How deeply does Building LLM Applications with DSPy cover Hugging Face Datasets?

Demonstrates installation, loading, pandas formatting, and split selection, but defers prompt optimization.

Hugging Face Datasets

As explained in Building LLM Applications with DSPy

Hugging Face Datasets is a Python library for downloading, processing, sharing, and loading machine-learning datasets.

Hugging Face Datasets downloads named datasets from a repository and can format them as pandas dataframes. Dataset splits commonly include train and test, and sometimes validation. For an ATIS baseline, the test split alone is used. section 3.2

Listing 3.1 Downloading the dataset

from datasets import load_dataset
import pandas as pd

ds = load_dataset("tuetschek/atis")
ds.set_format(type='pandas')
df = ds['test'][:]

Load the ATIS dataset, format it as pandas, and select its test split. section 3.2

How Building LLM Applications with DSPy covers it

Cover of Building LLM Applications with DSPy

liveBook manning.com

Read Building LLM Applications with DSPy on liveBook Get the book at manning.com

Related concepts

datasetuses · A dataset is an organized collection of related data items, records, or observations treated as a unit for storage, processing, analysis, or computation.
Oxford Flowers datasetuses · The Oxford Flowers dataset is an image dataset containing 8,189 images categorized into 102 flower species.
torchvisionused by · torchvision is a PyTorch library providing computer-vision datasets, models, image transformations, and related utilities.
Parquetproduces · Apache Parquet is an open, column-oriented binary file format for storing and processing structured data with schema and metadata support.

This explainer was generated by Manning's knowledge graph from the text of Building LLM Applications with DSPy. The section links point to the parts of the book it draws on.