skills.rest
FMurray
FMurrayCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

unstructured-pdf-generation

Generates synthetic PDF documents with RAG evaluation JSON files and uploads them to Unity Catalog Volumes.

Updated Mar 5, 2026
Search Tags:#rag#pdf generation#synthetic data#unstructured data#databricks#unity catalog#evaluation dataset
One-click install
npx skills add https://github.com/FMurray/mlfts --skill unstructured-pdf-generation-fmurray
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: unstructured-pdf-generation
Source: https://github.com/FMurray/mlfts/tree/main/.agents/skills/unstructured-pdf-generation
Command: npx skills add https://github.com/FMurray/mlfts --skill unstructured-pdf-generation-fmurray

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Building and testing RAG pipelines requires realistic document corpora with ground-truth evaluation data, which is time-consuming to create manually. This Skill generates synthetic PDF documents with LLM-produced content plus companion JSON files containing question/guideline pairs, ready for retrieval evaluation. ## Core Features & Use Cases - Synthetic PDF Generation: Create 5-50+ realistic documents (HR policies, technical docs, financial reports, training materials) from a text description using the generate_pdf_documents MCP tool. - Built-in Evaluation Data: Each PDF ships with a JSON file containing a question and evaluation guideline for automated RAG testing. - Unity Catalog Integration: Generated files are uploaded directly to Unity Catalog Volumes with configurable catalog, schema, volume, and folder. - Use Case: You are prototyping a Knowledge Assistant and need 15 HR policy PDFs with ground-truth questions to validate retrieval quality before connecting real data. ## Quick Start Ask the agent to generate 10 technical documentation PDFs about your product into the ai_dev_kit catalog and a schema of your choice using the generate_pdf_documents tool.

Frequently Asked Questions about 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?▼

Call the generate_pdf_documents MCP tool with a catalog, schema, detailed content description, and document count. The tool creates PDFs plus JSON files with question/guideline pairs and uploads everything to a Unity Catalog Volume.

How to create evaluation datasets for a RAG pipeline on Databricks?▼

Generate PDFs with this tool; each document includes a companion JSON containing a question and evaluation guideline. Use the question field to query your RAG system and the guideline field to judge response correctness.

Can I use Azure OpenAI instead of Databricks Foundation Models for PDF generation?▼

Yes. Set LLM_PROVIDER=AZURE with AZURE_OPENAI_ENDPOINT, AZURE_OPENAI_API_KEY, and AZURE_OPENAI_DEPLOYMENT environment variables. The default provider is Databricks Foundation Models via the DATABRICKS_MODEL variable.

What document sizes can I generate and how many PDFs should I create?▼

Three sizes are supported: SMALL (~1 page), MEDIUM (~4-6 pages, default), and LARGE (~10+ pages). Use 5-10 documents for demos, 15-30 for RAG testing, and 50+ for comprehensive evaluation.

Why does PDF generation fail with a no LLM endpoint configured error?▼

The tool requires an LLM endpoint set through environment variables. Set DATABRICKS_MODEL for Databricks Foundation Models or AZURE_OPENAI_DEPLOYMENT for Azure OpenAI before running generation.

Related Skills

Explore More Data & Analytics Skills→
BlackkadderBlackkadder

databricks-unstructured-pdf-generation

Convert HTML5 documents into PDFs and upload them to Unity Catalog volumes.

Community
Intermediate
MassimilianoPiliMassimilianoPili

langchain4j-rag-implementation-patterns

Implement RAG systems with LangChain4j for document ingestion and vector search.

Community
Advanced
JingyiWngJingyiWng

databricks-unstructured-pdf-generation

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

Community
Intermediate
mindspore-aimindspore-ai
258

performance-summary

Summarize and compare operator performance results from result.json files.

Official
Intermediate