awesome-copilot/plugins/arize-ax/skills/arize-dataset/SKILL.md

---
name: arize-dataset
description: "INVOKE THIS SKILL when creating, managing, or querying Arize datasets and examples. Also use when the user needs test data or evaluation examples for their model. Covers dataset CRUD, appending examples, exporting data, and file-based dataset creation using the ax CLI."
---

# Arize Dataset Skill

> **`SPACE`** — All `--space` flags and the `ARIZE_SPACE` env var accept a space **name** (e.g., `my-workspace`) or a base64 space **ID** (e.g., `U3BhY2U6...`). Find yours with `ax spaces list`.

## Concepts

- **Dataset** = a versioned collection of examples used for evaluation and experimentation
- **Dataset Version** = a snapshot of a dataset at a point in time; updates can be in-place or create a new version
- **Example** = a single record in a dataset with arbitrary user-defined fields (e.g., `question`, `answer`, `context`)
- **Space** = an organizational container; datasets belong to a space

System-managed fields on examples (`id`, `created_at`, `updated_at`) are auto-generated by the server -- never include them in create or append payloads.

## Prerequisites

Proceed directly with the task — run the `ax` command you need. Do NOT check versions, env vars, or profiles upfront.

If an `ax` command fails, troubleshoot based on the error:
- `command not found` or version error → see references/ax-setup.md
- `401 Unauthorized` / missing API key → run `ax profiles show` to inspect the current profile. If the profile is missing or the API key is wrong, follow references/ax-profiles.md to create/update it. If the user doesn't have their key, direct them to https://app.arize.com/admin > API Keys
- Space unknown → run `ax spaces list` to pick by name, or ask the user
- Project unclear → ask the user, or run `ax projects list -o json --limit 100` and present as selectable options
- **Security:** Never read `.env` files or search the filesystem for credentials. Use `ax profiles` for Arize credentials and `ax ai-integrations` for LLM provider keys. If credentials are not available through these channels, ask the user.

## List Datasets: `ax datasets list`

Browse datasets in a space. Output goes to stdout.

```bash
ax datasets list
ax datasets list --space SPACE --limit 20
ax datasets list --cursor CURSOR_TOKEN
ax datasets list -o json
```

### Flags

| Flag | Type | Default | Description |
|------|------|---------|-------------|
| `--space` | string | from profile | Filter by space |
| `--limit, -l` | int | 15 | Max results (1-100) |
| `--cursor` | string | none | Pagination cursor from previous response |
| `-o, --output` | string | table | Output format: table, json, csv, parquet, or file path |
| `-p, --profile` | string | default | Configuration profile |

## Get Dataset: `ax datasets get`

Quick metadata lookup -- returns dataset name, space, timestamps, and version list.

```bash
ax datasets get NAME_OR_ID
ax datasets get NAME_OR_ID -o json
ax datasets get NAME_OR_ID --space SPACE   # required when using dataset name instead of ID
```

### Flags

| Flag | Type | Default | Description |
|------|------|---------|-------------|
| `NAME_OR_ID` | string | required | Dataset name or ID (positional) |
| `--space` | string | none | Space name or ID (required if using dataset name instead of ID) |
| `-o, --output` | string | table | Output format |
| `-p, --profile` | string | default | Configuration profile |

### Response fields

| Field | Type | Description |
|-------|------|-------------|
| `id` | string | Dataset ID |
| `name` | string | Dataset name |
| `space_id` | string | Space this dataset belongs to |
| `created_at` | datetime | When the dataset was created |
| `updated_at` | datetime | Last modification time |
| `versions` | array | List of dataset versions (id, name, dataset_id, created_at, updated_at) |

## Export Dataset: `ax datasets export`

Download all examples to a file. Use `--all` for datasets larger than 500 examples (unlimited bulk export).

```bash
ax datasets export NAME_OR_ID
# -> dataset_abc123_20260305_141500/examples.json

ax datasets export NAME_OR_ID --all
ax datasets export NAME_OR_ID --version-id VERSION_ID
ax datasets export NAME_OR_ID --output-dir ./data
ax datasets export NAME_OR_ID --stdout
ax datasets export NAME_OR_ID --stdout | jq '.[0]'
ax datasets export NAME_OR_ID --space SPACE   # required when using dataset name instead of ID
```

### Flags

| Flag | Type | Default | Description |
|------|------|---------|-------------|
| `NAME_OR_ID` | string | required | Dataset name or ID (positional) |
| `--space` | string | none | Space name or ID (required if using dataset name instead of ID) |
| `--version-id` | string | latest | Export a specific dataset version |
| `--all` | bool | false | Unlimited bulk export (use for datasets > 500 examples) |
| `--output-dir` | string | `.` | Output directory |
| `--stdout` | bool | false | Print JSON to stdout instead of file |
| `-p, --profile` | string | default | Configuration profile |

**Agent auto-escalation rule:** If an export returns exactly 500 examples, the result is likely truncated — re-run with `--all` to get the full dataset.

**Export completeness verification:** After exporting, confirm the row count matches what the server reports:
```bash
# Get the server-reported count from dataset metadata
ax datasets get DATASET_NAME --space SPACE -o json | jq '.versions[-1] | {version: .id, examples: .example_count}'

# Compare to what was exported
jq 'length' dataset_*/examples.json

# If counts differ, re-export with --all
```

Output is a JSON array of example objects. Each example has system fields (`id`, `created_at`, `updated_at`) plus all user-defined fields:

```json
[
  {
    "id": "ex_001",
    "created_at": "2026-01-15T10:00:00Z",
    "updated_at": "2026-01-15T10:00:00Z",
    "question": "What is 2+2?",
    "answer": "4",
    "topic": "math"
  }
]
```

## Create Dataset: `ax datasets create`

Create a new dataset from a data file.

```bash
ax datasets create --name "My Dataset" --space SPACE --file data.csv
ax datasets create --name "My Dataset" --space SPACE --file data.json
ax datasets create --name "My Dataset" --space SPACE --file data.jsonl
ax datasets create --name "My Dataset" --space SPACE --file data.parquet
```

### Flags

| Flag | Type | Required | Description |
|------|------|----------|-------------|
| `--name, -n` | string | yes | Dataset name |
| `--space` | string | yes | Space to create the dataset in |
| `--file, -f` | path | yes | Data file: CSV, JSON, JSONL, or Parquet |
| `-o, --output` | string | no | Output format for the returned dataset metadata |
| `-p, --profile` | string | no | Configuration profile |

### Passing data via stdin

Use `--file -` to pipe data directly — no temp file needed:

```bash
echo '[{"question": "What is 2+2?", "answer": "4"}]' | ax datasets create --name "my-dataset" --space SPACE --file -

# Or with a heredoc
ax datasets create --name "my-dataset" --space SPACE --file - << 'EOF'
[{"question": "What is 2+2?", "answer": "4"}]
EOF
```

To add rows to an existing dataset, use `ax datasets append --json '[...]'` instead — no file needed.

### Supported file formats

| Format | Extension | Notes |
|--------|-----------|-------|
| CSV | `.csv` | Column headers become field names |
| JSON | `.json` | Array of objects |
| JSON Lines | `.jsonl` | One object per line (NOT a JSON array) |
| Parquet | `.parquet` | Column names become field names; preserves types |

**Format gotchas:**
- **CSV**: Loses type information — dates become strings, `null` becomes empty string. Use JSON/Parquet to preserve types.
- **JSONL**: Each line is a separate JSON object. A JSON array (`[{...}, {...}]`) in a `.jsonl` file will fail — use `.json` extension instead.
- **Parquet**: Preserves column types. Requires `pandas`/`pyarrow` to read locally: `pd.read_parquet("examples.parquet")`.

## Append Examples: `ax datasets append`

Add examples to an existing dataset. Two input modes -- use whichever fits.

### Inline JSON (agent-friendly)

Generate the payload directly -- no temp files needed:

```bash
ax datasets append DATASET_NAME --space SPACE --json '[{"question": "What is 2+2?", "answer": "4"}]'

ax datasets append DATASET_NAME --space SPACE --json '[
  {"question": "What is gravity?", "answer": "A fundamental force..."},
  {"question": "What is light?", "answer": "Electromagnetic radiation..."}
]'
```

### From a file

```bash
ax datasets append DATASET_NAME --space SPACE --file new_examples.csv
ax datasets append DATASET_NAME --space SPACE --file additions.json
```

### To a specific version

```bash
ax datasets append DATASET_NAME --space SPACE --json '[{"q": "..."}]' --version-id VERSION_ID
```

### Flags

| Flag | Type | Required | Description |
|------|------|----------|-------------|
| `NAME_OR_ID` | string | yes | Dataset name or ID (positional); add `--space` when using name |
| `--space` | string | no | Space name or ID (required if using dataset name instead of ID) |
| `--json` | string | mutex | JSON array of example objects |
| `--file, -f` | path | mutex | Data file (CSV, JSON, JSONL, Parquet) |
| `--version-id` | string | no | Append to a specific version (default: latest) |
| `-o, --output` | string | no | Output format for the returned dataset metadata |
| `-p, --profile` | string | no | Configuration profile |

Exactly one of `--json` or `--file` is required.

### Validation

- Each example must be a JSON object with at least one user-defined field
- Maximum 100,000 examples per request

**Schema validation before append:** If the dataset already has examples, inspect its schema before appending to avoid silent field mismatches:

```bash
# Check existing field names in the dataset
ax datasets export DATASET_NAME --space SPACE --stdout | jq '.[0] | keys'

# Verify your new data has matching field names
echo '[{"question": "..."}]' | jq '.[0] | keys'

# Both outputs should show the same user-defined fields
```

Fields are free-form: extra fields in new examples are added, and missing fields become null. However, typos in field names (e.g., `queston` vs `question`) create new columns silently -- verify spelling before appending.

## Delete Dataset: `ax datasets delete`

```bash
ax datasets delete NAME_OR_ID
ax datasets delete NAME_OR_ID --space SPACE   # required when using dataset name instead of ID
ax datasets delete NAME_OR_ID --force   # skip confirmation prompt
```

### Flags

| Flag | Type | Default | Description |
|------|------|---------|-------------|
| `NAME_OR_ID` | string | required | Dataset name or ID (positional) |
| `--space` | string | none | Space name or ID (required if using dataset name instead of ID) |
| `--force, -f` | bool | false | Skip confirmation prompt |
| `-p, --profile` | string | default | Configuration profile |

## Workflows

### Find a dataset by name

All dataset commands accept a name or ID directly. You can pass a dataset name as the positional argument (add `--space SPACE` when not using an ID):

```bash
# Use name directly
ax datasets get "eval-set-v1" --space SPACE
ax datasets export "eval-set-v1" --space SPACE

# Or resolve name to ID via list if you need the base64 ID
ax datasets list -o json | jq '.[] | select(.name == "eval-set-v1") | .id'
```

### Create a dataset from file for evaluation

1. Prepare a CSV/JSON/Parquet file with your evaluation columns (e.g., `input`, `expected_output`)
   - If generating data inline, pipe it via stdin using `--file -` (see the Create Dataset section)
2. `ax datasets create --name "eval-set-v1" --space SPACE --file eval_data.csv`
3. Verify: `ax datasets get DATASET_NAME --space SPACE`
4. Use the dataset name to run experiments

### Add examples to an existing dataset

```bash
# Find the dataset
ax datasets list --space SPACE

# Append inline or from a file using the dataset name (see Append Examples section for full syntax)
ax datasets append DATASET_NAME --space SPACE --json '[{"question": "...", "answer": "..."}]'
ax datasets append DATASET_NAME --space SPACE --file additional_examples.csv
```

### Download dataset for offline analysis

1. `ax datasets list --space SPACE` -- find the dataset name
2. `ax datasets export DATASET_NAME --space SPACE` -- download to file
3. Parse the JSON: `jq '.[] | .question' dataset_*/examples.json`

### Export a specific version

```bash
# List versions
ax datasets get DATASET_NAME --space SPACE -o json | jq '.versions'

# Export that version
ax datasets export DATASET_NAME --space SPACE --version-id VERSION_ID
```

### Iterate on a dataset

1. Export current version: `ax datasets export DATASET_NAME --space SPACE`
2. Modify the examples locally
3. Append new rows: `ax datasets append DATASET_NAME --space SPACE --file new_rows.csv`
4. Or create a fresh version: `ax datasets create --name "eval-set-v2" --space SPACE --file updated_data.json`

### Pipe export to other tools

```bash
# Count examples
ax datasets export DATASET_NAME --space SPACE --stdout | jq 'length'

# Extract a single field
ax datasets export DATASET_NAME --space SPACE --stdout | jq '.[].question'

# Convert to CSV with jq
ax datasets export DATASET_NAME --space SPACE --stdout | jq -r '.[] | [.question, .answer] | @csv'
```

## Dataset Example Schema

Examples are free-form JSON objects. There is no fixed schema -- columns are whatever fields you provide. System-managed fields are added by the server:

| Field | Type | Managed by | Notes |
|-------|------|-----------|-------|
| `id` | string | server | Auto-generated UUID. Required on update, forbidden on create/append |
| `created_at` | datetime | server | Immutable creation timestamp |
| `updated_at` | datetime | server | Auto-updated on modification |
| *(any user field)* | any JSON type | user | String, number, boolean, null, nested object, array |


## Related Skills

- **arize-trace**: Export production spans to understand what data to put in datasets → use `arize-trace`
- **arize-experiment**: Run evaluations against this dataset → next step is `arize-experiment`
- **arize-prompt-optimization**: Use dataset + experiment results to improve prompts → use `arize-prompt-optimization`

## Troubleshooting

| Problem | Solution |
|---------|----------|
| `ax: command not found` | See references/ax-setup.md |
| `401 Unauthorized` | API key is wrong, expired, or doesn't have access to this space. Fix the profile using references/ax-profiles.md. |
| `No profile found` | No profile is configured. See references/ax-profiles.md to create one. |
| `Dataset not found` | Verify dataset ID with `ax datasets list` |
| `File format error` | Supported: CSV, JSON, JSONL, Parquet. Use `--file -` to read from stdin. |
| `platform-managed column` | Remove `id`, `created_at`, `updated_at` from create/append payloads |
| `reserved column` | Remove `time`, `count`, or any `source_record_*` field |
| `Provide either --json or --file` | Append requires exactly one input source |
| `Examples array is empty` | Ensure your JSON array or file contains at least one example |
| `not a JSON object` | Each element in the `--json` array must be a `{...}` object, not a string or number |

## Save Credentials for Future Use

See references/ax-profiles.md § Save Credentials for Future Use.