insights
Creates, updates, deletes, gets or lists an insights resource.
Overview
| Name | insights |
| Type | Resource |
| Id | azure.ai_evaluation.insights |
Fields
The following fields are returned by SELECT queries:
- get_insight
- list_insights
| Name | Datatype | Description |
|---|---|---|
id | string | The unique identifier for the insights report. Required. |
displayName | string | User friendly display name for the insight. Required. |
metadata | object | Metadata about the insights report. Required. |
request | object | Request for the insights analysis. Required. |
result | object | The result of the insights report. |
state | string | The current state of the insights. Required. Known values are: "NotStarted", "Running", "Succeeded", "Failed", and "Canceled". (NotStarted, Running, Succeeded, Failed, Canceled) |
| Name | Datatype | Description |
|---|---|---|
id | string | The unique identifier for the insights report. Required. |
displayName | string | User friendly display name for the insight. Required. |
metadata | object | Metadata about the insights report. Required. |
request | object | Request for the insights analysis. Required. |
result | object | The result of the insights report. |
state | string | The current state of the insights. Required. Known values are: "NotStarted", "Running", "Succeeded", "Failed", and "Canceled". (NotStarted, Running, Succeeded, Failed, Canceled) |
Methods
The following methods are available for this resource:
| Name | Accessible by | Required Params | Optional Params | Description |
|---|---|---|---|---|
get_insight | select | id, endpoint | includeCoordinates | Get a specific insight by Id. |
list_insights | select | endpoint | type, evalId, runId, agentName, includeCoordinates | List all insights in reverse chronological order (newest first). |
generate_insights | exec | endpoint, displayName, request | Generate Insights. |
Parameters
Parameters can be passed in the WHERE clause of a query. Check the Methods section to see which parameters are required or optional for each operation.
| Name | Datatype | Description |
|---|---|---|
endpoint | string | The service endpoint host (no scheme), e.g. myaccount.table.cosmos.azure.com:443 - value of the client endpoint parameter. (default: ) |
id | string | The unique identifier for the insights report. Required. |
agentName | string | Filter by the agent name. Default value is None. |
evalId | string | Filter by the evaluation ID. Default value is None. |
includeCoordinates | boolean | Whether to include coordinates for visualization in the response. Defaults to false. Default value is None. |
runId | string | Filter by the evaluation run ID. Default value is None. |
type | string | Filter by the type of analysis. Known values are: "EvaluationRunClusterInsight", "AgentClusterInsight", and "EvaluationComparison". Default value is None. |
SELECT examples
- get_insight
- list_insights
Get a specific insight by Id.
SELECT
id,
displayName,
metadata,
request,
result,
state
FROM azure.ai_evaluation.insights
WHERE id = '{{ id }}' -- required
AND endpoint = '{{ endpoint }}' -- required
AND includeCoordinates = '{{ includeCoordinates }}'
;
List all insights in reverse chronological order (newest first).
SELECT
id,
displayName,
metadata,
request,
result,
state
FROM azure.ai_evaluation.insights
WHERE endpoint = '{{ endpoint }}' -- required
AND type = '{{ type }}'
AND evalId = '{{ evalId }}'
AND runId = '{{ runId }}'
AND agentName = '{{ agentName }}'
AND includeCoordinates = '{{ includeCoordinates }}'
;
Lifecycle Methods
- generate_insights
Generate Insights.
EXEC azure.ai_evaluation.insights.generate_insights
@endpoint='{{ endpoint }}' --required
@@json=
'{
"displayName": "{{ displayName }}",
"request": "{{ request }}"
}'
;