search_dataset
Search for specific text within Hugging Face datasets to find relevant data entries for analysis or training.
Instructions
Search for text within a Hugging Face dataset
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| dataset | Yes | Hugging Face dataset identifier in the format owner/dataset | |
| config | Yes | Dataset configuration/subset name. Use get_info to list available configs | |
| split | Yes | Dataset split name. Splits partition the data for training/evaluation | |
| query | Yes | Text to search for in the dataset | |
| auth_token | No | Hugging Face auth token for private/gated datasets |
Implementation Reference
- src/dataset_viewer/server.py:519-530 (handler)The handler for the 'search_dataset' tool within the @server.call_tool() function. Extracts arguments (dataset, config, split, query), instantiates DatasetViewerAPI if needed, calls its search method, and returns the JSON-formatted results as TextContent.
elif name == "search_dataset": dataset = arguments["dataset"] config = arguments["config"] split = arguments["split"] query = arguments["query"] search_result = await DatasetViewerAPI(auth_token=auth_token).search(dataset, config=config, split=split, query=query) return [ types.TextContent( type="text", text=json.dumps(search_result, indent=2) ) ] - src/dataset_viewer/server.py:305-336 (schema)The input schema definition for the 'search_dataset' tool, registered in @server.list_tools(). Specifies required parameters: dataset, config, split, query, and optional auth_token.
types.Tool( name="search_dataset", description="Search for text within a Hugging Face dataset", inputSchema={ "type": "object", "properties": { "dataset": { "type": "string", "description": "Hugging Face dataset identifier in the format owner/dataset", "pattern": "^[^/]+/[^/]+$", "examples": ["ylecun/mnist", "stanfordnlp/imdb"] }, "config": { "type": "string", "description": "Dataset configuration/subset name. Use get_info to list available configs", "examples": ["default", "en", "es"] }, "split": { "type": "string", "description": "Dataset split name. Splits partition the data for training/evaluation", "examples": ["train", "validation", "test"] }, "query": {"type": "string", "description": "Text to search for in the dataset"}, "auth_token": { "type": "string", "description": "Hugging Face auth token for private/gated datasets", "optional": True } }, "required": ["dataset", "config", "split", "query"], } ), - src/dataset_viewer/server.py:104-114 (helper)Helper method in DatasetViewerAPI class that performs the core search functionality by making an HTTP GET request to the Hugging Face dataset viewer API's /search endpoint with the provided parameters.
async def search(self, dataset: str, config: str, split: str, query: str) -> dict: """Search for text within a dataset split""" params = { "dataset": dataset, "config": config, "split": split, "query": query } response = await self.client.get("/search", params=params) response.raise_for_status() return response.json() - src/dataset_viewer/server.py:217-458 (registration)The @server.list_tools() handler that registers all tools, including 'search_dataset', by returning a list of Tool objects with their schemas and descriptions.
@server.list_tools() async def handle_list_tools() -> list[types.Tool]: """List available dataset tools for Hugging Face datasets""" return [ types.Tool( name="get_info", description="Get detailed information about a Hugging Face dataset including description, features, splits, and statistics. Run validate first to check if the dataset exists and is accessible.", inputSchema={ "type": "object", "properties": { "dataset": { "type": "string", "description": "Hugging Face dataset identifier in the format owner/dataset", "pattern": "^[^/]+/[^/]+$", "examples": ["ylecun/mnist", "stanfordnlp/imdb"] }, "auth_token": { "type": "string", "description": "Hugging Face auth token for private/gated datasets", "optional": True } }, "required": ["dataset"], } ), types.Tool( name="get_rows", description="Get paginated rows from a Hugging Face dataset", inputSchema={ "type": "object", "properties": { "dataset": { "type": "string", "description": "Hugging Face dataset identifier in the format owner/dataset", "pattern": "^[^/]+/[^/]+$", "examples": ["ylecun/mnist", "stanfordnlp/imdb"] }, "config": { "type": "string", "description": "Dataset configuration/subset name. Use get_info to list available configs", "examples": ["default", "en", "es"] }, "split": { "type": "string", "description": "Dataset split name. Splits partition the data for training/evaluation", "examples": ["train", "validation", "test"] }, "page": {"type": "integer", "description": "Page number (0-based), returns 100 rows per page", "default": 0}, "auth_token": { "type": "string", "description": "Hugging Face auth token for private/gated datasets", "optional": True } }, "required": ["dataset", "config", "split"], } ), types.Tool( name="get_first_rows", description="Get first rows from a Hugging Face dataset split", inputSchema={ "type": "object", "properties": { "dataset": { "type": "string", "description": "Hugging Face dataset identifier in the format owner/dataset", "pattern": "^[^/]+/[^/]+$", "examples": ["ylecun/mnist", "stanfordnlp/imdb"] }, "config": { "type": "string", "description": "Dataset configuration/subset name. Use get_info to list available configs", "examples": ["default", "en", "es"] }, "split": { "type": "string", "description": "Dataset split name. Splits partition the data for training/evaluation", "examples": ["train", "validation", "test"] }, "auth_token": { "type": "string", "description": "Hugging Face auth token for private/gated datasets", "optional": True } }, "required": ["dataset", "config", "split"], } ), types.Tool( name="search_dataset", description="Search for text within a Hugging Face dataset", inputSchema={ "type": "object", "properties": { "dataset": { "type": "string", "description": "Hugging Face dataset identifier in the format owner/dataset", "pattern": "^[^/]+/[^/]+$", "examples": ["ylecun/mnist", "stanfordnlp/imdb"] }, "config": { "type": "string", "description": "Dataset configuration/subset name. Use get_info to list available configs", "examples": ["default", "en", "es"] }, "split": { "type": "string", "description": "Dataset split name. Splits partition the data for training/evaluation", "examples": ["train", "validation", "test"] }, "query": {"type": "string", "description": "Text to search for in the dataset"}, "auth_token": { "type": "string", "description": "Hugging Face auth token for private/gated datasets", "optional": True } }, "required": ["dataset", "config", "split", "query"], } ), types.Tool( name="filter", description="Filter rows in a Hugging Face dataset using SQL-like conditions", inputSchema={ "type": "object", "properties": { "dataset": { "type": "string", "description": "Hugging Face dataset identifier in the format owner/dataset", "pattern": "^[^/]+/[^/]+$", "examples": ["ylecun/mnist", "stanfordnlp/imdb"] }, "config": { "type": "string", "description": "Dataset configuration/subset name. Use get_info to list available configs", "examples": ["default", "en", "es"] }, "split": { "type": "string", "description": "Dataset split name. Splits partition the data for training/evaluation", "examples": ["train", "validation", "test"] }, "where": { "type": "string", "description": "SQL-like WHERE clause to filter rows", "examples": ["column = \"value\"", "score > 0.5", "text LIKE \"%query%\""] }, "orderby": { "type": "string", "description": "SQL-like ORDER BY clause to sort results", "optional": True, "examples": ["column ASC", "score DESC", "name ASC, id DESC"] }, "page": { "type": "integer", "description": "Page number for paginated results (100 rows per page)", "default": 0, "minimum": 0 }, "auth_token": { "type": "string", "description": "Hugging Face auth token for private/gated datasets", "optional": True } }, "required": ["dataset", "config", "split", "where"], } ), types.Tool( name="get_statistics", description="Get statistics about a Hugging Face dataset", inputSchema={ "type": "object", "properties": { "dataset": { "type": "string", "description": "Hugging Face dataset identifier in the format owner/dataset", "pattern": "^[^/]+/[^/]+$", "examples": ["ylecun/mnist", "stanfordnlp/imdb"] }, "config": { "type": "string", "description": "Dataset configuration/subset name. Use get_info to list available configs", "examples": ["default", "en", "es"] }, "split": { "type": "string", "description": "Dataset split name. Splits partition the data for training/evaluation", "examples": ["train", "validation", "test"] }, "auth_token": { "type": "string", "description": "Hugging Face auth token for private/gated datasets", "optional": True } }, "required": ["dataset", "config", "split"], } ), types.Tool( name="get_parquet", description="Export Hugging Face dataset split as Parquet file", inputSchema={ "type": "object", "properties": { "dataset": { "type": "string", "description": "Hugging Face dataset identifier in the format owner/dataset", "pattern": "^[^/]+/[^/]+$", "examples": ["ylecun/mnist", "stanfordnlp/imdb"] }, "auth_token": { "type": "string", "description": "Hugging Face auth token for private/gated datasets", "optional": True } }, "required": ["dataset"], } ), types.Tool( name="validate", description="Check if a Hugging Face dataset exists and is accessible", inputSchema={ "type": "object", "properties": { "dataset": { "type": "string", "description": "Hugging Face dataset identifier in the format owner/dataset", "pattern": "^[^/]+/[^/]+$", "examples": ["ylecun/mnist", "stanfordnlp/imdb"] }, "auth_token": { "type": "string", "description": "Hugging Face auth token for private/gated datasets", "optional": True } }, "required": ["dataset"], } ), ]