Annotate a batch of experiment runs
Write human annotations to a batch of runs in an experiment.
Idempotency: Writes use upsert semantics — submitting the same annotation config name for the same run overwrites the previous value. Retrying on network failure will not create duplicates.
202 Accepted: The annotations have been accepted and will be written. Visibility in read queries may lag by a short interval. No response body is returned.
Unmatched record IDs: If a record_id does not correspond to an existing run in the experiment, the annotation for that record is silently ignored. No error is returned.
Payload Requirements
- experiment_id is the path parameter for the target experiment.
- annotations is a list of per-run annotation inputs, each identified by record_id.
- Annotation names must match existing annotation configs in the experiment's space.
- Up to 1000 runs may be annotated per request.
Valid example
{
"annotations": [
{"record_id": "run_abc", "values": [{"name": "quality", "label": "good"}]}
]
}
Invalid example (annotation name not found in space)
{
"annotations": [
{"record_id": "run_abc", "values": [{"name": "nonexistent_config"}]}
]
}
<Note>This endpoint is in beta, read more here.</Note>
Path parameters
A universally unique identifier (base64-encoded opaque string).
The unique experiment identifier (base64)
Request body
Example request
{
"annotations": [
{
"values": [
{
"name": "accuracy"
}
]
}
]
}Response
Annotations written successfully. The annotations have been accepted and will be written. Visibility in read queries may lag by a short interval.