Use a Sentence Transformers pipeline to extract document(s)/sentence(s) embedding(s) — hf_sentence_encode • huggingfaceR

Use a Sentence Transformers pipeline to extract document(s)/sentence(s) embedding(s)

Usage

hf_sentence_encode(
  model,
  text,
  batch_size = 64L,
  show_progress_bar = TRUE,
  tidy = TRUE,
  ...
)

Arguments

model: Model object you loaded with `hf_load_sentence_model()`
text: The text, or texts, you wish to embed/encode.
batch_size: How many texts to embed at once.
show_progress_bar: Whether to print a progress bar in the console or not.
tidy: Whether to tidy the output into a tibble or not.
...: other args sent to the model's encode method, e.g. device = device

Value

n-dimensional embeddings for every input `text`

Examples

if (FALSE) { # \dontrun{
text <- c("There are things we do know, things we don't know, and then there is quantum mechanics.")
sentence_mod <- hf_load_sentence_model("paraphrase-MiniLM-L6-v2")
embeddings <- hf_sentence_encode(model = sentence_mod, text, show_progress_bar = TRUE)
} # }