Hugging Face Datasets
Hugging Face Datasets is an open-source Python library for loading, processing, managing, and sharing machine-learning datasets.
Building LLM Applications with DSPy
Hugging Face Datasets is a Python library for downloading, processing, sharing, and loading machine-learning datasets.
- How it is used
- Downloads and prepares ATIS data for a baseline intent-classification task.
- How deep it goes
- Demonstrates installation, loading, pandas formatting, and split selection, but defers prompt optimization.
- Examples
- Uses airline customer-service requests from ATIS and loads its test split.
- What you can do after
- Apply via Hugging Face Datasets to load the ATIS test split as a pandas dataframe.
Read how Building LLM Applications with DSPy explains Hugging Face Datasets →
Build an Advanced RAG Application (From Scratch)
Hugging Face Datasets is a Python library and ecosystem for accessing, processing, and sharing machine-learning datasets.
- How it is used
- Supports the initial data-loading and preparation stage of a semantic-search pipeline.
- How deep it goes
- Demonstrates installation, loading, split extraction, DataFrame conversion, inspection, and filtering, stopping before advanced retrieval systems.
- Examples
- Uses hotel reviews and descriptions, filters for Paris, inspects rows, and counts hotels by name.
- What you can do after
- Build a filtered pandas dataset from a hosted machine-learning dataset for downstream semantic-search work.
Read how Build an Advanced RAG Application (From Scratch) explains Hugging Face Datasets →
Also covered in
- Learn Generative AI with PyTorch
- Hugging Face in Action
- AI-Powered Search
- Build AI Drug Discovery PipelinesIn early access (MEAP)
- Build a Text-to-Image Generator (from Scratch)
What to know first
- language modelA language model is a computational model that represents patterns in linguistic sequences to assign probabilities, predict, generate, or evaluate language.
Related concepts
- datasetuses · A dataset is an organized collection of related data items, records, observations, or examples treated as a unit for storage, processing, or analysis.
- Oxford Flowers datasetuses · The Oxford Flowers dataset is an image dataset containing 8,189 images categorized into 102 flower species.
- Parquetproduces · Apache Parquet is an open, column-oriented binary file format for storing and processing structured data with schema and metadata support.
- torchvisionused by · torchvision is a PyTorch library providing computer-vision datasets, models, image transformations, and related utilities.
Questions about Hugging Face Datasets
What is Hugging Face Datasets?
Hugging Face Datasets is an open-source Python library for loading, processing, managing, and sharing machine-learning datasets.
Which Manning books explain Hugging Face Datasets?
Building LLM Applications with DSPy and Build an Advanced RAG Application (From Scratch).
What should I know before learning Hugging Face Datasets?
Manning books that teach Hugging Face Datasets usually introduce language model first.
What is Hugging Face Datasets also called?
Hugging Face Datasets is also called datasets library.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.

