Log

Log an external generation to an evaluation run for a datapoint.

The run must have status ‘running’.

Path parameters

evaluation_idstringRequired

ID of the evaluation run. Starts with evrun_.

Query parameters

evaluatee_idstringOptional

String ID of evaluatee version to return. If not defined, the first evaluatee will be returned. Starts with evv_.

Request

This endpoint expects an object.

datapoint_idstringRequired

The datapoint for which a log was generated. Must be one of the datapoints in the dataset being evaluated.

logobjectRequired

The log generated for the datapoint.

Response

Successful Response

idstring

String ID of logged datapoint. Starts with data_.

project_idstring

String ID of project the datapoint belongs to. Starts with pr_.

session_idstringOptional

String ID of session the datapoint belongs to. Populated only if the datapoint was logged with session_id or session_reference_id, and is None otherwise. Starts with sesh_.

1	import requests
2
3	url = "https://api.humanloop.com/v4/evaluations/evaluation_id/log"
4
5	payload = {
6	"datapoint_id": "datapoint_id",
7	"log": {}
8	}
9	headers = {
10	"X-API-KEY": "<apiKey>",
11	"Content-Type": "application/json"
12	}
13
14	response = requests.post(url, json=payload, headers=headers)
15
16	print(response.json())

Path parameters

Headers

Query parameters

Request

Response

Errors