Get Logs for Evaluation

GET

https://api.humanloop.com/v5/evaluations/:id/logs

GET

/v5/evaluations/:id/logs

1 from humanloop import Humanloop
2 
3 client = Humanloop(
4     api_key="YOUR_API_KEY",
5 )
6 client.evaluations.get_logs(
7     id="id",
8 )

Try it

1 {
2   "records": [
3     {
4       "run_id": "run_id",
5       "log": {
6         "prompt": {
7           "path": "path",
8           "id": "id",
9           "model": "model",
10           "name": "name",
11           "version_id": "version_id",
12           "created_at": "2024-01-15T09:30:00Z",
13           "updated_at": "2024-01-15T09:30:00Z",
14           "last_used_at": "2024-01-15T09:30:00Z",
15           "version_logs_count": 1,
16           "total_logs_count": 1,
17           "inputs": [
18             {
19               "name": "name"
20             }
21           ]
22         },
23         "id": "id",
24         "evaluator_logs": [
25           {
26             "id": "id",
27             "evaluator_logs": [],
28             "evaluator": {
29               "path": "path",
30               "id": "id",
31               "spec": {
32                 "arguments_type": "target_free",
33                 "return_type": "boolean",
34                 "evaluator_type": "llm"
35               },
36               "name": "name",
37               "version_id": "version_id",
38               "created_at": "2024-01-15T09:30:00Z",
39               "updated_at": "2024-01-15T09:30:00Z",
40               "last_used_at": "2024-01-15T09:30:00Z",
41               "version_logs_count": 1,
42               "total_logs_count": 1,
43               "inputs": [
44                 {
45                   "name": "name"
46                 }
47               ]
48             }
49           }
50         ]
51       },
52       "evaluator_logs": [
53         {
54           "prompt": {
55             "path": "path",
56             "id": "id",
57             "model": "model",
58             "name": "name",
59             "version_id": "version_id",
60             "created_at": "2024-01-15T09:30:00Z",
61             "updated_at": "2024-01-15T09:30:00Z",
62             "last_used_at": "2024-01-15T09:30:00Z",
63             "version_logs_count": 1,
64             "total_logs_count": 1,
65             "inputs": [
66               {
67                 "name": "name"
68               }
69             ]
70           },
71           "id": "id",
72           "evaluator_logs": [
73             {
74               "id": "id",
75               "evaluator_logs": [],
76               "evaluator": {
77                 "path": "path",
78                 "id": "id",
79                 "spec": {
80                   "arguments_type": "target_free",
81                   "return_type": "boolean",
82                   "evaluator_type": "llm"
83                 },
84                 "name": "name",
85                 "version_id": "version_id",
86                 "created_at": "2024-01-15T09:30:00Z",
87                 "updated_at": "2024-01-15T09:30:00Z",
88                 "last_used_at": "2024-01-15T09:30:00Z",
89                 "version_logs_count": 1,
90                 "total_logs_count": 1,
91                 "inputs": [
92                   {
93                     "name": "name"
94                   }
95                 ]
96               }
97             }
98           ]
99         }
100       ],
101       "datapoint": {
102         "id": "id"
103       }
104     }
105   ],
106   "page": 1,
107   "size": 1,
108   "total": 1
109 }

Get the Logs associated to a specific Evaluation.

This returns the Logs associated to all Runs within with the Evaluation.

Path parameters

idstringRequired

String ID of evaluation. Starts with ev_ or evr_.

Query parameters

pageintegerOptional>=1Defaults to 1

Page number for pagination.

sizeintegerOptional>=0Defaults to 10

Page size for pagination. Number of Logs to fetch.

run_idstringOptional

Filter by Run IDs. Only Logs for the specified Runs will be returned.

Response

Successful Response

recordslist of objects

pageinteger

sizeinteger

totalinteger

Get Logs for Evaluation

Path parameters

Headers

Query parameters

Response

Errors