Models Datasets · Querying PostHog Data · PostHog/skills · Skills Docs

Models Datasets · Querying PostHog Data · PostHog/skills · Skills Docs

Column	Type	Nullable	Description
`id`	UUID	NOT NULL	Dataset UUID.
`team_id`	Integer	NOT NULL
`name`	String	NOT NULL	Dataset name.
`description`	String	NOT NULL	What the dataset contains.
`metadata`	JSON	NOT NULL	JSON dataset metadata.
`archived`	Boolean	NOT NULL	Whether the dataset is archived.
`current_revision_id`	UUID	NULL	Latest committed revision; NULL before the first item mutation.
`created_by_id`	Integer	NULL	User who created the dataset.
`created_at`	DateTime	NOT NULL	When the dataset was created.
`updated_at`	DateTime	NULL	When the dataset fields or item contents last changed.

Column	Type	Nullable	Description
`id`	UUID	NOT NULL	Dataset revision UUID.
`team_id`	Integer	NOT NULL
`dataset_id`	UUID	NOT NULL	Parent dataset; joins to datasets.id.
`revision`	Integer	NOT NULL	Monotonic revision number within the dataset.
`created_by_id`	Integer	NULL	User who committed the revision.
`created_at`	DateTime	NOT NULL	When the revision was committed.

Column	Type	Nullable	Description
`id`	UUID	NOT NULL	Stable dataset item UUID.
`team_id`	Integer	NOT NULL
`dataset_id`	UUID	NOT NULL	Parent dataset; joins to datasets.id.
`client_item_id`	String	NULL	Optional caller-owned stable key, unique within the dataset.
`current_version_id`	UUID	NULL	Latest immutable item version.
`created_by_id`	Integer	NULL	User who created the item.
`created_at`	DateTime	NOT NULL	When the item was created.
`updated_at`	DateTime	NULL	When the item last received a version.

Column	Type	Nullable	Description
`id`	UUID	NOT NULL	Dataset item version UUID.
`team_id`	Integer	NOT NULL
`dataset_id`	UUID	NOT NULL	Parent dataset; joins to datasets.id.
`dataset_item_id`	UUID	NOT NULL	Stable item; joins to dataset_items.id.
`dataset_revision_id`	UUID	NOT NULL	Revision that introduced this version; joins to dataset_revisions.id.
`version`	Integer	NOT NULL	Monotonic version number within the item.
`archived`	Boolean	NOT NULL	Whether this version archives the item.
`input`	JSON	NOT NULL	JSON input supplied to the system under test.
`expected_output`	JSON	NULL	Optional JSON expected output.
`source_output`	JSON	NULL	Optional JSON output captured from the source trace.
`metadata`	JSON	NOT NULL	JSON item metadata.
`source_trace_id`	String	NULL	Source AI trace ID.
`source_event_id`	String	NULL	Source event ID within the trace.
`source_timestamp`	DateTime	NULL	Timestamp used to retrieve the source trace event.
`created_by_id`	Integer	NULL	User who created this version.
`created_at`	DateTime	NOT NULL	When the version was created.

SELECT
    i.id,
    i.client_item_id,
    v.version,
    v.input,
    v.expected_output,
    v.source_output,
    v.metadata
FROM system.dataset_items AS i
INNER JOIN system.dataset_item_versions AS v ON v.id = i.current_version_id
WHERE i.dataset_id = '01234567-89ab-cdef-0123-456789abcdef'
  AND v.archived = false
ORDER BY i.created_at DESC
LIMIT 100

SELECT
    i.id,
    i.client_item_id,
    argMax(v.version, r.revision) AS version,
    argMax(v.input, r.revision) AS input,
    tupleElement(argMax(tuple(v.expected_output), r.revision), 1) AS expected_output,
    tupleElement(argMax(tuple(v.source_output), r.revision), 1) AS source_output,
    argMax(v.metadata, r.revision) AS metadata
FROM system.dataset_items AS i
INNER JOIN system.dataset_item_versions AS v ON v.dataset_item_id = i.id
INNER JOIN system.dataset_revisions AS r ON r.id = v.dataset_revision_id
WHERE i.dataset_id = '01234567-89ab-cdef-0123-456789abcdef'
  AND r.revision <= 7
GROUP BY i.id, i.client_item_id
HAVING argMax(v.archived, r.revision) = false
ORDER BY i.id

SELECT
    version,
    archived,
    input,
    expected_output,
    metadata,
    dataset_revision_id,
    created_by_id,
    created_at
FROM system.dataset_item_versions
WHERE dataset_item_id = '01234567-89ab-cdef-0123-456789abcdef'
ORDER BY version DESC