List Evaluators

1 from humanloop import Humanloop 2 client = Humanloop(api_key="YOUR_API_KEY", ) 3 response = client.evaluators.list(size=1, ) 4 for item in response: 5 yield item 6 # alternatively, you can paginate page-by-page 7 for page in response.iter_pages(): 8 yield page

1 { 2 "records": [ 3 { 4 "path": "Shared Evaluators/Accuracy Evaluator", 5 "id": "ev_890bcd", 6 "spec": { 7 "arguments_type": "target_required", 8 "return_type": "number", 9 "evaluator_type": "python", 10 "code": "def evaluate(answer, target):\n return 0.5" 11 }, 12 "name": "Accuracy Evaluator", 13 "version_id": "evv_012def", 14 "created_at": "2024-05-01T12:00:00Z", 15 "updated_at": "2024-05-01T12:00:00Z", 16 "last_used_at": "2024-05-01T12:00:00Z", 17 "version_logs_count": 1, 18 "total_logs_count": 1, 19 "inputs": [ 20 { 21 "name": "answer" 22 } 23 ], 24 "type": "evaluator" 25 } 26 ], 27 "page": 0, 28 "size": 1, 29 "total": 1 30 }

Get a list of all Evaluators.

Query parameters

pageintegerOptional>=1Defaults to 1

Page offset for pagination.

sizeintegerOptionalDefaults to 10

Page size for pagination. Number of Evaluators to fetch.

namestringOptional

Case-insensitive filter for Evaluator name.

user_filterstringOptional

Case-insensitive filter for users in the Evaluator. This filter matches against both email address and name of users.

sort_byenumOptional

Field to sort Evaluators by

Allowed values:

orderenumOptional

Direction to sort by.

Allowed values:

Response

Successful Response

recordslist of objects

pageinteger

sizeinteger

totalinteger

Headers

Query parameters

Response

Errors