skills.rest
lightning-rod-labs
lightning-rod-labsOFFICIAL
Explore all skills by this author →
Website𝕏@lightningrodaiGitHub

custom-dataset-seeds

Generate Lightning Rod forecasting seed samples from PDFs, CSVs, and text files.

57|6|Updated Jan 16, 2026
Search Tags:#pdf#rag#forecasting#labeling#seeds#dataset generation#csv ingestion
One-click install
npx skills add https://github.com/lightning-rod-labs/lightningrod-python-sdk --skill custom-dataset-seeds
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: custom-dataset-seeds
Source: https://github.com/lightning-rod-labs/lightningrod-python-sdk/tree/main/skills/custom-dataset-seeds
Command: npx skills add https://github.com/lightning-rod-labs/lightningrod-python-sdk --skill custom-dataset-seeds

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It converts local files and user-provided datasets (like PDFs, CSVs, and text) into Lightning Rod “seeds” so you can quickly build labeled forecasting datasets without manual preprocessing.

Core Features & Use Cases

  • File-to-samples ingestion: Chunk documents or map CSV columns into model-ready samples with optional embedded labels and metadata.
  • FileSet-based workflows: Upload large or metadata-rich corpora as a FileSet for scalable transformation and temporal/metadata filtering.
  • Flexible context and labeling strategies: Generate seeds-only, whole-document (non-RAG) context/labels using chronological constraints, or RAG context/labels using vector retrieval with payload/temporal filters.
  • Fitness + chunking guidance: Provide practical checks (volume, date coverage, text quality, label availability) and recommended chunking parameters to improve results.

Quick Start

Convert your PDFs into seeds and run a transforms pipeline with a limit on generated questions by asking: “Ingest data/*.pdf as samples with chunk_size=1000 and chunk_overlap=100, create an input_dataset from those samples, then run lr.transforms.run(pipeline, input_dataset=input_dataset, max_questions=10).”

Frequently Asked Questions about custom-dataset-seeds

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert PDFs and CSVs into labeled training data for forecasting?▼

To convert PDFs and CSVs into labeled training data, you ingest local files as model-ready samples using configurable chunking and optional embedded labels. This process transforms raw documents and datasets into structured forecasting seeds without manual preprocessing.

What is the best way to generate dataset samples from large corpora with metadata?▼

The best way to generate dataset samples from large corpora is uploading files as a FileSet. This enables scalable transformation, metadata filtering, and chronological constraints to process large document collections efficiently.

Can I use RAG retrieval to build context for forecasting datasets?▼

Yes, you can use RAG retrieval to build context for forecasting datasets. The generation components support Qdrant-based vector retrieval with payload and temporal filters to extract relevant context for your labels.

Does file chunking support configurable size and overlap parameters for text ingestion?▼

File chunking supports configurable size and overlap parameters for text ingestion. You can specify values like chunk_size and chunk_overlap to control how documents are segmented before generating seeds.

How do I check if my files are suitable for dataset generation before processing?▼

To check if your files are suitable for dataset generation, use the provided fitness guidance. This evaluates volume, date coverage, text quality, and label availability to recommend optimal chunking parameters before processing.

Related Skills

Explore More Data & Analytics Skills→
hepai-labhepai-lab
21

ragflow-knowledge

Ingest PDFs into a RAGFlow dataset with chunking and metadata enrichment.

Community
Advanced
vadimcomanescuvadimcomanescu
24

aeon

Train ROCKET-based classifiers on time series datasets with scikit-learn compatible APIs.

Community
Advanced
kilburnkilburn

qdrant

Configure Qdrant collections, vectors, HNSW, and quantization for vector search.

Community
Advanced
lightning-rod-labslightning-rod-labs
57

bigquery-seeds

Creates BigQuery-backed seed datasets from publicly queryable tables for forecasting and training.

Official
Intermediate