hf_classify_zero_shot: Zero-Shot Classification

In huggingfaceR: Access 'Hugging Face' Models and Datasets

Zero-Shot Classification

Description

Classify text into custom categories without training a model. The model determines which labels best describe the input text.

Usage

hf_classify_zero_shot(
  text,
  labels,
  model = hf_default_model("zero_shot"),
  multi_label = FALSE,
  token = NULL,
  endpoint_url = NULL,
  ...
)

Arguments

text	Character vector of text(s) to classify.
labels	Character vector of candidate labels/categories.
model	Character string. Model ID from Hugging Face Hub. Default: "facebook/bart-large-mnli"
multi_label	Logical. If TRUE, allows multiple labels per text. Default: FALSE (single label per text).
token	Character string or NULL. API token for authentication.
endpoint_url	Character string or NULL. A custom Inference Endpoint URL.
...	Additional arguments (currently unused).

Value

A tibble with columns: text, label, score (sorted by score descending)

Examples

## Not run: 
# Classify into custom categories
hf_classify_zero_shot(
  "I just bought a new laptop",
  labels = c("technology", "sports", "politics", "food")
)

# Multi-label classification
hf_classify_zero_shot(
  "This laptop is great for gaming",
  labels = c("technology", "gaming", "entertainment"),
  multi_label = TRUE
)

## End(Not run)

huggingfaceR documentation built on Aug. 30, 2026, 1:06 a.m.