OverviewHistoryStatsSecurity
npx skills add ...
Documentation
SKILL.md
npx skills add arize-ai/arize-skills --skill arize-annotation
Creates and manages annotation configs (categorical, continuous, freeform label schemas) and annotation queues (human review workflows) on Arize. Applies human annotations to project spans via the Python SDK. Use when the user mentions annotation config, annotation queue, label schema, human feedback, bulk annotate spans, update_annotations, labeling queue, annotate record, or human review.
npx skills add arize-ai/arize-skills --skill arize-annotation
SPACE—--spaceflags accept a space name (e.g.,my-workspace) or a base64 space ID (e.g.,U3BhY2U6...). Find yours withax spaces list.
This skill covers annotation configs (the label schema) and annotation queues (human review workflows), as well as programmatically annotating project spans via the Python SDK.
Direction: Human labeling in Arize attaches values defined by configs to spans, dataset examples, experiment-related records, and queue items in the product UI. This skill covers: ax annotation-configs, ax annotation-queues, and bulk span updates with ArizeClient.spans.update_annotations.
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.md401 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 Keysax spaces list to pick by name, or ask the user.env files or search the filesystem for credentials. Use ax profiles for Arize credentials and ax ai-integrations for LLM provider keys. Never ask the user to paste secrets into chat. For missing credentials, see references/ax-profiles.md.An annotation config defines the schema for a single type of human feedback label. Before anyone can annotate a span, dataset record, experiment output, or queue item, a config must exist for that label in the space.
| Field | Description |
|---|---|
| Name | Descriptive identifier (e.g. Correctness, Helpfulness). Must be unique within the space. |
| Type | CATEGORICAL (pick from a list), CONTINUOUS (numeric range), or FREEFORM (free text). |
| Values | For categorical: array of {"label": str, "score": number} pairs. |
| Min/Max Score | For continuous: numeric bounds. |
| Optimization Direction | Whether higher scores are better (MINIMIZE) or worse (MAXIMIZE). Used to render trends in the UI. |
| Surface | Typical path |
|---|---|
| Project spans | Python SDK spans.update_annotations (below) and/or the Arize UI |
| Dataset examples | Arize UI (human labeling flows); configs must exist in the space |
| Experiment outputs | Often reviewed alongside datasets or traces in the UI — see arize-experiment, arize-dataset |
| Annotation queue items | ax annotation-queues CLI (below) and/or the Arize UI; configs must exist |
Always ensure the relevant annotation config exists in the space before expecting labels to persist.
Categorical configs present a fixed set of labels for reviewers to choose from.
Common binary label pairs:
correct / incorrecthelpful / unhelpfulsafe / unsaferelevant / irrelevantpass / failContinuous configs let reviewers enter a numeric score within a defined range.
Freeform configs collect open-ended text feedback. No additional flags needed beyond name and space.
Each config type has its own update command. Only changed fields are updated.
Freeform:
Continuous:
Categorical:
--space is required when using a name instead of ID. Each --value supplies the
complete categorical label list: it replaces existing labels rather than appending to
them. Repeat --value for every label that should remain, or omitted labels are removed.
Note: Deletion is irreversible. Any annotation queue associations to this config are also removed in the product (queues may remain; fix associations in the Arize UI if needed).
ax annotation-queuesAnnotation queues route records (spans, dataset examples, experiment runs) to human reviewers. Each queue is linked to one or more annotation configs that define what labels reviewers can apply.
At least one --annotation-config-id is required.
Repeat --annotation-config-id and --annotator-email to attach multiple configs or reviewers.
Add records to an existing queue after creation. Records can come from spans (by project and time range) or dataset examples.
--record-sources is required and accepts a JSON file path or inline JSON array. Each source specifies record_type (SPAN or EXAMPLE) plus type-specific fields:
project_id, start_time (ISO 8601), end_time (ISO 8601), optional span_idsdataset_id, example_idsList flags (--annotation-config-id, --annotator-email) fully replace existing values when provided — pass all desired values, not just the new ones.
Annotations are upserted by config name — call once per annotation config. Supply at least one of --score, --label, or --text.
Assign users to review a specific record by repeating --email; this fully replaces existing assignments, so pass every assignee each time (passing no --email flags clears all assignments):
Use the Python SDK to bulk-apply annotations to project spans when you already have labels (e.g., from a review export or an external labeling tool).
DataFrame column schema:
| Column | Required | Description |
|---|---|---|
context.span_id | yes | The span to annotate |
annotation.<name>.label | one of | Categorical or freeform label |
annotation.<name>.score | one of | Numeric score |
annotation.<name>.updated_by | no | Annotator identifier (email or name) |
annotation.<name>.updated_at | no | Timestamp in milliseconds since epoch |
annotation.notes | no | Freeform notes on the span |
Limitation: Annotations apply only to spans within 31 days prior to submission.
| Problem | Solution |
|---|---|
ax: command not found | See references/ax-setup.md |
401 Unauthorized | API key may not have access to this space. Verify at https://app.arize.com/admin > API Keys |
Annotation config not found | ax annotation-configs list --space SPACE (or use ax annotation-configs get NAME_OR_ID --space SPACE) |
409 Conflict on create | Name already exists in the space. Use a different name or get the existing config ID. |
| Queue not found | ax annotation-queues list --space SPACE; verify the queue name or ID |
| Record not appearing in queue | Ensure the annotation config linked to the queue exists; check ax annotation-configs list --space SPACE |
| Span SDK errors or missing spans | Confirm project_name, space_id, and span IDs; use arize-trace to export spans |
The ax CLI provides batch annotation commands for writing annotations at scale without the Python SDK. All commands accept a file (CSV, JSON, JSONL, or Parquet) with up to 1000 annotations per request and use upsert semantics (existing annotations with the same key are updated; new ones are created).
| Resource | Command | Skill |
|---|---|---|
| Spans | ax spans annotate PROJECT --file annotations.json | arize-trace |
| Dataset examples | ax datasets annotate-examples NAME_OR_ID --file annotations.json | arize-dataset |
| Experiment runs | ax experiments annotate-runs NAME_OR_ID --file annotations.json --dataset DATASET | arize-experiment |
All three commands support --space SPACE. See the linked skills for full flag tables and file format details.
ax spans annotateax datasets annotate-examplesax experiments annotate-runsSee references/ax-profiles.md § Save Credentials for Future Use.
ax annotation-configs create categorical \
--name "Correctness" \
--space SPACE \
--value correct \
--value incorrect \
--optimization-direction MAXIMIZEax annotation-configs create continuous \
--name "Quality Score" \
--space SPACE \
--min-score 0 \
--max-score 10 \
--optimization-direction MAXIMIZEax annotation-configs create freeform \
--name "Reviewer Notes" \
--space SPACEax annotation-configs get NAME_OR_ID
ax annotation-configs get NAME_OR_ID -o json
ax annotation-configs get NAME_OR_ID --space SPACE # required when using name instead of IDax annotation-configs update freeform NAME_OR_ID --space SPACE --new-name "Updated Name"ax annotation-configs update continuous NAME_OR_ID --space SPACE --min-score 1 --max-score 5 --optimization-direction MINIMIZEax annotation-configs update categorical NAME_OR_ID --space SPACE --value correct --value incorrect --optimization-direction MAXIMIZEax annotation-configs delete NAME_OR_ID
ax annotation-configs delete NAME_OR_ID --space SPACE # required when using name instead of ID
ax annotation-configs delete NAME_OR_ID --force # skip confirmationax annotation-queues list --space SPACE
ax annotation-queues list --space SPACE -o json
ax annotation-queues list --space SPACE --name "Review" # substring filter
ax annotation-queues get NAME_OR_ID --space SPACE
ax annotation-queues get NAME_OR_ID --space SPACE -o jsonax annotation-queues create \
--name "Correctness Review" \
--space SPACE \
--annotation-config-id CONFIG_ID \
--annotator-email reviewer@example.com \
--instructions "Label each response as correct or incorrect." \
--assignment-method ALL # or: RANDOMax annotation-queues add-records NAME_OR_ID --space SPACE --record-sources sources.json
ax annotation-queues add-records NAME_OR_ID --space SPACE \
--record-sources '[{"record_type": "EXAMPLE", "dataset_id": "ds-1", "example_ids": ["ex-1", "ex-2"]}]'ax annotation-queues update NAME_OR_ID --space SPACE --name "New Name"
ax annotation-queues update NAME_OR_ID --space SPACE --instructions "Updated instructions"
ax annotation-queues update NAME_OR_ID --space SPACE \
--annotation-config-id CONFIG_ID_A \
--annotation-config-id CONFIG_ID_Bax annotation-queues delete NAME_OR_ID --space SPACE
ax annotation-queues delete NAME_OR_ID --space SPACE --force # skip confirmationax annotation-queues list-records NAME_OR_ID --space SPACE
ax annotation-queues list-records NAME_OR_ID --space SPACE --limit 50 -o jsonax annotation-queues annotate-record NAME_OR_ID RECORD_ID \
--annotation-name "Correctness" \
--label "correct" \
--space SPACE
ax annotation-queues annotate-record NAME_OR_ID RECORD_ID \
--annotation-name "Quality Score" \
--score 8.5 \
--text "Response was accurate but slightly verbose." \
--space SPACEax annotation-queues assign-record NAME_OR_ID RECORD_ID --email user@example.com --space SPACEax annotation-queues delete-records NAME_OR_ID --space SPACEimport pandas as pd
from arize import ArizeClient
import os
client = ArizeClient(api_key=os.environ["ARIZE_API_KEY"])
# Build a DataFrame with annotation columns
# Required: context.span_id + at least one annotation.<name>.label or annotation.<name>.score
annotations_df = pd.DataFrame([
{
"context.span_id": "span_001",
"annotation.Correctness.label": "correct",
"annotation.Correctness.updated_by": "reviewer@example.com",
},
{
"context.span_id": "span_002",
"annotation.Correctness.label": "incorrect",
"annotation.Correctness.updated_by": "reviewer@example.com",
},
])
response = client.spans.update_annotations(
space_id=os.environ["ARIZE_SPACE_ID"],
project_name="your-project",
dataframe=annotations_df,
validate=True,
)