For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
DiscordPlatform
DocumentationIntegrationsAPI referenceSDKsChangelog
DocumentationIntegrationsAPI referenceSDKsChangelog
  • API Reference
      • POSTCreate an evaluator
      • POSTList evaluators with filters
      • GETRetrieve an evaluator
      • PATCHUpdate an evaluator
      • DELDelete an evaluator
      • POSTRun an evaluator
      • GETList evaluators
      • GETGet evaluators summary
      • POSTGet filtered evaluators summary
      • PUTReplace an evaluator
      • GETList evaluator versions
      • POSTCreate evaluator version
      • GETRetrieve evaluator version
      • PUTReplace evaluator version
      • PATCHUpdate evaluator version
  • Reference
    • Filters API Reference
LogoLogo
DiscordPlatform
API ReferenceEvaluators

List evaluators with filters

POST
https://api.respan.ai/api/evaluators/list/
POST
/api/evaluators/list/
$curl -X POST "https://api.respan.ai/api/evaluators/list/?sort_by=name" \
>     -H "Authorization: Bearer sk_live_xxxxx" \
>     -H "Content-Type: application/json" \
>     -d '{}'
1{
2  "count": 1,
3  "results": [
4    {
5      "id": "evl_550e8400",
6      "name": "Response Quality",
7      "type": "llm",
8      "score_value_type": "numerical",
9      "version_id": "evlv_550e8400",
10      "version": 1,
11      "is_read_only": false,
12      "version_description": "Tightened rubric wording",
13      "evaluator_slug": "response_quality",
14      "eval_class": "keywordsai_custom_llm",
15      "description": "Grades whether the response is accurate and complete.",
16      "score_config": {
17        "min_score": 1,
18        "max_score": 5,
19        "choices": [
20          {
21            "name": "Excellent",
22            "value": "excellent"
23          }
24        ]
25      },
26      "passing_conditions": {
27        "primary_score": {
28          "operator": "gte",
29          "value": 3
30        }
31      },
32      "llm_config": {
33        "model": "gpt-4o-mini",
34        "evaluator_definition": "Rate the response quality.\n<input>{{input}}</input>\n<output>{{output}}</output>",
35        "scoring_rubric": "1=Poor, 5=Excellent",
36        "temperature": 0.1,
37        "max_tokens": 200,
38        "top_p": 0.9,
39        "frequency_penalty": 0.5,
40        "presence_penalty": 0.3,
41        "stop": [
42          "\n"
43        ],
44        "response_format": {},
45        "tools": [
46          {}
47        ],
48        "verbosity": "detailed"
49      },
50      "code_config": {
51        "eval_code_snippet": "def main(eval_inputs):\n    return 1 if eval_inputs.get('output') else 0"
52      },
53      "configurations": {},
54      "categorical_choices": [
55        {
56          "name": "Excellent",
57          "value": "excellent"
58        }
59      ],
60      "starred": false,
61      "created_at": "2024-01-15T09:30:00Z",
62      "updated_at": "2024-01-15T09:30:00Z",
63      "created_by": {
64        "id": 101,
65        "first_name": "Alice",
66        "last_name": "Johnson",
67        "email": "alice.johnson@respan.ai"
68      },
69      "updated_by": {
70        "id": 102,
71        "first_name": "Bob",
72        "last_name": "Smith",
73        "email": "bob.smith@respan.ai"
74      },
75      "editor": {
76        "id": 103,
77        "first_name": "Carol",
78        "last_name": "Davis",
79        "email": "carol.davis@respan.ai"
80      },
81      "tags": [
82        {
83          "id": 10,
84          "name": "Quality",
85          "color": "#4CAF50"
86        }
87      ]
88    }
89  ],
90  "next": "https://api.respan.ai/api/evaluators/list/?page=2",
91  "previous": "https://api.respan.ai/api/evaluators/list/?page=1",
92  "current_filters": {},
93  "filters_data": {}
94}

List evaluators using POST-for-filtering. The backend returns only the current draft/latest row for each evaluator and includes filter metadata for dashboard clients.

Was this page helpful?
Previous

Retrieve an evaluator

Next
Built with

Headers

AuthorizationstringRequired

Bearer token. Use Bearer YOUR_API_KEY for API key auth or Bearer <JWT> for dashboard auth.

Query parameters

pageintegerOptional>=1
Page number.
page_sizeintegerOptional1-100
Number of results to return per page. Maximum 100.
sort_bystringOptional

Field to sort by. Prefix with - for descending order.

Request

This endpoint expects an object.
filtersobjectOptional
Filter criteria using the standard Respan filter format.
is_exportingbooleanOptionalDefaults to false
Reserved for dashboard exports.

Response

Paginated filtered evaluator list.
countinteger
Number of resources returned on this page.
resultslist of objects
nextstring or null
URL for the next page, if any.
previousstring or null
URL for the previous page, if any.
current_filtersobject
Normalized filters applied to this request.
filters_datamap from strings to any
Available filter options for evaluator list UI clients.

Errors

400
Bad Request Error
401
Unauthorized Error