Skills

Explore More Data & Analytics Skills→
PaldomPaldom
11

databricks-synthetic-data-gen

Generate synthetic data with Spark and Faker into Unity Catalog volumes.

Community
Advanced
patrykkopycinskipatrykkopycinski
6

rag-pipeline

Set up a RAG pipeline with Elasticsearch for vector retrieval.

Community
Intermediate
jsolarzjsolarz

pdf

Extract text, tables, and images from PDF documents using Python libraries.

Community
Advanced
ricablericable
1

ruvector-agentic-synth

Generates synthetic data for AI/ML training, RAG evaluation, and agentic workflow testing.

Community
Intermediate