Skip to main content
GET
/
versions
/
{id}
/
compatible-metrics
List metrics annotated with compatibility for a version
curl --request GET \
  --url https://api.galtea.ai/versions/{id}/compatible-metrics \
  --header 'Authorization: Bearer <token>'
[
  {
    "id": "metric_123",
    "name": "Accuracy",
    "isCompatible": true,
    "source": "PARTIAL_PROMPT",
    "description": "Measures the accuracy of responses",
    "incompatibilityReason": "Missing required parameters: product_capabilities, retrieval_context"
  }
]

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-....

Path Parameters

​
id
string
required

Version ID to evaluate compatibility against

Query Parameters

​
limit
integer

Maximum number of metrics to return (default 100)

Response

List of metrics with compatibility annotations

​
id
string
required
Example:

"metric_123"

​
name
string
required
Example:

"Accuracy"

​
isCompatible
boolean
required

Whether the metric can be satisfied by the resolved product metadata and conversation endpoint connection output mapping.

​
source
enum<string> | null

Evaluation method for the metric. FULL_PROMPT is deprecated for creation — POST /metrics rejects it with a 400. Use PARTIAL_PROMPT for new AI Evaluation metrics. The value remains in the enum because existing FULL_PROMPT metrics are still returned by reads and filters.

Available options:
SELF_HOSTED,
FULL_PROMPT,
PARTIAL_PROMPT,
HUMAN_EVALUATION,
GEVAL,
DEEPEVAL,
DETERMINISTIC
Example:

"PARTIAL_PROMPT"

​
description
string | null
Example:

"Measures the accuracy of responses"

​
incompatibilityReason
string | null

Human-readable explanation of why the metric is incompatible. Non-null iff isCompatible === false.

Example:

"Missing required parameters: product_capabilities, retrieval_context"