Humanloop Documentation and API Reference

Update the status of an evaluation run.

Can only be used to update the status of an evaluation run that uses external or human evaluators. The evaluation must currently have status ‘running’ if swithcing to completed, or it must have status ‘completed’ if switching back to ‘running’.

Path parameters

idstringRequired

String ID of evaluation run. Starts with ev_.

Request

This endpoint expects an object.

statusenumRequired

Allowed values: pendingrunningcompletedcancelled

The new status of the evaluation.

Response

Successful Response

idstring

Unique ID for the evaluation. Starts with ev_.

statusenum

Allowed values: pendingrunningcompletedcancelled

Status of an evaluation.

configobject

created_atdatetime

updated_atdatetime

evaluatorslist of objects

datasetobject

dataset_version_idstring

dataset_snapshotobjectOptional

evaluator_aggregateslist of objectsOptional

Errors

1 curl -X PATCH https://api.humanloop.com/v4/evaluations/id/status \ 2 -H "X-API-KEY: <apiKey>" \ 3 -H "Content-Type: application/json" \ 4 -d '{ 5 "status": "pending" 6 }'

1 { 2 "id": "id", 3 "status": "pending", 4 "config": { 5 "type": "generic", 6 "id": "config", 7 "name": "config", 8 "status": "config", 9 "created_by": { 10 "id": "id", 11 "email_address": "email_address", 12 "verified": true, 13 "full_name": "full_name" 14 }, 15 "description": "config", 16 "other": { 17 "key": "value" 18 } 19 }, 20 "created_at": "2024-01-15T09:30:00Z", 21 "updated_at": "2024-01-15T09:30:00Z", 22 "evaluators": [ 23 { 24 "name": "name", 25 "description": "description", 26 "arguments_type": "target_free", 27 "return_type": "boolean", 28 "type": "python", 29 "id": "id", 30 "created_at": "2024-01-15T09:30:00Z", 31 "updated_at": "2024-01-15T09:30:00Z", 32 "code": "code", 33 "model_config": { 34 "id": "id", 35 "model": "model" 36 }, 37 "logging_project": { 38 "id": "id", 39 "name": "name", 40 "users": [ 41 { 42 "id": "id", 43 "email_address": "email_address" 44 } 45 ], 46 "data_count": 1, 47 "feedback_types": [ 48 { 49 "type": "rating" 50 } 51 ], 52 "team_id": "team_id", 53 "created_at": "2024-01-15T09:30:00Z", 54 "updated_at": "2024-01-15T09:30:00Z" 55 } 56 } 57 ], 58 "dataset": { 59 "id": "id", 60 "name": "name", 61 "datapoint_count": 1, 62 "created_at": "2024-01-15T09:30:00Z", 63 "updated_at": "2024-01-15T09:30:00Z", 64 "project_id": "project_id", 65 "description": "description" 66 }, 67 "dataset_version_id": "dataset_version_id", 68 "dataset_snapshot": { 69 "id": "id", 70 "name": "name", 71 "datapoint_count": 1, 72 "created_at": "2024-01-15T09:30:00Z", 73 "updated_at": "2024-01-15T09:30:00Z", 74 "project_id": "project_id", 75 "description": "description" 76 }, 77 "evaluator_aggregates": [ 78 { 79 "model_config_id": "model_config_id", 80 "evaluator_id": "evaluator_id", 81 "evaluator_version_id": "evaluator_version_id", 82 "aggregate_value": 1.1 83 } 84 ] 85 }

1	curl -X PATCH https://api.humanloop.com/v4/evaluations/id/status \
2	-H "X-API-KEY: <apiKey>" \
3	-H "Content-Type: application/json" \
4	-d '{
5	"status": "pending"
6	}'

1	{
2	"id": "id",
3	"status": "pending",
4	"config": {
5	"type": "generic",
6	"id": "config",
7	"name": "config",
8	"status": "config",
9	"created_by": {
10	"id": "id",
11	"email_address": "email_address",
12	"verified": true,
13	"full_name": "full_name"
14	},
15	"description": "config",
16	"other": {
17	"key": "value"
18	}
19	},
20	"created_at": "2024-01-15T09:30:00Z",
21	"updated_at": "2024-01-15T09:30:00Z",
22	"evaluators": [
23	{
24	"name": "name",
25	"description": "description",
26	"arguments_type": "target_free",
27	"return_type": "boolean",
28	"type": "python",
29	"id": "id",
30	"created_at": "2024-01-15T09:30:00Z",
31	"updated_at": "2024-01-15T09:30:00Z",
32	"code": "code",
33	"model_config": {
34	"id": "id",
35	"model": "model"
36	},
37	"logging_project": {
38	"id": "id",
39	"name": "name",
40	"users": [
41	{
42	"id": "id",
43	"email_address": "email_address"
44	}
45	],
46	"data_count": 1,
47	"feedback_types": [
48	{
49	"type": "rating"
50	}
51	],
52	"team_id": "team_id",
53	"created_at": "2024-01-15T09:30:00Z",
54	"updated_at": "2024-01-15T09:30:00Z"
55	}
56	}
57	],
58	"dataset": {
59	"id": "id",
60	"name": "name",
61	"datapoint_count": 1,
62	"created_at": "2024-01-15T09:30:00Z",
63	"updated_at": "2024-01-15T09:30:00Z",
64	"project_id": "project_id",
65	"description": "description"
66	},
67	"dataset_version_id": "dataset_version_id",
68	"dataset_snapshot": {
69	"id": "id",
70	"name": "name",
71	"datapoint_count": 1,
72	"created_at": "2024-01-15T09:30:00Z",
73	"updated_at": "2024-01-15T09:30:00Z",
74	"project_id": "project_id",
75	"description": "description"
76	},
77	"evaluator_aggregates": [
78	{
79	"model_config_id": "model_config_id",
80	"evaluator_id": "evaluator_id",
81	"evaluator_version_id": "evaluator_version_id",
82	"aggregate_value": 1.1
83	}
84	]
85	}