Clickhouse Eval Results Retrieve

GET

https://api.respan.ai/clickhouse/eval-results/:id/

GET

/clickhouse/eval-results/:id/

$ curl https://api.respan.ai/clickhouse/eval-results/id/ \
>      -H "Authorization: Bearer <token>"

200Retrieved

1 {
2   "id": "string",
3   "created_at": "2024-01-15T09:30:00Z",
4   "updated_by": 1,
5   "evaluator": {
6     "is_public": true,
7     "created_by": {
8       "id": 1,
9       "email": "string",
10       "name": "string",
11       "username": "string",
12       "first_name": "string",
13       "last_name": "string"
14     },
15     "updated_by": {
16       "id": 1,
17       "email": "string",
18       "name": "string",
19       "username": "string",
20       "first_name": "string",
21       "last_name": "string"
22     },
23     "editor": {
24       "id": 1,
25       "email": "string",
26       "name": "string",
27       "username": "string",
28       "first_name": "string",
29       "last_name": "string"
30     },
31     "name": "string",
32     "created_at": "2024-01-15T09:30:00Z",
33     "updated_at": "2024-01-15T09:30:00Z",
34     "version_id": "string",
35     "configurations": {},
36     "categorical_choices": [
37       {}
38     ],
39     "score_config": {},
40     "passing_conditions": {},
41     "llm_config": {},
42     "code_config": {},
43     "project": "string",
44     "eval_class": "string",
45     "id": "string",
46     "version": 1,
47     "is_read_only": true,
48     "version_description": "string",
49     "evaluator_slug": "string",
50     "description": "string",
51     "type": "llm",
52     "score_value_type": "numerical",
53     "custom_required_fields": [
54       "string"
55     ],
56     "starred": true
57   },
58   "inputs": "string",
59   "type": "llm",
60   "environment": "string",
61   "numerical_value": 1.1,
62   "string_value": "string",
63   "boolean_value": true,
64   "categorical_value": [
65     "string"
66   ],
67   "json_value": "string",
68   "is_passed": true,
69   "cost": 1.1,
70   "evaluator_id": "string",
71   "evaluator_slug": "string",
72   "scorer": "string",
73   "log_id": "string",
74   "prompt_id": "string",
75   "prompt_version_number": 1,
76   "dataset_id": "string",
77   "status": "pending",
78   "error_message": "string"
79 }

Operates on the Postgres-based EvalResult models for update and detail point retrieval Synced to clickhouse automatically via evaluation.signals

Authentication

AuthorizationBearer

JWT access token or Respan API key

Path parameters

idstringRequired

Response

idstringRead-only

created_atdatetimeRead-only

updated_byinteger or nullRead-only

evaluatorobject

User-friendly serializer for evaluator detail view via API.

inputsstringRead-only

typeenumOptional

llm - Llm
code - Code
human - Human
function - Function
human_numerical - Human Numerical
human_categorical - Human Categorical
human_boolean - Human Boolean
human_text - Human Text
custom - Custom

environmentstringOptional<=30 characters

numerical_valuedoubleOptional

string_valuestringOptional

boolean_valueboolean or nullOptional

categorical_valuelist of stringsOptional

json_valuestringOptional

is_passedbooleanOptional

costdoubleOptional

evaluator_idstringOptional

evaluator_slugstringOptional<=255 characters

scorerstringOptional<=255 characters

log_idstringOptional

prompt_idstringOptional

prompt_version_numberintegerOptional

dataset_idstringOptional

statusenumOptional

pending - Pending
completed - Completed
failed - Failed

error_messagestring or nullOptional