skills.rest
Paldom
PaldomCOMMUNITY
Explore all skills by this author →
GitHub

databricks-unstructured-pdf-generation

Generate synthetic PDFs with JSON metadata for RAG testing via MCP tool.

11|3|Updated Jun 10, 2025
Search Tags:#pdf#qa#rag#retrieval#vector-search#synthetic-data
One-click install
npx skills add https://github.com/Paldom/databricks-apps-fastapi-starter --skill databricks-unstructured-pdf-generation-paldom
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: databricks-unstructured-pdf-generation
Source: https://github.com/Paldom/databricks-apps-fastapi-starter/tree/main/.gemini/skills/databricks-unstructured-pdf-generation
Command: npx skills add https://github.com/Paldom/databricks-apps-fastapi-starter --skill databricks-unstructured-pdf-generation-paldom

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Generates synthetic PDF documents to support RAG pipelines and unstructured data use cases, removing the need to source real documents for testing and evaluation.

Core Features & Use Cases

  • Generate synthetic PDFs with LLM-driven content and accompanying JSON metadata for QA and RAG testing
  • Auto-upload to Unity Catalog Volumes for integrated data workflows
  • Use cases include building test datasets, evaluation datasets for vector search, and demonstration materials

Quick Start

Use the generate_pdf_documents MCP tool to create 10 PDFs and corresponding JSON files for RAG evaluation.

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 pipeline testing?▼

To generate synthetic PDFs for RAG testing, this tool creates LLM-driven documents with accompanying JSON metadata. It outputs multiple PDFs configurable by catalog, schema, count, and volume, which you can load directly into vector stores.

What is the best way to create evaluation datasets for vector search?▼

Creating evaluation datasets for vector search is done by generating synthetic PDFs with accompanying JSON metadata. This approach provides structured test data for unstructured data use cases without needing to source real documents.

Does synthetic PDF generation support Unity Catalog Volumes?▼

Synthetic PDF generation supports Unity Catalog Volumes for integrated data workflows. You can configure the catalog, schema, and volume to auto-upload the generated PDFs and JSON files directly into your knowledge base.

Can I specify the number of documents and folder when generating unstructured data?▼

You can specify the count and folder when generating unstructured data by using optional volume and folder overrides. This allows you to scale the synthetic PDF generation to match your specific testing requirements.

Why do I need JSON metadata alongside synthetic PDFs for QA?▼

You need JSON metadata alongside synthetic PDFs for QA to map the generated content to expected answers. This metadata pairs with the LLM-driven PDF documents to provide structured evaluation criteria for retrieval and vector search testing.

Related Skills

Explore More Data & Analytics Skills→
juanlamadrid20juanlamadrid20

unstructured-pdf-generation

Generate synthetic PDFs with JSON metadata for RAG pipelines.

Community
Intermediate
thbehthbeh

databricks-vector-search

Manage Databricks vector search endpoints, indexes, and similarity queries.

Community
Advanced
tawf-labstawf-labs
1

langchain-rag

Build retrieval-augmented generation workflows that ground LLM answers in external documents.

Official
Intermediate
thbehthbeh

databricks-unstructured-pdf-generation

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

Community
Intermediate