skills.rest
JingyiWng
JingyiWngCOMMUNITY
Explore all skills by this author →
GitHub

databricks-unstructured-pdf-generation

Generate synthetic PDFs with question-answer JSON metadata into Unity Catalog volumes.

Updated Mar 25, 2026
Search Tags:#pdf#rag#json#generate#unity-catalog#synthetic-data
One-click install
npx skills add https://github.com/JingyiWng/databricks_ai_dev_kit_price_watcher --skill databricks-unstructured-pdf-generation-jingyiwng
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: databricks-unstructured-pdf-generation
Source: https://github.com/JingyiWng/databricks_ai_dev_kit_price_watcher/tree/main/.claude/skills/databricks-unstructured-pdf-generation
Command: npx skills add https://github.com/JingyiWng/databricks_ai_dev_kit_price_watcher --skill databricks-unstructured-pdf-generation-jingyiwng

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Many RAG and unstructured data projects lack realistic PDF test data and associated evaluation metadata, making it hard to benchmark retrieval pipelines.

Core Features & Use Cases

  • Synthetic PDF Generation: Creates PDFs with LLM‑generated content based on a user‑provided description.
  • Evaluation JSON: Produces a companion JSON file containing a question and answer‑guideline for each PDF, enabling automated RAG testing.
  • Flexible Deployment: Saves files directly to Unity Catalog volumes, with options for custom volume, folder, document size, and overwrite control.
  • Typical Scenarios: Building demo corpora for HR policies, technical documentation, financial reports, or training materials; feeding PDFs into vector stores for retrieval experiments.

Quick Start

Ask the skill to generate 5 medium‑size synthetic PDFs about cloud infrastructure documentation in catalog my_catalog and schema my_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?▼

You can generate synthetic PDFs for RAG testing by providing a content description to the Skill, which creates LLM-generated documents and saves them directly to Unity Catalog volumes.

What is the best way to create PDF test data with question-answer metadata?▼

The best way to create PDF test data with QA metadata is using a Skill that generates both the synthetic PDFs and a companion JSON file containing questions and answer-guidelines for automated evaluation.

Can I save generated PDFs and JSON files directly to Unity Catalog volumes?▼

Yes, you can save generated synthetic PDFs and their companion JSON files directly to Unity Catalog volumes, with configurable options for custom catalog, schema, folder, and overwrite control.

How do I control the size and count of synthetic PDFs generated for a demo corpus?▼

You can control the size and count of synthetic PDFs by specifying your desired parameters when prompting the Skill, allowing you to build demo corpora scaled to your retrieval benchmark needs.

What kind of content can I use for synthetic PDF generation in unstructured data pipelines?▼

You can generate synthetic PDF content for unstructured data pipelines by providing a custom description, applicable to scenarios like HR policies, technical documentation, financial reports, or training materials.

Does generating synthetic PDFs for retrieval experiments require a specific volume setup?▼

Generating synthetic PDFs requires an accessible Unity Catalog volume, where you must specify the target catalog and schema to successfully store the output PDFs and JSON evaluation files.

Related Skills

Explore More Data & Analytics Skills→
juanlamadrid20juanlamadrid20

unstructured-pdf-generation

Generate synthetic PDFs with JSON metadata for RAG pipelines.

Community
Intermediate
mindmorassmindmorass
2

knowledge-ingestion-patterns

Ingest PDFs, websites, code repos, and notes into vector databases with chunking and metadata schemas.

Community
Basic
Ubuntu-Tech-SolutionsUbuntu-Tech-Solutions

pdf-processing

Extract text, tables, and metadata from PDF documents.

Official
Intermediate
alessandro9110alessandro9110
4

databricks-synthetic-data-generation

Generate synthetic transactional data with Faker and Spark for Databricks.

Community
Advanced