Dimensionality Reduction with UMAP — hf_embed_umap • huggingfaceR

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

Usage

hf_embed_umap(
  text,
  model = "BAAI/bge-small-en-v1.5",
  token = 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.
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

if (FALSE) { # \dontrun{
# 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()
} # }