Skip to main content
GET
/
metrics
Get metrics
curl --request GET \
  --url https://api.galtea.ai/metrics \
  --header 'Authorization: Bearer <token>'
[
  {
    "id": "metric_123",
    "organizationId": "org_123",
    "userId": "user_123",
    "name": "Accuracy",
    "evaluationParams": [
      "input",
      "actualOutput",
      "expectedOutput"
    ],
    "source": "FULL_PROMPT",
    "judgePrompt": "Evaluate the accuracy of the response",
    "tags": [
      "accuracy",
      "quality"
    ],
    "description": "Measures the accuracy of responses",
    "documentationUrl": "https://docs.example.com/metrics/accuracy",
    "evaluatorModelName": "GPT-4",
    "areEvalParamsTop": true,
    "isBeingOptimized": true,
    "specificationIds": [
      "spec_123"
    ],
    "userGroupIds": [
      "ug_123"
    ],
    "createdAt": "2023-11-07T05:31:56Z",
    "legacyAt": "2023-11-07T05:31:56Z",
    "disabledAt": "2023-11-07T05:31:56Z"
  }
]

Authorizations

Authorization
string
header
required

API key authorization. Pass your API key in the Authorization header as a Bearer token. Both new (gsk_*) and legacy (gsk-) API keys are accepted, e.g. Authorization: Bearer gsk_... or Authorization: Bearer gsk-....

Query Parameters

ids
string[]

Filter by metric IDs

organizationIds
string[]

Filter by organization IDs

productIds
string[]

Filter by product IDs

names
string[]

Filter by metric names (exact match, multiple)

name
string

Filter by metric name (partial match)

description
string

Filter by metric description (partial match)

tags
string[]

Filter by tags

sources
enum<string>[]

Filter by metric sources

Available options:
SELF_HOSTED,
FULL_PROMPT,
PARTIAL_PROMPT,
HUMAN_EVALUATION,
GEVAL,
DEEPEVAL,
DETERMINISTIC
specificationIds
string[]

Filter by specification IDs

userGroupIds
string[]

Filter by user group IDs

fromCreatedAt
string<date-time>

Filter metrics created at or after this timestamp (ISO 8601 format)

toCreatedAt
string<date-time>

Filter metrics created at or before this timestamp (ISO 8601 format)

includeDefaultEntities
boolean

Include default/predefined metrics

includeOwnEntities
boolean

Include metrics owned by the user's organization

includeLegacy
boolean

Include legacy/deprecated metrics

suitableForMonitoring
boolean

Filter metrics suitable for monitoring

sort
string[]

Sort instructions (field and direction pairs)

limit
integer

Maximum number of results

offset
integer

Number of results to skip

Response

Metrics retrieved successfully

id
string
Example:

"metric_123"

organizationId
string | null
Example:

"org_123"

userId
string | null
Example:

"user_123"

name
string
Example:

"Accuracy"

evaluationParams
string[]

Ordered list of inference-result fields the evaluator needs (e.g. input, actualOutput, expectedOutput, retrievalContext). Determines which data the evaluation engine extracts from each inference result.

Example:
["input", "actualOutput", "expectedOutput"]
source
enum<string> | null
Available options:
SELF_HOSTED,
FULL_PROMPT,
PARTIAL_PROMPT,
HUMAN_EVALUATION,
GEVAL,
DEEPEVAL,
DETERMINISTIC
Example:

"FULL_PROMPT"

judgePrompt
string | null
Example:

"Evaluate the accuracy of the response"

tags
string[]
Example:
["accuracy", "quality"]
description
string | null
Example:

"Measures the accuracy of responses"

documentationUrl
string | null
Example:

"https://docs.example.com/metrics/accuracy"

evaluatorModelName
string | null
Example:

"GPT-4"

areEvalParamsTop
boolean | null

When true, evaluationParams are injected at the top level of the evaluator prompt instead of nested inside the conversation context.

isBeingOptimized
boolean

Whether the metric is currently being optimized.

specificationIds
string[]
Example:
["spec_123"]
userGroupIds
string[]
Example:
["ug_123"]
createdAt
string<date-time>
legacyAt
string<date-time> | null
disabledAt
string<date-time> | null