@spec dataset_tags(keyword()) :: {:ok, map()} | {:error, Exception.t()}

Returns all available dataset tags.

@spec datasets(keyword()) :: Enumerable.t()

Searches for datasets on the Hub.

Options

• :search — full-text search
• :author — filter by author
• :task_categories — list of task categories
• :language — language code or list
• :multilinguality — "multilingual", "monolingual"
• :size_categories — list: ["n<1K", "1K<n<10K", "10K<n<100K", "100K<n<1M", "1M<n<10M", "n>10M"]
• :format — data format: "parquet", "csv", "json", etc.
• :sort — sort field: "downloads", "likes", "lastModified"
• :direction — sort direction
• :limit — max results
• :access_token

Example

# Large English datasets for text classification
HuggingfaceClient.search_datasets(
  task_categories: ["text-classification"],
  language: "en",
  size_categories: ["100K<n<1M", "1M<n<10M"]
)
|> Enum.take(10)

@spec model_tags(keyword()) :: {:ok, map()} | {:error, Exception.t()}

Returns all available model tags (tasks, libraries, languages, etc.).

Example

{:ok, tags} = HuggingfaceClient.Hub.Search.model_tags()
IO.inspect(tags["tasks"])
IO.inspect(tags["libraries"])

@spec models(keyword()) :: Enumerable.t()

Searches for models on the Hub with full filter support.

Returns a lazy stream of model info maps.

Options

• :search — full-text search query
• :author — filter by author/organization
• :task / :pipeline_tag — filter by ML task (e.g. "text-generation", "image-classification")
• :language — filter by language code (e.g. "en", "fr")
• :library — filter by library (e.g. "transformers", "diffusers", "pytorch")
• :tags — filter by tags (list or single string)
• :dataset — filter by training dataset
• :sort — sort field: "downloads", "likes", "lastModified", "created_at"
• :direction — sort direction: -1 (descending) or 1 (ascending)
• :limit — max results
• :full — if true, return full model info (slower)
• :cardData — if true, include model card metadata
• :inference — filter by inference status: "warm", "cold", "frozen"
• :gated — if true, only return gated models
• :num_parameters — filter by parameter count range, e.g. "min:1B,max:10B"
• :access_token

Example

# Top LLMs by downloads
HuggingfaceClient.search_models(
  task: "text-generation",
  sort: "downloads",
  direction: -1,
  limit: 50
)
|> Enum.each(fn m -> IO.puts(m["id"]) end)

# PyTorch image classifiers with >1B params
HuggingfaceClient.search_models(
  task: "image-classification",
  library: "pytorch",
  num_parameters: "min:1B"
)
|> Enum.take(20)

@spec spaces(keyword()) :: Enumerable.t()

Searches for Spaces on the Hub.

Options

• :search — full-text search
• :author — filter by author
• :sdk — filter by SDK: "gradio", "streamlit", "docker", "static"
• :tags — filter by tags
• :sort — "likes", "createdAt", "lastModified"
• :direction — sort direction
• :limit — max results
• :access_token

Example

# Top Gradio demos by likes
HuggingfaceClient.search_spaces(
  sdk: "gradio",
  sort: "likes",
  direction: -1,
  limit: 20
)
|> Enum.each(fn s -> IO.puts("#{s["id"]}: #{s["likes"]} likes") end)

@spec trending_models(keyword()) :: {:ok, [map()]} | {:error, Exception.t()}

Returns trending models on the Hub.

Example

{:ok, trending} = HuggingfaceClient.Hub.Search.trending_models(limit: 10)
Enum.each(trending, fn m -> IO.puts(m["id"]) end)

@spec trending_spaces(keyword()) :: {:ok, [map()]} | {:error, Exception.t()}

Returns trending Spaces on the Hub.

@spec unified(
  String.t(),
  keyword()
) :: {:ok, map()} | {:error, Exception.t()}

Full-text search across all Hub content (models, datasets, spaces, papers).

Options

• :query — search query (required)
• :type — filter by type: "model", "dataset", "space", "paper" (default: all)
• :limit — max results per type
• :access_token

Example

{:ok, results} = HuggingfaceClient.Hub.Search.unified("BERT fine-tuning")
IO.puts("Models: #{length(results["models"])}")
IO.puts("Datasets: #{length(results["datasets"])}")