Humanloop Documentation and API Reference

Create an Evaluator or update it with a new version if it already exists.

Evaluators are identified by the ID or their path. The spec provided determines the version of the Evaluator.

If you provide a commit message, then the new version will be committed; otherwise it will be uncommitted. If you try to commit an already committed version, an exception will be raised.

Request

This endpoint expects an object.

specobjectRequired

pathstringOptional

Path of the Evaluator, including the name. This locates the Evaluator in the Humanloop filesystem and is used as as a unique identifier. For example: folder/name or just name.

idstringOptional

ID for an existing Evaluator.

commit_messagestringOptional

Message describing the changes made.

Response

Successful Response

pathstring

Path of the Evaluator including the Evaluator name, which is used as a unique identifier.

idstring

Unique identifier for the Evaluator.

specobject

namestring

Name of the Evaluator, which is used as a unique identifier.

version_idstring

Unique identifier for the specific Evaluator Version. If no query params provided, the default deployed Evaluator Version is returned.

created_atdatetime

updated_atdatetime

statusenum

Allowed values: uncommittedcommitteddeleted

An enumeration.

last_used_atdatetime

version_logs_countinteger

The number of logs that have been generated for this Evaluator Version

total_logs_countinteger

The number of logs that have been generated across all Evaluator Versions

inputslist of objects

Inputs associated to the Evaluator. Inputs correspond to any of the variables used within the Evaluator template.

directory_idstringOptional

ID of the directory that the file is in on Humanloop.

commit_messagestringOptional

Message describing the changes made.

type"evaluator"OptionalDefaults to evaluator

environmentslist of objectsOptional

The list of environments the Evaluator Version is deployed to.

created_byanyOptional

The user who created the Evaluator.

evaluatorslist of objectsOptional

Evaluators that have been attached to this Evaluator that are used for monitoring logs.

evaluator_aggregateslist of objectsOptional

Aggregation of Evaluator results for the Evaluator Version.

attributesmap from strings to anyOptional

Additional fields to describe the Evaluator. Helpful to separate Evaluator versions from each other with details on how they were created or used.

1	curl -X POST https://api.humanloop.com/v5/evaluators \
2	-H "X-API-KEY: <apiKey>" \
3	-H "Content-Type: application/json" \
4	-d '{
5	"spec": {
6	"arguments_type": "target_required",
7	"return_type": "number",
8	"evaluator_type": "python",
9	"code": "def evaluate(answer, target):\n return 0.5"
10	},
11	"path": "Shared Evaluators/Accuracy Evaluator",
12	"commit_message": "Initial commit"
13	}'

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

Upsert Evaluator

Request

Response

Errors