# Hugging face dataset rows

Reads rows of a public Hugging Face dataset without downloading it, through the Dataset Viewer: column names and types, then the rows from an offset. Needs dataset.

Reads rows of a public Hugging Face dataset without downloading it, through the Dataset Viewer: column names and types, then the rows from an offset. Use it to see what a dataset really contains before relying on it. Long cells are cut and media cells come as links. Config and split names come from huggingface/dataset-size. Returns an error for gated or unviewable datasets, or a config or split that does not exist. Content follows each dataset's own licence.

- Tool ID: `huggingface/dataset-rows`
- Name in the catalog: Hugging Face dataset rows
- Provider: [Hugging Face](/providers/huggingface.md)
- Capability: [GitHub, npm & PyPI](/tools/developer-data/code.md)
- Price: no charge per call
- Authentication: an authorised Agentik workspace is required for execution, including zero-price tools.

## Pricing contract

No charge per call. A workspace is still needed so your agent can call it.


```json
{
  "model": "per_call",
  "amountUsd": 0
}
```

## Complete input schema


```json
{
  "type": "object",
  "properties": {
    "dataset": {
      "type": "string",
      "pattern": "^[A-Za-z0-9][A-Za-z0-9._-]{0,95}(/[A-Za-z0-9][A-Za-z0-9._-]{0,95})?$",
      "description": "Dataset id with its owner, e.g. 'openai/gsm8k'"
    },
    "config": {
      "type": "string",
      "pattern": "^[A-Za-z0-9._-]{1,100}$",
      "default": "default",
      "description": "Dataset configuration, e.g. 'main'"
    },
    "split": {
      "type": "string",
      "pattern": "^[A-Za-z0-9._-]{1,60}$",
      "default": "train",
      "description": "Split name, e.g. 'train'"
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "maximum": 100000000,
      "default": 0,
      "description": "First row, e.g. 0"
    },
    "length": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "default": 5,
      "description": "Rows to return, e.g. 5"
    }
  },
  "required": [
    "dataset"
  ],
  "additionalProperties": false
}
```

## Published example

This is the provider tool’s published example. Replace example values with the user’s requested inputs, respecting the schema; do not execute an example merely to test a connection.


```json
{
  "tool_id": "huggingface/dataset-rows",
  "input": {
    "dataset": "openai/gsm8k",
    "config": "main",
    "split": "train",
    "length": 3
  }
}
```

## Execute and retrieve

Inspect again before execution, explain the price and obtain the required authority. Use MCP run_tool or POST /v1/run with this tool ID, valid input and an idempotency key. Save the returned run ID and follow the actual state. If Agentik answers that the tool is temporarily unavailable, do not retry it blindly; use discovery to propose an alternative.

A partial or uncertain result can still have consumed provider resources. Consult [billing](/docs/billing.md), [idempotency](/docs/idempotency.md) and [asynchronous results](/docs/async.md).

Licence: Hugging Face Dataset Viewer; rows follow each dataset's own licence.

[Provider documentation](https://huggingface.co/docs/dataset-viewer/rows)

[REST inspection](https://api.agentik.cc/v1/tools/huggingface/dataset-rows) · [OpenAPI](/openapi.json) · [Connection guide](/connect.md)

---

[HTML page](/providers/huggingface/dataset-rows) · [Agent index](/llms.txt)