Check Inference API Availability — hf_check

Check whether a model supports the Hugging Face Serverless Inference API. Not all models on the Hub are served by the Inference API. This function queries model metadata to determine availability before you make inference calls.

Usage

hf_check_inference(model_id, token = NULL, quiet = FALSE)

Arguments

model_id: Character string. The model ID (e.g., "BAAI/bge-small-en-v1.5").
token: Character string or NULL. API token for authentication.
quiet: Logical. If TRUE, suppress console output and return result invisibly. Default: FALSE.

Value

A list (invisibly if quiet = TRUE) with components:

model_id: The model ID queried.
available: Logical. TRUE if the model is available on the Inference API.
pipeline_tag: The model's task type (e.g., "feature-extraction").
inference_provider: The inference provider, if available.

Examples

if (FALSE) { # \dontrun{
# Check if a model supports serverless inference
hf_check_inference("BAAI/bge-small-en-v1.5")

# Use programmatically
result <- hf_check_inference("some-org/some-model", quiet = TRUE)
if (result$available) {
  embeddings <- hf_embed("hello", model = "some-org/some-model")
}
} # }