hf_embed_umap: Dimensionality Reduction with UMAP

In huggingfaceR: Access 'Hugging Face' Models and Datasets

Dimensionality Reduction with UMAP

Description

Reduce embedding dimensions to 2D using UMAP for visualization. Requires the 'uwot' package to be installed.

Usage

hf_embed_umap(
  text,
  model = hf_default_model("embed"),
  token = NULL,
  endpoint_url = NULL,
  n_neighbors = 15,
  min_dist = 0.1,
  ...
)

Arguments

text	Character vector of text(s) to embed and reduce.
model	Character string. Model ID for generating embeddings. Default: "BAAI/bge-small-en-v1.5".
token	Character string or NULL. API token for authentication.
endpoint_url	Character string or NULL. A custom Inference Endpoint URL.
n_neighbors	Integer. UMAP n_neighbors parameter. Default: 15.
min_dist	Numeric. UMAP min_dist parameter. Default: 0.1.
...	Additional arguments passed to uwot::umap().

Value

A tibble with columns: text, umap_1, umap_2

Examples

## Not run: 
# Reduce and visualize
library(ggplot2)
texts <- c("cat", "dog", "kitten", "puppy", "car", "truck")
coords <- hf_embed_umap(texts)

ggplot(coords, aes(umap_1, umap_2, label = text)) +
  geom_text() +
  theme_minimal()

## End(Not run)

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