Arize Dataset Skill

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: check .env for ARIZE_API_KEY and use it to create/update the profile via references/ax-profiles.md. If .env has no key either, ask the user for their Arize API key (https://app.arize.com/admin > API Keys)
• Space ID unknown → check .env for ARIZE_SPACE_ID, or run ax spaces list -o json, or ask the user
• Project unclear → check .env for ARIZE_DEFAULT_PROJECT, or ask, or run ax projects list -o json --limit 100 and present as selectable options

List Datasets: ax datasets list

Browse datasets in a space. Output goes to stdout.

ax datasets list
ax datasets list --space-id SPACE_ID --limit 20
ax datasets list --cursor CURSOR_TOKEN
ax datasets list -o json

Flags

Get Dataset: ax datasets get

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

ax datasets get DATASET_ID
ax datasets get DATASET_ID -o json

Flags

Response fields

Export Dataset: ax datasets export

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

ax datasets export DATASET_ID
# -> dataset_abc123_20260305_141500/examples.json

ax datasets export DATASET_ID --all
ax datasets export DATASET_ID --version-id VERSION_ID
ax datasets export DATASET_ID --output-dir ./data
ax datasets export DATASET_ID --stdout
ax datasets export DATASET_ID --stdout | jq '.[0]'

Flags

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:

# Get the server-reported count from dataset metadata
ax datasets get DATASET_ID -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:

[
  {
    "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.

ax datasets create --name "My Dataset" --space-id SPACE_ID --file data.csv
ax datasets create --name "My Dataset" --space-id SPACE_ID --file data.json
ax datasets create --name "My Dataset" --space-id SPACE_ID --file data.jsonl
ax datasets create --name "My Dataset" --space-id SPACE_ID --file data.parquet

Flags

Passing data via stdin

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

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

# Or with a heredoc
ax datasets create --name "my-dataset" --space-id SPACE_ID --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 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:

ax datasets append DATASET_ID --json '[{"question": "What is 2+2?", "answer": "4"}]'

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

From a file

ax datasets append DATASET_ID --file new_examples.csv
ax datasets append DATASET_ID --file additions.json

To a specific version

ax datasets append DATASET_ID --json '[{"q": "..."}]' --version-id VERSION_ID

Flags

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:

# Check existing field names in the dataset
ax datasets export DATASET_ID --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

ax datasets delete DATASET_ID
ax datasets delete DATASET_ID --force   # skip confirmation prompt

Flags

Workflows

Find a dataset by name

Users often refer to datasets by name rather than ID. Resolve a name to an ID before running other commands:

# Find dataset ID by name
ax datasets list -o json | jq '.[] | select(.name == "eval-set-v1") | .id'

# If the list is paginated, fetch more
ax datasets list -o json --limit 100 | jq '.[] | select(.name | test("eval-set")) | {id, name}'

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-id SPACE_ID --file eval_data.csv
3. Verify: ax datasets get DATASET_ID
4. Use the dataset ID to run experiments

Add examples to an existing dataset

# Find the dataset
ax datasets list

# Append inline or from a file (see Append Examples section for full syntax)
ax datasets append DATASET_ID --json '[{"question": "...", "answer": "..."}]'
ax datasets append DATASET_ID --file additional_examples.csv

Download dataset for offline analysis

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

Export a specific version

# List versions
ax datasets get DATASET_ID -o json | jq '.versions'

# Export that version
ax datasets export DATASET_ID --version-id VERSION_ID

Iterate on a dataset

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

Pipe export to other tools

# Count examples
ax datasets export DATASET_ID --stdout | jq 'length'

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

# Convert to CSV with jq
ax datasets export DATASET_ID --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:

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

Save Credentials for Future Use

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