[Integrations](https://spiral.ai/integrations) › [Gemini](https://spiral.ai/integrations/gemini) › [Hugging Face dataset search](https://spiral.ai/integrations/gemini/hugging-face-dataset-search)

# How to Use Hugging Face dataset search in Gemini

Find dataset repositories on Hugging Face and compare their metadata, downloads, and likes. Use it to build a shortlist before inspecting individual datasets and their documentation.

|  |  |
| --- | --- |
| Model | Hugging Face dataset search |
| Available through | Alexandria |
| Category | Developer |
| Price | $0.00873 per call. |
| Returns | json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Hugging Face dataset search in Gemini

- Use Hugging Face dataset search to find squad datasets and compare five results by their descriptions, declared licenses, and download counts where returned.
- Use Hugging Face dataset search to look this up and give me the result as a table.
- Pull the latest numbers from Hugging Face dataset search and tell me what changed since last week.
- Check Hugging Face dataset search and summarize what you find in three bullet points.
- Pull the newest data from Hugging Face dataset search and give me the result as a table.

## How to set up Hugging Face dataset search in Gemini

Pick the way that suits you. Each takes about two minutes.

### Use the Gemini connector

1. **Open Connected Apps**: On your computer, go to gemini.google.com. At the bottom, click Settings › Connected Apps. If you don't see Connected Apps, click Personal Intelligence first, then Connected Apps.

2. **Add Spiral as a custom app**: Under Custom apps, click Add a custom app and paste this MCP server URL:

```text
https://api.spiral.ai/mcp
```

3. **Sign in to Spiral and approve**: Follow the on-screen instructions. Spiral opens: sign in, pick the organization and click Authorize. No API key.

### Use the Spiral skill

1. **Send Gemini this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run Hugging Face dataset search**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "alexandria",
    "model": "huggingface-co/hub/datasets",
    "input": {
      "sort": "downloads"
    }
  }'
```

Then paste one of the prompts above: Gemini finds Hugging Face dataset search on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/gemini

## Hugging Face dataset search tools and prices

- [Hugging Face · Datasets](https://spiral.ai/tools/alexandria/huggingface-co/hub/datasets) (Alexandria): $0.00873 per call.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| sort | downloads, likes, trending, last_modified, created | downloads | Sort key; always descending. |
| tags |  | — | Additional Hub tag filters, e.g. `arxiv:2312.15503`. |
| task |  | — | Task category, e.g. `question-answering`, `text-classification`, `image-classification`. |
| limit | 1 to 100 | 20 | limit |
| author |  | — | Owner user or organization, e.g. `openai`. |
| cursor |  | — | Opaque `next_cursor` from the previous page. |

## What can you do with Hugging Face dataset search in Gemini?

Get a readable shortlist of Hugging Face resources for an ML experiment. A chat app can explain repository metadata and card content, including documented limitations that affect the choice.

### Prepare a repository license review

Shortlist models and datasets, collect their declared license metadata, and read their cards for the accompanying usage statements. Produce a review table with links to the original repositories.

### Plan a model evaluation

Find candidate models and evaluation datasets, inspect their repository metadata, and extract documented tasks and limitations from their cards. Turn the findings into a proposed evaluation shortlist.

### Build an internal ML catalog

Discover repositories from selected public organizations, inspect known model and dataset records, and add card summaries to a searchable internal catalog.

### Check documentation before adoption

Find relevant model and dataset repositories, inspect their metadata, and read their cards. Build a checklist of documented uses, citations, and limitations that still need review.

### Select a training dataset

Discover datasets for the intended task, inspect descriptions and available configurations, and read the cards before proposing which data to evaluate.

### Compare repository interest

Compare downloads and likes across shortlisted repositories. Keep model and dataset download comparisons separate because Hugging Face counts them differently.

## Overview

- [Alexandria](https://spiral.ai/providers/alexandria)
- [All Gemini guides](https://spiral.ai/integrations/gemini)

## Hugging Face dataset search in other agents

- [Amp](https://spiral.ai/integrations/amp/hugging-face-dataset-search)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/hugging-face-dataset-search)
- [Claude](https://spiral.ai/integrations/claude-desktop/hugging-face-dataset-search)
- [Claude Code](https://spiral.ai/integrations/claude-code/hugging-face-dataset-search)
- [Cline](https://spiral.ai/integrations/cline/hugging-face-dataset-search)
- [Codex](https://spiral.ai/integrations/codex/hugging-face-dataset-search)
- [Cursor](https://spiral.ai/integrations/cursor/hugging-face-dataset-search)
- [Devin](https://spiral.ai/integrations/devin/hugging-face-dataset-search)
- [dots](https://spiral.ai/integrations/dots/hugging-face-dataset-search)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/hugging-face-dataset-search)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/hugging-face-dataset-search)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/hugging-face-dataset-search)
- [goose](https://spiral.ai/integrations/goose/hugging-face-dataset-search)
- [Grok](https://spiral.ai/integrations/grok/hugging-face-dataset-search)
- [Grok Build](https://spiral.ai/integrations/grok-build/hugging-face-dataset-search)
- [Hermes](https://spiral.ai/integrations/hermes/hugging-face-dataset-search)
- [Instinct](https://spiral.ai/integrations/instinct/hugging-face-dataset-search)
- [Manus](https://spiral.ai/integrations/manus/hugging-face-dataset-search)
- [Muse](https://spiral.ai/integrations/muse/hugging-face-dataset-search)
- [Muse Code](https://spiral.ai/integrations/muse-code/hugging-face-dataset-search)
- [n8n](https://spiral.ai/integrations/n8n/hugging-face-dataset-search)
- [Notion](https://spiral.ai/integrations/notion/hugging-face-dataset-search)
- [OpenClaw](https://spiral.ai/integrations/openclaw/hugging-face-dataset-search)
- [opencode](https://spiral.ai/integrations/opencode/hugging-face-dataset-search)
- [Perplexity](https://spiral.ai/integrations/perplexity/hugging-face-dataset-search)
- [Raycast](https://spiral.ai/integrations/raycast/hugging-face-dataset-search)
- [VS Code](https://spiral.ai/integrations/vscode/hugging-face-dataset-search)
- [Windsurf](https://spiral.ai/integrations/windsurf/hugging-face-dataset-search)
- [Zapier](https://spiral.ai/integrations/zapier/hugging-face-dataset-search)

## More Gemini guides

- [Hugging Face dataset details](https://spiral.ai/integrations/gemini/hugging-face-dataset-details)
- [Hugging Face model details](https://spiral.ai/integrations/gemini/hugging-face-model-details)
- [Higgsfield model documentation](https://spiral.ai/integrations/gemini/higgsfield-model-documentation)
- [Hugging Face model search](https://spiral.ai/integrations/gemini/hugging-face-model-search)
- [Higgsfield model catalog](https://spiral.ai/integrations/gemini/higgsfield-model-catalog)
- [Hugging Face repository card](https://spiral.ai/integrations/gemini/hugging-face-repository-card)

## Questions about Hugging Face dataset search in Gemini

**Can Gemini use Hugging Face dataset search?**

Yes. Add Spiral to Gemini as an MCP server, and Gemini can find and run Hugging Face dataset search like any built-in tool.

**How much does Hugging Face dataset search cost in Gemini?**

$0.00873 per call. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Gemini plan is separate.

**Do I need an Alexandria account to use Hugging Face dataset search in Gemini?**

No. Spiral runs Hugging Face dataset search on its own Alexandria account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Hugging Face dataset search in Gemini?**

About two minutes: open Connected Apps, then add Spiral as a custom app, then sign in to Spiral and approve.

**Does Gemini wait while Hugging Face dataset search runs?**

Hugging Face dataset search runs in the background. Gemini starts the run, checks on it and gives you the json when it's ready.

**Does this cover models and datasets outside Hugging Face?**

The data comes from repositories on Hugging Face Hub. A model or dataset hosted only elsewhere is outside this repository coverage.

**How complete are repository records?**

Many Hub metadata attributes are optional, and search listings contain fewer attributes than individual repository responses. Model cards are recommended to document training, evaluations, and limitations, but that recommendation does not establish that every card includes them.

**What period do download counts cover?**

The standard Hub downloads attribute covers the last 30 days for models and datasets. Cumulative downloads are defined separately.

**Are download counts counts of people?**

Model downloads count requests to designated files, including GET and HEAD requests. Dataset downloads combine files fetched from one repository within a five-minute window for the same IP-based user, so the two totals use different counting rules.

**Where do license and language labels come from?**

Hugging Face uses repository card metadata for these labels. Dataset cards can declare license, language, and size, while model cards also carry publisher-supplied metadata.

