API Reference

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Evaluation Dashboards

Create Evaluation Dashboard

client.EvaluationDashboards.New(ctx, body) (*EvaluationDashboard, error)

POST/v5/evaluation-dashboards

List Evaluation Dashboards

client.EvaluationDashboards.List(ctx, query) (*CursorPage[EvaluationDashboard], error)

GET/v5/evaluation-dashboards

Get Evaluation Dashboard

client.EvaluationDashboards.Get(ctx, dashboardID, query) (*EvaluationDashboard, error)

GET/v5/evaluation-dashboards/{dashboard_id}

Patch Evaluation Dashboard

client.EvaluationDashboards.Update(ctx, dashboardID, body) (*EvaluationDashboard, error)

PATCH/v5/evaluation-dashboards/{dashboard_id}

Delete Evaluation Dashboard

client.EvaluationDashboards.Archive(ctx, dashboardID) (*EvaluationDashboard, error)

DELETE/v5/evaluation-dashboards/{dashboard_id}

ModelsExpand Collapse

type EvaluationDashboard struct{…}

ID string

Unique identifier of the dashboard

AccountID string

Account that owns this dashboard

CreatedAt Time

When the dashboard was created

formatdate-time

CreatedBy Identity

The identity that created the entity.

ID string

Type IdentityType

One of the following:

const IdentityTypeUser IdentityType = "user"

const IdentityTypeServiceAccount IdentityType = "service_account"

Object IdentityObjectOptional

Name string

Dashboard name

Tags []string

The tags associated with the entity

UpdatedAt Time

When the dashboard was last updated

formatdate-time

ArchivedAt TimeOptional

When the dashboard was archived (soft-deleted)

formatdate-time

Description stringOptional

Dashboard description

ErrorMessage stringOptional

Error message if computation failed

EvaluationGroupID stringOptional

Evaluation group ID

EvaluationID stringOptional

Evaluation ID

Object EvaluationDashboardObjectOptional

WidgetOrder []stringOptional

Ordered array of widget IDs

WidgetResults []EvaluationDashboardWidgetResultOptional

Widget results for this dashboard. Populated with ‘widget_results’ view.

ID string

Unique identifier of the widget result

AccountID string

Account that owns this widget result

ComputationStatus EvaluationDashboardWidgetResultComputationStatus

Status of the computation

One of the following:

const EvaluationDashboardWidgetResultComputationStatusPending EvaluationDashboardWidgetResultComputationStatus = "pending"

const EvaluationDashboardWidgetResultComputationStatusCompleted EvaluationDashboardWidgetResultComputationStatus = "completed"

const EvaluationDashboardWidgetResultComputationStatusFailed EvaluationDashboardWidgetResultComputationStatus = "failed"

CreatedAt Time

When the widget result was created

formatdate-time

WidgetID string

Unique identifier of the widget

ComputationJobID stringOptional

Temporal workflow ID or job ID for async computation tracking

ComputedAt TimeOptional

Timestamp when computation completed successfully

formatdate-time

ComputedResult map[string, any]Optional

Cached computation results

ErrorMessage stringOptional

Error message if computation failed

EvaluationGroupID stringOptional

FK to evaluation_groups. Null if result is for a single evaluation.

EvaluationID stringOptional

FK to evaluations. Null if result is for an evaluation group.

Object EvaluationDashboardWidgetResultObjectOptional

Widget EvaluationDashboardWidgetOptional

Widget that this result is for

ID string

Unique identifier of the widget

AccountID string

Account that owns this widget

CreatedAt Time

When the widget was created

formatdate-time

Title string

Widget title

Type EvaluationWidgetTypeEnum

Widget type

One of the following:

const EvaluationWidgetTypeEnumBar EvaluationWidgetTypeEnum = "bar"

const EvaluationWidgetTypeEnumHistogram EvaluationWidgetTypeEnum = "histogram"

const EvaluationWidgetTypeEnumDonut EvaluationWidgetTypeEnum = "donut"

const EvaluationWidgetTypeEnumScatter EvaluationWidgetTypeEnum = "scatter"

const EvaluationWidgetTypeEnumMetric EvaluationWidgetTypeEnum = "metric"

const EvaluationWidgetTypeEnumTable EvaluationWidgetTypeEnum = "table"

const EvaluationWidgetTypeEnumMarkdown EvaluationWidgetTypeEnum = "markdown"

const EvaluationWidgetTypeEnumHeading EvaluationWidgetTypeEnum = "heading"

const EvaluationWidgetTypeEnumTimeseries EvaluationWidgetTypeEnum = "timeseries"

ArchivedAt TimeOptional

When the widget was archived (soft-deleted)

formatdate-time

Config map[string, any]Optional

Chart-specific display configuration

Object EvaluationDashboardWidgetObjectOptional

Query EvaluationDashboardWidgetQueryUnionOptional

Structured query AST for metric computation (SeriesQuery or MetricQuery)

One of the following:

type SeriesQuery struct{…}

Query that returns a series of records (used for table/bar/histogram/donut/scatter widgets).

Used for widget types: table, bar, histogram, donut, scatter. Returns: {“type”: “series”, “data”: […]}

Example SQL equivalent: SELECT category, AVG(score) as avg_score, COUNT(*) as count FROM evaluation_items WHERE score > 0.5 AND category = ‘test’ GROUP BY category ORDER BY avg_score DESC LIMIT 100

Select []SelectItem

Expression SelectItemExpressionUnion

Reference to a column from evaluation_items.data

Example: {“type”: “COLUMN”, “column”: “category”}

One of the following:

type SelectItemExpressionColumn struct{…}

Reference to a column from evaluation_items.data

Example: {“type”: “COLUMN”, “column”: “category”}

Column string

Column name from evaluation_items.data

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Type stringOptional

type SelectItemExpressionAggregation struct{…}

Aggregation function to apply

Examples: {“type”: “AGGREGATION”, “function”: “AVG”, “column”: “score”} {“type”: “AGGREGATION”, “function”: “COUNT”, “column”: ”*”} {“type”: “AGGREGATION”, “function”: “PERCENTILE”, “column”: “score”, “params”: {“percentile”: 95}}

Column string

Column to aggregate, or '' for COUNT()

Function string

Supported aggregation functions

One of the following:

const SelectItemExpressionAggregationFunctionCount SelectItemExpressionAggregationFunction = "COUNT"

const SelectItemExpressionAggregationFunctionSum SelectItemExpressionAggregationFunction = "SUM"

const SelectItemExpressionAggregationFunctionAvg SelectItemExpressionAggregationFunction = "AVG"

const SelectItemExpressionAggregationFunctionMin SelectItemExpressionAggregationFunction = "MIN"

const SelectItemExpressionAggregationFunctionMax SelectItemExpressionAggregationFunction = "MAX"

const SelectItemExpressionAggregationFunctionStddev SelectItemExpressionAggregationFunction = "STDDEV"

const SelectItemExpressionAggregationFunctionVariance SelectItemExpressionAggregationFunction = "VARIANCE"

const SelectItemExpressionAggregationFunctionPercentile SelectItemExpressionAggregationFunction = "PERCENTILE"

const SelectItemExpressionAggregationFunctionCountDistinct SelectItemExpressionAggregationFunction = "COUNT_DISTINCT"

const SelectItemExpressionAggregationFunctionPercentage SelectItemExpressionAggregationFunction = "PERCENTAGE"

EvaluationIDs []stringOptional

Optional subset of evaluation IDs for per-aggregation filtering in evaluation group dashboards.

Params map[string, any]Optional

Function parameters (e.g., {‘percentile’: 95} for PERCENTILE, {‘percentage_filters’: Filter} for PERCENTAGE)

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Type stringOptional

Alias stringOptional

Optional alias for the selected item

EvaluationIDs []stringOptional

Optional subset of evaluation IDs to compute on. Only applicable for evaluation group dashboards. If omitted, computes on all evaluations in the group.

Filter FilterOptional

Filter conditions (WHERE clause)

Conditions []FilterCondition

Column string

Column name to filter on

Operator string

Comparison operator

One of the following:

const FilterConditionOperatorEquals FilterConditionOperator = "="

const FilterConditionOperatorNotEquals FilterConditionOperator = "!="

const FilterConditionOperatorGreater FilterConditionOperator = ">"

const FilterConditionOperatorLess FilterConditionOperator = "<"

const FilterConditionOperatorGreaterOrEquals FilterConditionOperator = ">="

const FilterConditionOperatorLessOrEquals FilterConditionOperator = "<="

const FilterConditionOperatorIn FilterConditionOperator = "IN"

const FilterConditionOperatorNotIn FilterConditionOperator = "NOT IN"

const FilterConditionOperatorLike FilterConditionOperator = "LIKE"

const FilterConditionOperatorNotLike FilterConditionOperator = "NOT LIKE"

const FilterConditionOperatorIsNull FilterConditionOperator = "IS NULL"

const FilterConditionOperatorIsNotNull FilterConditionOperator = "IS NOT NULL"

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Value FilterConditionValueUnionOptional

Value to compare against. Not required for IS NULL / IS NOT NULL operators.

One of the following:

string

float64

bool

type FilterConditionValueArray []any

LogicalOperators []stringOptional

Logical operators connecting conditions. Length must be len(conditions) - 1

One of the following:

const FilterLogicalOperatorAnd FilterLogicalOperator = "AND"

const FilterLogicalOperatorOr FilterLogicalOperator = "OR"

GroupBy []stringOptional

Columns to group by

LatestOnly boolOptional

When True, the widget computes against rows from only the most recent active evaluation in the group (by EvaluationORM.created_at). Only applicable for evaluation group dashboards. Composes with evaluation_ids (latest within the subset). Cannot be combined with per-aggregation evaluation_ids; the use case enforces these rules.

Limit int64Optional

Max rows to return

minimum1

OrderBy []SeriesQueryOrderByOptional

Sort order

Column string

Column name to sort by

Direction stringOptional

Sort direction

One of the following:

const SeriesQueryOrderByDirectionAsc SeriesQueryOrderByDirection = "ASC"

const SeriesQueryOrderByDirectionDesc SeriesQueryOrderByDirection = "DESC"

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

type MetricQuery struct{…}

Query that returns a single metric value (used for metric widgets).

Used for widget type: metric. Enforces exactly 1 aggregation in select. Returns: {“type”: “metric”, “data”: …}

Example SQL equivalent: SELECT AVG(score) as average_score FROM evaluation_items

Select []SelectItem

Expression SelectItemExpressionUnion

Reference to a column from evaluation_items.data

Example: {“type”: “COLUMN”, “column”: “category”}

One of the following:

type SelectItemExpressionColumn struct{…}

Reference to a column from evaluation_items.data

Example: {“type”: “COLUMN”, “column”: “category”}

Column string

Column name from evaluation_items.data

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Type stringOptional

type SelectItemExpressionAggregation struct{…}

Aggregation function to apply

Examples: {“type”: “AGGREGATION”, “function”: “AVG”, “column”: “score”} {“type”: “AGGREGATION”, “function”: “COUNT”, “column”: ”*”} {“type”: “AGGREGATION”, “function”: “PERCENTILE”, “column”: “score”, “params”: {“percentile”: 95}}

Column string

Column to aggregate, or '' for COUNT()

Function string

Supported aggregation functions

One of the following:

const SelectItemExpressionAggregationFunctionCount SelectItemExpressionAggregationFunction = "COUNT"

const SelectItemExpressionAggregationFunctionSum SelectItemExpressionAggregationFunction = "SUM"

const SelectItemExpressionAggregationFunctionAvg SelectItemExpressionAggregationFunction = "AVG"

const SelectItemExpressionAggregationFunctionMin SelectItemExpressionAggregationFunction = "MIN"

const SelectItemExpressionAggregationFunctionMax SelectItemExpressionAggregationFunction = "MAX"

const SelectItemExpressionAggregationFunctionStddev SelectItemExpressionAggregationFunction = "STDDEV"

const SelectItemExpressionAggregationFunctionVariance SelectItemExpressionAggregationFunction = "VARIANCE"

const SelectItemExpressionAggregationFunctionPercentile SelectItemExpressionAggregationFunction = "PERCENTILE"

const SelectItemExpressionAggregationFunctionCountDistinct SelectItemExpressionAggregationFunction = "COUNT_DISTINCT"

const SelectItemExpressionAggregationFunctionPercentage SelectItemExpressionAggregationFunction = "PERCENTAGE"

EvaluationIDs []stringOptional

Optional subset of evaluation IDs for per-aggregation filtering in evaluation group dashboards.

Params map[string, any]Optional

Function parameters (e.g., {‘percentile’: 95} for PERCENTILE, {‘percentage_filters’: Filter} for PERCENTAGE)

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Type stringOptional

Alias stringOptional

Optional alias for the selected item

EvaluationIDs []stringOptional

Optional subset of evaluation IDs to compute on. Only applicable for evaluation group dashboards. If omitted, computes on all evaluations in the group.

Filter FilterOptional

Filter conditions (WHERE clause)

Conditions []FilterCondition

Column string

Column name to filter on

Operator string

Comparison operator

One of the following:

const FilterConditionOperatorEquals FilterConditionOperator = "="

const FilterConditionOperatorNotEquals FilterConditionOperator = "!="

const FilterConditionOperatorGreater FilterConditionOperator = ">"

const FilterConditionOperatorLess FilterConditionOperator = "<"

const FilterConditionOperatorGreaterOrEquals FilterConditionOperator = ">="

const FilterConditionOperatorLessOrEquals FilterConditionOperator = "<="

const FilterConditionOperatorIn FilterConditionOperator = "IN"

const FilterConditionOperatorNotIn FilterConditionOperator = "NOT IN"

const FilterConditionOperatorLike FilterConditionOperator = "LIKE"

const FilterConditionOperatorNotLike FilterConditionOperator = "NOT LIKE"

const FilterConditionOperatorIsNull FilterConditionOperator = "IS NULL"

const FilterConditionOperatorIsNotNull FilterConditionOperator = "IS NOT NULL"

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Value FilterConditionValueUnionOptional

Value to compare against. Not required for IS NULL / IS NOT NULL operators.

One of the following:

string

float64

bool

type FilterConditionValueArray []any

LogicalOperators []stringOptional

Logical operators connecting conditions. Length must be len(conditions) - 1

One of the following:

const FilterLogicalOperatorAnd FilterLogicalOperator = "AND"

const FilterLogicalOperatorOr FilterLogicalOperator = "OR"

LatestOnly boolOptional

When True, the widget computes against rows from only the most recent active evaluation in the group (by EvaluationORM.created_at). Only applicable for evaluation group dashboards. Composes with evaluation_ids (latest within the subset). Cannot be combined with per-aggregation evaluation_ids; the use case enforces these rules.

Widgets []EvaluationDashboardWidgetOptional

Widgets associated with this dashboard. Populated with ‘widgets’ view.

ID string

Unique identifier of the widget

AccountID string

Account that owns this widget

CreatedAt Time

When the widget was created

formatdate-time

Title string

Widget title

Type EvaluationWidgetTypeEnum

Widget type

One of the following:

const EvaluationWidgetTypeEnumBar EvaluationWidgetTypeEnum = "bar"

const EvaluationWidgetTypeEnumHistogram EvaluationWidgetTypeEnum = "histogram"

const EvaluationWidgetTypeEnumDonut EvaluationWidgetTypeEnum = "donut"

const EvaluationWidgetTypeEnumScatter EvaluationWidgetTypeEnum = "scatter"

const EvaluationWidgetTypeEnumMetric EvaluationWidgetTypeEnum = "metric"

const EvaluationWidgetTypeEnumTable EvaluationWidgetTypeEnum = "table"

const EvaluationWidgetTypeEnumMarkdown EvaluationWidgetTypeEnum = "markdown"

const EvaluationWidgetTypeEnumHeading EvaluationWidgetTypeEnum = "heading"

const EvaluationWidgetTypeEnumTimeseries EvaluationWidgetTypeEnum = "timeseries"

ArchivedAt TimeOptional

When the widget was archived (soft-deleted)

formatdate-time

Config map[string, any]Optional

Chart-specific display configuration

Object EvaluationDashboardWidgetObjectOptional

Query EvaluationDashboardWidgetQueryUnionOptional

Structured query AST for metric computation (SeriesQuery or MetricQuery)

One of the following:

type SeriesQuery struct{…}

Query that returns a series of records (used for table/bar/histogram/donut/scatter widgets).

Used for widget types: table, bar, histogram, donut, scatter. Returns: {“type”: “series”, “data”: […]}

Example SQL equivalent: SELECT category, AVG(score) as avg_score, COUNT(*) as count FROM evaluation_items WHERE score > 0.5 AND category = ‘test’ GROUP BY category ORDER BY avg_score DESC LIMIT 100

Select []SelectItem

Expression SelectItemExpressionUnion

Reference to a column from evaluation_items.data

Example: {“type”: “COLUMN”, “column”: “category”}

One of the following:

type SelectItemExpressionColumn struct{…}

Reference to a column from evaluation_items.data

Example: {“type”: “COLUMN”, “column”: “category”}

Column string

Column name from evaluation_items.data

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Type stringOptional

type SelectItemExpressionAggregation struct{…}

Aggregation function to apply

Examples: {“type”: “AGGREGATION”, “function”: “AVG”, “column”: “score”} {“type”: “AGGREGATION”, “function”: “COUNT”, “column”: ”*”} {“type”: “AGGREGATION”, “function”: “PERCENTILE”, “column”: “score”, “params”: {“percentile”: 95}}

Column string

Column to aggregate, or '' for COUNT()

Function string

Supported aggregation functions

One of the following:

const SelectItemExpressionAggregationFunctionCount SelectItemExpressionAggregationFunction = "COUNT"

const SelectItemExpressionAggregationFunctionSum SelectItemExpressionAggregationFunction = "SUM"

const SelectItemExpressionAggregationFunctionAvg SelectItemExpressionAggregationFunction = "AVG"

const SelectItemExpressionAggregationFunctionMin SelectItemExpressionAggregationFunction = "MIN"

const SelectItemExpressionAggregationFunctionMax SelectItemExpressionAggregationFunction = "MAX"

const SelectItemExpressionAggregationFunctionStddev SelectItemExpressionAggregationFunction = "STDDEV"

const SelectItemExpressionAggregationFunctionVariance SelectItemExpressionAggregationFunction = "VARIANCE"

const SelectItemExpressionAggregationFunctionPercentile SelectItemExpressionAggregationFunction = "PERCENTILE"

const SelectItemExpressionAggregationFunctionCountDistinct SelectItemExpressionAggregationFunction = "COUNT_DISTINCT"

const SelectItemExpressionAggregationFunctionPercentage SelectItemExpressionAggregationFunction = "PERCENTAGE"

EvaluationIDs []stringOptional

Optional subset of evaluation IDs for per-aggregation filtering in evaluation group dashboards.

Params map[string, any]Optional

Function parameters (e.g., {‘percentile’: 95} for PERCENTILE, {‘percentage_filters’: Filter} for PERCENTAGE)

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Type stringOptional

Alias stringOptional

Optional alias for the selected item

EvaluationIDs []stringOptional

Optional subset of evaluation IDs to compute on. Only applicable for evaluation group dashboards. If omitted, computes on all evaluations in the group.

Filter FilterOptional

Filter conditions (WHERE clause)

Conditions []FilterCondition

Column string

Column name to filter on

Operator string

Comparison operator

One of the following:

const FilterConditionOperatorEquals FilterConditionOperator = "="

const FilterConditionOperatorNotEquals FilterConditionOperator = "!="

const FilterConditionOperatorGreater FilterConditionOperator = ">"

const FilterConditionOperatorLess FilterConditionOperator = "<"

const FilterConditionOperatorGreaterOrEquals FilterConditionOperator = ">="

const FilterConditionOperatorLessOrEquals FilterConditionOperator = "<="

const FilterConditionOperatorIn FilterConditionOperator = "IN"

const FilterConditionOperatorNotIn FilterConditionOperator = "NOT IN"

const FilterConditionOperatorLike FilterConditionOperator = "LIKE"

const FilterConditionOperatorNotLike FilterConditionOperator = "NOT LIKE"

const FilterConditionOperatorIsNull FilterConditionOperator = "IS NULL"

const FilterConditionOperatorIsNotNull FilterConditionOperator = "IS NOT NULL"

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Value FilterConditionValueUnionOptional

Value to compare against. Not required for IS NULL / IS NOT NULL operators.

One of the following:

string

float64

bool

type FilterConditionValueArray []any

LogicalOperators []stringOptional

Logical operators connecting conditions. Length must be len(conditions) - 1

One of the following:

const FilterLogicalOperatorAnd FilterLogicalOperator = "AND"

const FilterLogicalOperatorOr FilterLogicalOperator = "OR"

GroupBy []stringOptional

Columns to group by

LatestOnly boolOptional

When True, the widget computes against rows from only the most recent active evaluation in the group (by EvaluationORM.created_at). Only applicable for evaluation group dashboards. Composes with evaluation_ids (latest within the subset). Cannot be combined with per-aggregation evaluation_ids; the use case enforces these rules.

Limit int64Optional

Max rows to return

minimum1

OrderBy []SeriesQueryOrderByOptional

Sort order

Column string

Column name to sort by

Direction stringOptional

Sort direction

One of the following:

const SeriesQueryOrderByDirectionAsc SeriesQueryOrderByDirection = "ASC"

const SeriesQueryOrderByDirectionDesc SeriesQueryOrderByDirection = "DESC"

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

type MetricQuery struct{…}

Query that returns a single metric value (used for metric widgets).

Used for widget type: metric. Enforces exactly 1 aggregation in select. Returns: {“type”: “metric”, “data”: …}

Example SQL equivalent: SELECT AVG(score) as average_score FROM evaluation_items

Select []SelectItem

Expression SelectItemExpressionUnion

Reference to a column from evaluation_items.data

Example: {“type”: “COLUMN”, “column”: “category”}

One of the following:

type SelectItemExpressionColumn struct{…}

Reference to a column from evaluation_items.data

Example: {“type”: “COLUMN”, “column”: “category”}

Column string

Column name from evaluation_items.data

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Type stringOptional

type SelectItemExpressionAggregation struct{…}

Aggregation function to apply

Examples: {“type”: “AGGREGATION”, “function”: “AVG”, “column”: “score”} {“type”: “AGGREGATION”, “function”: “COUNT”, “column”: ”*”} {“type”: “AGGREGATION”, “function”: “PERCENTILE”, “column”: “score”, “params”: {“percentile”: 95}}

Column string

Column to aggregate, or '' for COUNT()

Function string

Supported aggregation functions

One of the following:

const SelectItemExpressionAggregationFunctionCount SelectItemExpressionAggregationFunction = "COUNT"

const SelectItemExpressionAggregationFunctionSum SelectItemExpressionAggregationFunction = "SUM"

const SelectItemExpressionAggregationFunctionAvg SelectItemExpressionAggregationFunction = "AVG"

const SelectItemExpressionAggregationFunctionMin SelectItemExpressionAggregationFunction = "MIN"

const SelectItemExpressionAggregationFunctionMax SelectItemExpressionAggregationFunction = "MAX"

const SelectItemExpressionAggregationFunctionStddev SelectItemExpressionAggregationFunction = "STDDEV"

const SelectItemExpressionAggregationFunctionVariance SelectItemExpressionAggregationFunction = "VARIANCE"

const SelectItemExpressionAggregationFunctionPercentile SelectItemExpressionAggregationFunction = "PERCENTILE"

const SelectItemExpressionAggregationFunctionCountDistinct SelectItemExpressionAggregationFunction = "COUNT_DISTINCT"

const SelectItemExpressionAggregationFunctionPercentage SelectItemExpressionAggregationFunction = "PERCENTAGE"

EvaluationIDs []stringOptional

Optional subset of evaluation IDs for per-aggregation filtering in evaluation group dashboards.

Params map[string, any]Optional

Function parameters (e.g., {‘percentile’: 95} for PERCENTILE, {‘percentage_filters’: Filter} for PERCENTAGE)

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Type stringOptional

Alias stringOptional

Optional alias for the selected item

EvaluationIDs []stringOptional

Optional subset of evaluation IDs to compute on. Only applicable for evaluation group dashboards. If omitted, computes on all evaluations in the group.

Filter FilterOptional

Filter conditions (WHERE clause)

Conditions []FilterCondition

Column string

Column name to filter on

Operator string

Comparison operator

One of the following:

const FilterConditionOperatorEquals FilterConditionOperator = "="

const FilterConditionOperatorNotEquals FilterConditionOperator = "!="

const FilterConditionOperatorGreater FilterConditionOperator = ">"

const FilterConditionOperatorLess FilterConditionOperator = "<"

const FilterConditionOperatorGreaterOrEquals FilterConditionOperator = ">="

const FilterConditionOperatorLessOrEquals FilterConditionOperator = "<="

const FilterConditionOperatorIn FilterConditionOperator = "IN"

const FilterConditionOperatorNotIn FilterConditionOperator = "NOT IN"

const FilterConditionOperatorLike FilterConditionOperator = "LIKE"

const FilterConditionOperatorNotLike FilterConditionOperator = "NOT LIKE"

const FilterConditionOperatorIsNull FilterConditionOperator = "IS NULL"

const FilterConditionOperatorIsNotNull FilterConditionOperator = "IS NOT NULL"

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Value FilterConditionValueUnionOptional

Value to compare against. Not required for IS NULL / IS NOT NULL operators.

One of the following:

string

float64

bool

type FilterConditionValueArray []any

LogicalOperators []stringOptional

Logical operators connecting conditions. Length must be len(conditions) - 1

One of the following:

const FilterLogicalOperatorAnd FilterLogicalOperator = "AND"

const FilterLogicalOperatorOr FilterLogicalOperator = "OR"

LatestOnly boolOptional

When True, the widget computes against rows from only the most recent active evaluation in the group (by EvaluationORM.created_at). Only applicable for evaluation group dashboards. Composes with evaluation_ids (latest within the subset). Cannot be combined with per-aggregation evaluation_ids; the use case enforces these rules.

Evaluation DashboardsWidgets

Add Widget to Dashboard

client.EvaluationDashboards.Widgets.New(ctx, dashboardID, body) (*EvaluationDashboardWidgetWithResult, error)

POST/v5/evaluation-dashboards/{dashboard_id}/widgets

Update Dashboard Widget

client.EvaluationDashboards.Widgets.Update(ctx, widgetID, params) (*EvaluationDashboardWidgetWithResult, error)

PATCH/v5/evaluation-dashboards/{dashboard_id}/widgets/{widget_id}

Remove Widget from Dashboard

client.EvaluationDashboards.Widgets.Remove(ctx, widgetID, body) error

DELETE/v5/evaluation-dashboards/{dashboard_id}/widgets/{widget_id}

ModelsExpand Collapse

type EvaluationDashboardWidget struct{…}

ID string

Unique identifier of the widget

AccountID string

Account that owns this widget

CreatedAt Time

When the widget was created

formatdate-time

Title string

Widget title

Type EvaluationWidgetTypeEnum

Widget type

One of the following:

const EvaluationWidgetTypeEnumBar EvaluationWidgetTypeEnum = "bar"

const EvaluationWidgetTypeEnumHistogram EvaluationWidgetTypeEnum = "histogram"

const EvaluationWidgetTypeEnumDonut EvaluationWidgetTypeEnum = "donut"

const EvaluationWidgetTypeEnumScatter EvaluationWidgetTypeEnum = "scatter"

const EvaluationWidgetTypeEnumMetric EvaluationWidgetTypeEnum = "metric"

const EvaluationWidgetTypeEnumTable EvaluationWidgetTypeEnum = "table"

const EvaluationWidgetTypeEnumMarkdown EvaluationWidgetTypeEnum = "markdown"

const EvaluationWidgetTypeEnumHeading EvaluationWidgetTypeEnum = "heading"

const EvaluationWidgetTypeEnumTimeseries EvaluationWidgetTypeEnum = "timeseries"

ArchivedAt TimeOptional

When the widget was archived (soft-deleted)

formatdate-time

Config map[string, any]Optional

Chart-specific display configuration

Object EvaluationDashboardWidgetObjectOptional

Query EvaluationDashboardWidgetQueryUnionOptional

Structured query AST for metric computation (SeriesQuery or MetricQuery)

One of the following:

type SeriesQuery struct{…}

Query that returns a series of records (used for table/bar/histogram/donut/scatter widgets).

Used for widget types: table, bar, histogram, donut, scatter. Returns: {“type”: “series”, “data”: […]}

Example SQL equivalent: SELECT category, AVG(score) as avg_score, COUNT(*) as count FROM evaluation_items WHERE score > 0.5 AND category = ‘test’ GROUP BY category ORDER BY avg_score DESC LIMIT 100

Select []SelectItem

Expression SelectItemExpressionUnion

Reference to a column from evaluation_items.data

Example: {“type”: “COLUMN”, “column”: “category”}

One of the following:

type SelectItemExpressionColumn struct{…}

Reference to a column from evaluation_items.data

Example: {“type”: “COLUMN”, “column”: “category”}

Column string

Column name from evaluation_items.data

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Type stringOptional

type SelectItemExpressionAggregation struct{…}

Aggregation function to apply

Examples: {“type”: “AGGREGATION”, “function”: “AVG”, “column”: “score”} {“type”: “AGGREGATION”, “function”: “COUNT”, “column”: ”*”} {“type”: “AGGREGATION”, “function”: “PERCENTILE”, “column”: “score”, “params”: {“percentile”: 95}}

Column string

Column to aggregate, or '' for COUNT()

Function string

Supported aggregation functions

One of the following:

const SelectItemExpressionAggregationFunctionCount SelectItemExpressionAggregationFunction = "COUNT"

const SelectItemExpressionAggregationFunctionSum SelectItemExpressionAggregationFunction = "SUM"

const SelectItemExpressionAggregationFunctionAvg SelectItemExpressionAggregationFunction = "AVG"

const SelectItemExpressionAggregationFunctionMin SelectItemExpressionAggregationFunction = "MIN"

const SelectItemExpressionAggregationFunctionMax SelectItemExpressionAggregationFunction = "MAX"

const SelectItemExpressionAggregationFunctionStddev SelectItemExpressionAggregationFunction = "STDDEV"

const SelectItemExpressionAggregationFunctionVariance SelectItemExpressionAggregationFunction = "VARIANCE"

const SelectItemExpressionAggregationFunctionPercentile SelectItemExpressionAggregationFunction = "PERCENTILE"

const SelectItemExpressionAggregationFunctionCountDistinct SelectItemExpressionAggregationFunction = "COUNT_DISTINCT"

const SelectItemExpressionAggregationFunctionPercentage SelectItemExpressionAggregationFunction = "PERCENTAGE"

EvaluationIDs []stringOptional

Optional subset of evaluation IDs for per-aggregation filtering in evaluation group dashboards.

Params map[string, any]Optional

Function parameters (e.g., {‘percentile’: 95} for PERCENTILE, {‘percentage_filters’: Filter} for PERCENTAGE)

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Type stringOptional

Alias stringOptional

Optional alias for the selected item

EvaluationIDs []stringOptional

Optional subset of evaluation IDs to compute on. Only applicable for evaluation group dashboards. If omitted, computes on all evaluations in the group.

Filter FilterOptional

Filter conditions (WHERE clause)

Conditions []FilterCondition

Column string

Column name to filter on

Operator string

Comparison operator

One of the following:

const FilterConditionOperatorEquals FilterConditionOperator = "="

const FilterConditionOperatorNotEquals FilterConditionOperator = "!="

const FilterConditionOperatorGreater FilterConditionOperator = ">"

const FilterConditionOperatorLess FilterConditionOperator = "<"

const FilterConditionOperatorGreaterOrEquals FilterConditionOperator = ">="

const FilterConditionOperatorLessOrEquals FilterConditionOperator = "<="

const FilterConditionOperatorIn FilterConditionOperator = "IN"

const FilterConditionOperatorNotIn FilterConditionOperator = "NOT IN"

const FilterConditionOperatorLike FilterConditionOperator = "LIKE"

const FilterConditionOperatorNotLike FilterConditionOperator = "NOT LIKE"

const FilterConditionOperatorIsNull FilterConditionOperator = "IS NULL"

const FilterConditionOperatorIsNotNull FilterConditionOperator = "IS NOT NULL"

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Value FilterConditionValueUnionOptional

Value to compare against. Not required for IS NULL / IS NOT NULL operators.

One of the following:

string

float64

bool

type FilterConditionValueArray []any

LogicalOperators []stringOptional

Logical operators connecting conditions. Length must be len(conditions) - 1

One of the following:

const FilterLogicalOperatorAnd FilterLogicalOperator = "AND"

const FilterLogicalOperatorOr FilterLogicalOperator = "OR"

GroupBy []stringOptional

Columns to group by

LatestOnly boolOptional

When True, the widget computes against rows from only the most recent active evaluation in the group (by EvaluationORM.created_at). Only applicable for evaluation group dashboards. Composes with evaluation_ids (latest within the subset). Cannot be combined with per-aggregation evaluation_ids; the use case enforces these rules.

Limit int64Optional

Max rows to return

minimum1

OrderBy []SeriesQueryOrderByOptional

Sort order

Column string

Column name to sort by

Direction stringOptional

Sort direction

One of the following:

const SeriesQueryOrderByDirectionAsc SeriesQueryOrderByDirection = "ASC"

const SeriesQueryOrderByDirectionDesc SeriesQueryOrderByDirection = "DESC"

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

type MetricQuery struct{…}

Query that returns a single metric value (used for metric widgets).

Used for widget type: metric. Enforces exactly 1 aggregation in select. Returns: {“type”: “metric”, “data”: …}

Example SQL equivalent: SELECT AVG(score) as average_score FROM evaluation_items

Select []SelectItem

Expression SelectItemExpressionUnion

Reference to a column from evaluation_items.data

Example: {“type”: “COLUMN”, “column”: “category”}

One of the following:

type SelectItemExpressionColumn struct{…}

Reference to a column from evaluation_items.data

Example: {“type”: “COLUMN”, “column”: “category”}

Column string

Column name from evaluation_items.data

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Type stringOptional

type SelectItemExpressionAggregation struct{…}

Aggregation function to apply

Examples: {“type”: “AGGREGATION”, “function”: “AVG”, “column”: “score”} {“type”: “AGGREGATION”, “function”: “COUNT”, “column”: ”*”} {“type”: “AGGREGATION”, “function”: “PERCENTILE”, “column”: “score”, “params”: {“percentile”: 95}}

Column string

Column to aggregate, or '' for COUNT()

Function string

Supported aggregation functions

One of the following:

const SelectItemExpressionAggregationFunctionCount SelectItemExpressionAggregationFunction = "COUNT"

const SelectItemExpressionAggregationFunctionSum SelectItemExpressionAggregationFunction = "SUM"

const SelectItemExpressionAggregationFunctionAvg SelectItemExpressionAggregationFunction = "AVG"

const SelectItemExpressionAggregationFunctionMin SelectItemExpressionAggregationFunction = "MIN"

const SelectItemExpressionAggregationFunctionMax SelectItemExpressionAggregationFunction = "MAX"

const SelectItemExpressionAggregationFunctionStddev SelectItemExpressionAggregationFunction = "STDDEV"

const SelectItemExpressionAggregationFunctionVariance SelectItemExpressionAggregationFunction = "VARIANCE"

const SelectItemExpressionAggregationFunctionPercentile SelectItemExpressionAggregationFunction = "PERCENTILE"

const SelectItemExpressionAggregationFunctionCountDistinct SelectItemExpressionAggregationFunction = "COUNT_DISTINCT"

const SelectItemExpressionAggregationFunctionPercentage SelectItemExpressionAggregationFunction = "PERCENTAGE"

EvaluationIDs []stringOptional

Optional subset of evaluation IDs for per-aggregation filtering in evaluation group dashboards.

Params map[string, any]Optional

Function parameters (e.g., {‘percentile’: 95} for PERCENTILE, {‘percentage_filters’: Filter} for PERCENTAGE)

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Type stringOptional

Alias stringOptional

Optional alias for the selected item

EvaluationIDs []stringOptional

Optional subset of evaluation IDs to compute on. Only applicable for evaluation group dashboards. If omitted, computes on all evaluations in the group.

Filter FilterOptional

Filter conditions (WHERE clause)

Conditions []FilterCondition

Column string

Column name to filter on

Operator string

Comparison operator

One of the following:

const FilterConditionOperatorEquals FilterConditionOperator = "="

const FilterConditionOperatorNotEquals FilterConditionOperator = "!="

const FilterConditionOperatorGreater FilterConditionOperator = ">"

const FilterConditionOperatorLess FilterConditionOperator = "<"

const FilterConditionOperatorGreaterOrEquals FilterConditionOperator = ">="

const FilterConditionOperatorLessOrEquals FilterConditionOperator = "<="

const FilterConditionOperatorIn FilterConditionOperator = "IN"

const FilterConditionOperatorNotIn FilterConditionOperator = "NOT IN"

const FilterConditionOperatorLike FilterConditionOperator = "LIKE"

const FilterConditionOperatorNotLike FilterConditionOperator = "NOT LIKE"

const FilterConditionOperatorIsNull FilterConditionOperator = "IS NULL"

const FilterConditionOperatorIsNotNull FilterConditionOperator = "IS NOT NULL"

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Value FilterConditionValueUnionOptional

Value to compare against. Not required for IS NULL / IS NOT NULL operators.

One of the following:

string

float64

bool

type FilterConditionValueArray []any

LogicalOperators []stringOptional

Logical operators connecting conditions. Length must be len(conditions) - 1

One of the following:

const FilterLogicalOperatorAnd FilterLogicalOperator = "AND"

const FilterLogicalOperatorOr FilterLogicalOperator = "OR"

LatestOnly boolOptional

When True, the widget computes against rows from only the most recent active evaluation in the group (by EvaluationORM.created_at). Only applicable for evaluation group dashboards. Composes with evaluation_ids (latest within the subset). Cannot be combined with per-aggregation evaluation_ids; the use case enforces these rules.

type EvaluationDashboardWidgetResult struct{…}

ID string

Unique identifier of the widget result

AccountID string

Account that owns this widget result

ComputationStatus EvaluationDashboardWidgetResultComputationStatus

Status of the computation

One of the following:

const EvaluationDashboardWidgetResultComputationStatusPending EvaluationDashboardWidgetResultComputationStatus = "pending"

const EvaluationDashboardWidgetResultComputationStatusCompleted EvaluationDashboardWidgetResultComputationStatus = "completed"

const EvaluationDashboardWidgetResultComputationStatusFailed EvaluationDashboardWidgetResultComputationStatus = "failed"

CreatedAt Time

When the widget result was created

formatdate-time

WidgetID string

Unique identifier of the widget

ComputationJobID stringOptional

Temporal workflow ID or job ID for async computation tracking

ComputedAt TimeOptional

Timestamp when computation completed successfully

formatdate-time

ComputedResult map[string, any]Optional

Cached computation results

ErrorMessage stringOptional

Error message if computation failed

EvaluationGroupID stringOptional

FK to evaluation_groups. Null if result is for a single evaluation.

EvaluationID stringOptional

FK to evaluations. Null if result is for an evaluation group.

Object EvaluationDashboardWidgetResultObjectOptional

Widget EvaluationDashboardWidgetOptional

Widget that this result is for

ID string

Unique identifier of the widget

AccountID string

Account that owns this widget

CreatedAt Time

When the widget was created

formatdate-time

Title string

Widget title

Type EvaluationWidgetTypeEnum

Widget type

One of the following:

const EvaluationWidgetTypeEnumBar EvaluationWidgetTypeEnum = "bar"

const EvaluationWidgetTypeEnumHistogram EvaluationWidgetTypeEnum = "histogram"

const EvaluationWidgetTypeEnumDonut EvaluationWidgetTypeEnum = "donut"

const EvaluationWidgetTypeEnumScatter EvaluationWidgetTypeEnum = "scatter"

const EvaluationWidgetTypeEnumMetric EvaluationWidgetTypeEnum = "metric"

const EvaluationWidgetTypeEnumTable EvaluationWidgetTypeEnum = "table"

const EvaluationWidgetTypeEnumMarkdown EvaluationWidgetTypeEnum = "markdown"

const EvaluationWidgetTypeEnumHeading EvaluationWidgetTypeEnum = "heading"

const EvaluationWidgetTypeEnumTimeseries EvaluationWidgetTypeEnum = "timeseries"

ArchivedAt TimeOptional

When the widget was archived (soft-deleted)

formatdate-time

Config map[string, any]Optional

Chart-specific display configuration

Object EvaluationDashboardWidgetObjectOptional

Query EvaluationDashboardWidgetQueryUnionOptional

Structured query AST for metric computation (SeriesQuery or MetricQuery)

One of the following:

type SeriesQuery struct{…}

Query that returns a series of records (used for table/bar/histogram/donut/scatter widgets).

Used for widget types: table, bar, histogram, donut, scatter. Returns: {“type”: “series”, “data”: […]}

Example SQL equivalent: SELECT category, AVG(score) as avg_score, COUNT(*) as count FROM evaluation_items WHERE score > 0.5 AND category = ‘test’ GROUP BY category ORDER BY avg_score DESC LIMIT 100

Select []SelectItem

Expression SelectItemExpressionUnion

Reference to a column from evaluation_items.data

Example: {“type”: “COLUMN”, “column”: “category”}

One of the following:

type SelectItemExpressionColumn struct{…}

Reference to a column from evaluation_items.data

Example: {“type”: “COLUMN”, “column”: “category”}

Column string

Column name from evaluation_items.data

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Type stringOptional

type SelectItemExpressionAggregation struct{…}

Aggregation function to apply

Examples: {“type”: “AGGREGATION”, “function”: “AVG”, “column”: “score”} {“type”: “AGGREGATION”, “function”: “COUNT”, “column”: ”*”} {“type”: “AGGREGATION”, “function”: “PERCENTILE”, “column”: “score”, “params”: {“percentile”: 95}}

Column string

Column to aggregate, or '' for COUNT()

Function string

Supported aggregation functions

One of the following:

const SelectItemExpressionAggregationFunctionCount SelectItemExpressionAggregationFunction = "COUNT"

const SelectItemExpressionAggregationFunctionSum SelectItemExpressionAggregationFunction = "SUM"

const SelectItemExpressionAggregationFunctionAvg SelectItemExpressionAggregationFunction = "AVG"

const SelectItemExpressionAggregationFunctionMin SelectItemExpressionAggregationFunction = "MIN"

const SelectItemExpressionAggregationFunctionMax SelectItemExpressionAggregationFunction = "MAX"

const SelectItemExpressionAggregationFunctionStddev SelectItemExpressionAggregationFunction = "STDDEV"

const SelectItemExpressionAggregationFunctionVariance SelectItemExpressionAggregationFunction = "VARIANCE"

const SelectItemExpressionAggregationFunctionPercentile SelectItemExpressionAggregationFunction = "PERCENTILE"

const SelectItemExpressionAggregationFunctionCountDistinct SelectItemExpressionAggregationFunction = "COUNT_DISTINCT"

const SelectItemExpressionAggregationFunctionPercentage SelectItemExpressionAggregationFunction = "PERCENTAGE"

EvaluationIDs []stringOptional

Optional subset of evaluation IDs for per-aggregation filtering in evaluation group dashboards.

Params map[string, any]Optional

Function parameters (e.g., {‘percentile’: 95} for PERCENTILE, {‘percentage_filters’: Filter} for PERCENTAGE)

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Type stringOptional

Alias stringOptional

Optional alias for the selected item

EvaluationIDs []stringOptional

Optional subset of evaluation IDs to compute on. Only applicable for evaluation group dashboards. If omitted, computes on all evaluations in the group.

Filter FilterOptional

Filter conditions (WHERE clause)

Conditions []FilterCondition

Column string

Column name to filter on

Operator string

Comparison operator

One of the following:

const FilterConditionOperatorEquals FilterConditionOperator = "="

const FilterConditionOperatorNotEquals FilterConditionOperator = "!="

const FilterConditionOperatorGreater FilterConditionOperator = ">"

const FilterConditionOperatorLess FilterConditionOperator = "<"

const FilterConditionOperatorGreaterOrEquals FilterConditionOperator = ">="

const FilterConditionOperatorLessOrEquals FilterConditionOperator = "<="

const FilterConditionOperatorIn FilterConditionOperator = "IN"

const FilterConditionOperatorNotIn FilterConditionOperator = "NOT IN"

const FilterConditionOperatorLike FilterConditionOperator = "LIKE"

const FilterConditionOperatorNotLike FilterConditionOperator = "NOT LIKE"

const FilterConditionOperatorIsNull FilterConditionOperator = "IS NULL"

const FilterConditionOperatorIsNotNull FilterConditionOperator = "IS NOT NULL"

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Value FilterConditionValueUnionOptional

Value to compare against. Not required for IS NULL / IS NOT NULL operators.

One of the following:

string

float64

bool

type FilterConditionValueArray []any

LogicalOperators []stringOptional

Logical operators connecting conditions. Length must be len(conditions) - 1

One of the following:

const FilterLogicalOperatorAnd FilterLogicalOperator = "AND"

const FilterLogicalOperatorOr FilterLogicalOperator = "OR"

GroupBy []stringOptional

Columns to group by

LatestOnly boolOptional

When True, the widget computes against rows from only the most recent active evaluation in the group (by EvaluationORM.created_at). Only applicable for evaluation group dashboards. Composes with evaluation_ids (latest within the subset). Cannot be combined with per-aggregation evaluation_ids; the use case enforces these rules.

Limit int64Optional

Max rows to return

minimum1

OrderBy []SeriesQueryOrderByOptional

Sort order

Column string

Column name to sort by

Direction stringOptional

Sort direction

One of the following:

const SeriesQueryOrderByDirectionAsc SeriesQueryOrderByDirection = "ASC"

const SeriesQueryOrderByDirectionDesc SeriesQueryOrderByDirection = "DESC"

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

type MetricQuery struct{…}

Query that returns a single metric value (used for metric widgets).

Used for widget type: metric. Enforces exactly 1 aggregation in select. Returns: {“type”: “metric”, “data”: …}

Example SQL equivalent: SELECT AVG(score) as average_score FROM evaluation_items

Select []SelectItem

Expression SelectItemExpressionUnion

Reference to a column from evaluation_items.data

Example: {“type”: “COLUMN”, “column”: “category”}

One of the following:

type SelectItemExpressionColumn struct{…}

Reference to a column from evaluation_items.data

Example: {“type”: “COLUMN”, “column”: “category”}

Column string

Column name from evaluation_items.data

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Type stringOptional

type SelectItemExpressionAggregation struct{…}

Aggregation function to apply

Examples: {“type”: “AGGREGATION”, “function”: “AVG”, “column”: “score”} {“type”: “AGGREGATION”, “function”: “COUNT”, “column”: ”*”} {“type”: “AGGREGATION”, “function”: “PERCENTILE”, “column”: “score”, “params”: {“percentile”: 95}}

Column string

Column to aggregate, or '' for COUNT()

Function string

Supported aggregation functions

One of the following:

const SelectItemExpressionAggregationFunctionCount SelectItemExpressionAggregationFunction = "COUNT"

const SelectItemExpressionAggregationFunctionSum SelectItemExpressionAggregationFunction = "SUM"

const SelectItemExpressionAggregationFunctionAvg SelectItemExpressionAggregationFunction = "AVG"

const SelectItemExpressionAggregationFunctionMin SelectItemExpressionAggregationFunction = "MIN"

const SelectItemExpressionAggregationFunctionMax SelectItemExpressionAggregationFunction = "MAX"

const SelectItemExpressionAggregationFunctionStddev SelectItemExpressionAggregationFunction = "STDDEV"

const SelectItemExpressionAggregationFunctionVariance SelectItemExpressionAggregationFunction = "VARIANCE"

const SelectItemExpressionAggregationFunctionPercentile SelectItemExpressionAggregationFunction = "PERCENTILE"

const SelectItemExpressionAggregationFunctionCountDistinct SelectItemExpressionAggregationFunction = "COUNT_DISTINCT"

const SelectItemExpressionAggregationFunctionPercentage SelectItemExpressionAggregationFunction = "PERCENTAGE"

EvaluationIDs []stringOptional

Optional subset of evaluation IDs for per-aggregation filtering in evaluation group dashboards.

Params map[string, any]Optional

Function parameters (e.g., {‘percentile’: 95} for PERCENTILE, {‘percentage_filters’: Filter} for PERCENTAGE)

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Type stringOptional

Alias stringOptional

Optional alias for the selected item

EvaluationIDs []stringOptional

Optional subset of evaluation IDs to compute on. Only applicable for evaluation group dashboards. If omitted, computes on all evaluations in the group.

Filter FilterOptional

Filter conditions (WHERE clause)

Conditions []FilterCondition

Column string

Column name to filter on

Operator string

Comparison operator

One of the following:

const FilterConditionOperatorEquals FilterConditionOperator = "="

const FilterConditionOperatorNotEquals FilterConditionOperator = "!="

const FilterConditionOperatorGreater FilterConditionOperator = ">"

const FilterConditionOperatorLess FilterConditionOperator = "<"

const FilterConditionOperatorGreaterOrEquals FilterConditionOperator = ">="

const FilterConditionOperatorLessOrEquals FilterConditionOperator = "<="

const FilterConditionOperatorIn FilterConditionOperator = "IN"

const FilterConditionOperatorNotIn FilterConditionOperator = "NOT IN"

const FilterConditionOperatorLike FilterConditionOperator = "LIKE"

const FilterConditionOperatorNotLike FilterConditionOperator = "NOT LIKE"

const FilterConditionOperatorIsNull FilterConditionOperator = "IS NULL"

const FilterConditionOperatorIsNotNull FilterConditionOperator = "IS NOT NULL"

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Value FilterConditionValueUnionOptional

Value to compare against. Not required for IS NULL / IS NOT NULL operators.

One of the following:

string

float64

bool

type FilterConditionValueArray []any

LogicalOperators []stringOptional

Logical operators connecting conditions. Length must be len(conditions) - 1

One of the following:

const FilterLogicalOperatorAnd FilterLogicalOperator = "AND"

const FilterLogicalOperatorOr FilterLogicalOperator = "OR"

LatestOnly boolOptional

When True, the widget computes against rows from only the most recent active evaluation in the group (by EvaluationORM.created_at). Only applicable for evaluation group dashboards. Composes with evaluation_ids (latest within the subset). Cannot be combined with per-aggregation evaluation_ids; the use case enforces these rules.

type EvaluationDashboardWidgetResultResponse struct{…}

Computed result for a widget - used in widget creation response

ID string

Unique identifier of the widget result

ComputationStatus string

Status: pending, completed, or failed

WidgetID string

Widget ID this result belongs to

ComputedAt TimeOptional

When computation completed

formatdate-time

ComputedResult map[string, any]Optional

Computed result data. Metric: {type: ‘metric’, data: 42}, Series: {type: ‘series’, data: [{x: ‘A’, y: 10}, …]}

ErrorMessage stringOptional

Error message if computation failed

type EvaluationDashboardWidgetWithResult struct{…}

Response model for widget creation - includes widget and computed result

ID string

Unique identifier of the widget

AccountID string

Account that owns this widget

CreatedAt Time

When the widget was created

formatdate-time

Title string

Widget title

Type EvaluationWidgetTypeEnum

Widget type

One of the following:

const EvaluationWidgetTypeEnumBar EvaluationWidgetTypeEnum = "bar"

const EvaluationWidgetTypeEnumHistogram EvaluationWidgetTypeEnum = "histogram"

const EvaluationWidgetTypeEnumDonut EvaluationWidgetTypeEnum = "donut"

const EvaluationWidgetTypeEnumScatter EvaluationWidgetTypeEnum = "scatter"

const EvaluationWidgetTypeEnumMetric EvaluationWidgetTypeEnum = "metric"

const EvaluationWidgetTypeEnumTable EvaluationWidgetTypeEnum = "table"

const EvaluationWidgetTypeEnumMarkdown EvaluationWidgetTypeEnum = "markdown"

const EvaluationWidgetTypeEnumHeading EvaluationWidgetTypeEnum = "heading"

const EvaluationWidgetTypeEnumTimeseries EvaluationWidgetTypeEnum = "timeseries"

Config map[string, any]Optional

Display configuration

Object EvaluationDashboardWidgetWithResultObjectOptional

Query EvaluationDashboardWidgetWithResultQueryUnionOptional

Structured query AST for computation (SeriesQuery or MetricQuery)

One of the following:

type SeriesQuery struct{…}

Query that returns a series of records (used for table/bar/histogram/donut/scatter widgets).

Used for widget types: table, bar, histogram, donut, scatter. Returns: {“type”: “series”, “data”: […]}

Example SQL equivalent: SELECT category, AVG(score) as avg_score, COUNT(*) as count FROM evaluation_items WHERE score > 0.5 AND category = ‘test’ GROUP BY category ORDER BY avg_score DESC LIMIT 100

Select []SelectItem

Expression SelectItemExpressionUnion

Reference to a column from evaluation_items.data

Example: {“type”: “COLUMN”, “column”: “category”}

One of the following:

type SelectItemExpressionColumn struct{…}

Reference to a column from evaluation_items.data

Example: {“type”: “COLUMN”, “column”: “category”}

Column string

Column name from evaluation_items.data

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Type stringOptional

type SelectItemExpressionAggregation struct{…}

Aggregation function to apply

Examples: {“type”: “AGGREGATION”, “function”: “AVG”, “column”: “score”} {“type”: “AGGREGATION”, “function”: “COUNT”, “column”: ”*”} {“type”: “AGGREGATION”, “function”: “PERCENTILE”, “column”: “score”, “params”: {“percentile”: 95}}

Column string

Column to aggregate, or '' for COUNT()

Function string

Supported aggregation functions

One of the following:

const SelectItemExpressionAggregationFunctionCount SelectItemExpressionAggregationFunction = "COUNT"

const SelectItemExpressionAggregationFunctionSum SelectItemExpressionAggregationFunction = "SUM"

const SelectItemExpressionAggregationFunctionAvg SelectItemExpressionAggregationFunction = "AVG"

const SelectItemExpressionAggregationFunctionMin SelectItemExpressionAggregationFunction = "MIN"

const SelectItemExpressionAggregationFunctionMax SelectItemExpressionAggregationFunction = "MAX"

const SelectItemExpressionAggregationFunctionStddev SelectItemExpressionAggregationFunction = "STDDEV"

const SelectItemExpressionAggregationFunctionVariance SelectItemExpressionAggregationFunction = "VARIANCE"

const SelectItemExpressionAggregationFunctionPercentile SelectItemExpressionAggregationFunction = "PERCENTILE"

const SelectItemExpressionAggregationFunctionCountDistinct SelectItemExpressionAggregationFunction = "COUNT_DISTINCT"

const SelectItemExpressionAggregationFunctionPercentage SelectItemExpressionAggregationFunction = "PERCENTAGE"

EvaluationIDs []stringOptional

Optional subset of evaluation IDs for per-aggregation filtering in evaluation group dashboards.

Params map[string, any]Optional

Function parameters (e.g., {‘percentile’: 95} for PERCENTILE, {‘percentage_filters’: Filter} for PERCENTAGE)

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Type stringOptional

Alias stringOptional

Optional alias for the selected item

EvaluationIDs []stringOptional

Optional subset of evaluation IDs to compute on. Only applicable for evaluation group dashboards. If omitted, computes on all evaluations in the group.

Filter FilterOptional

Filter conditions (WHERE clause)

Conditions []FilterCondition

Column string

Column name to filter on

Operator string

Comparison operator

One of the following:

const FilterConditionOperatorEquals FilterConditionOperator = "="

const FilterConditionOperatorNotEquals FilterConditionOperator = "!="

const FilterConditionOperatorGreater FilterConditionOperator = ">"

const FilterConditionOperatorLess FilterConditionOperator = "<"

const FilterConditionOperatorGreaterOrEquals FilterConditionOperator = ">="

const FilterConditionOperatorLessOrEquals FilterConditionOperator = "<="

const FilterConditionOperatorIn FilterConditionOperator = "IN"

const FilterConditionOperatorNotIn FilterConditionOperator = "NOT IN"

const FilterConditionOperatorLike FilterConditionOperator = "LIKE"

const FilterConditionOperatorNotLike FilterConditionOperator = "NOT LIKE"

const FilterConditionOperatorIsNull FilterConditionOperator = "IS NULL"

const FilterConditionOperatorIsNotNull FilterConditionOperator = "IS NOT NULL"

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Value FilterConditionValueUnionOptional

Value to compare against. Not required for IS NULL / IS NOT NULL operators.

One of the following:

string

float64

bool

type FilterConditionValueArray []any

LogicalOperators []stringOptional

Logical operators connecting conditions. Length must be len(conditions) - 1

One of the following:

const FilterLogicalOperatorAnd FilterLogicalOperator = "AND"

const FilterLogicalOperatorOr FilterLogicalOperator = "OR"

GroupBy []stringOptional

Columns to group by

LatestOnly boolOptional

When True, the widget computes against rows from only the most recent active evaluation in the group (by EvaluationORM.created_at). Only applicable for evaluation group dashboards. Composes with evaluation_ids (latest within the subset). Cannot be combined with per-aggregation evaluation_ids; the use case enforces these rules.

Limit int64Optional

Max rows to return

minimum1

OrderBy []SeriesQueryOrderByOptional

Sort order

Column string

Column name to sort by

Direction stringOptional

Sort direction

One of the following:

const SeriesQueryOrderByDirectionAsc SeriesQueryOrderByDirection = "ASC"

const SeriesQueryOrderByDirectionDesc SeriesQueryOrderByDirection = "DESC"

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

type MetricQuery struct{…}

Query that returns a single metric value (used for metric widgets).

Used for widget type: metric. Enforces exactly 1 aggregation in select. Returns: {“type”: “metric”, “data”: …}

Example SQL equivalent: SELECT AVG(score) as average_score FROM evaluation_items

Select []SelectItem

Expression SelectItemExpressionUnion

Reference to a column from evaluation_items.data

Example: {“type”: “COLUMN”, “column”: “category”}

One of the following:

type SelectItemExpressionColumn struct{…}

Reference to a column from evaluation_items.data

Example: {“type”: “COLUMN”, “column”: “category”}

Column string

Column name from evaluation_items.data

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Type stringOptional

type SelectItemExpressionAggregation struct{…}

Aggregation function to apply

Examples: {“type”: “AGGREGATION”, “function”: “AVG”, “column”: “score”} {“type”: “AGGREGATION”, “function”: “COUNT”, “column”: ”*”} {“type”: “AGGREGATION”, “function”: “PERCENTILE”, “column”: “score”, “params”: {“percentile”: 95}}

Column string

Column to aggregate, or '' for COUNT()

Function string

Supported aggregation functions

One of the following:

const SelectItemExpressionAggregationFunctionCount SelectItemExpressionAggregationFunction = "COUNT"

const SelectItemExpressionAggregationFunctionSum SelectItemExpressionAggregationFunction = "SUM"

const SelectItemExpressionAggregationFunctionAvg SelectItemExpressionAggregationFunction = "AVG"

const SelectItemExpressionAggregationFunctionMin SelectItemExpressionAggregationFunction = "MIN"

const SelectItemExpressionAggregationFunctionMax SelectItemExpressionAggregationFunction = "MAX"

const SelectItemExpressionAggregationFunctionStddev SelectItemExpressionAggregationFunction = "STDDEV"

const SelectItemExpressionAggregationFunctionVariance SelectItemExpressionAggregationFunction = "VARIANCE"

const SelectItemExpressionAggregationFunctionPercentile SelectItemExpressionAggregationFunction = "PERCENTILE"

const SelectItemExpressionAggregationFunctionCountDistinct SelectItemExpressionAggregationFunction = "COUNT_DISTINCT"

const SelectItemExpressionAggregationFunctionPercentage SelectItemExpressionAggregationFunction = "PERCENTAGE"

EvaluationIDs []stringOptional

Optional subset of evaluation IDs for per-aggregation filtering in evaluation group dashboards.

Params map[string, any]Optional

Function parameters (e.g., {‘percentile’: 95} for PERCENTILE, {‘percentage_filters’: Filter} for PERCENTAGE)

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Type stringOptional

Alias stringOptional

Optional alias for the selected item

EvaluationIDs []stringOptional

Optional subset of evaluation IDs to compute on. Only applicable for evaluation group dashboards. If omitted, computes on all evaluations in the group.

Filter FilterOptional

Filter conditions (WHERE clause)

Conditions []FilterCondition

Column string

Column name to filter on

Operator string

Comparison operator

One of the following:

const FilterConditionOperatorEquals FilterConditionOperator = "="

const FilterConditionOperatorNotEquals FilterConditionOperator = "!="

const FilterConditionOperatorGreater FilterConditionOperator = ">"

const FilterConditionOperatorLess FilterConditionOperator = "<"

const FilterConditionOperatorGreaterOrEquals FilterConditionOperator = ">="

const FilterConditionOperatorLessOrEquals FilterConditionOperator = "<="

const FilterConditionOperatorIn FilterConditionOperator = "IN"

const FilterConditionOperatorNotIn FilterConditionOperator = "NOT IN"

const FilterConditionOperatorLike FilterConditionOperator = "LIKE"

const FilterConditionOperatorNotLike FilterConditionOperator = "NOT LIKE"

const FilterConditionOperatorIsNull FilterConditionOperator = "IS NULL"

const FilterConditionOperatorIsNotNull FilterConditionOperator = "IS NOT NULL"

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Value FilterConditionValueUnionOptional

Value to compare against. Not required for IS NULL / IS NOT NULL operators.

One of the following:

string

float64

bool

type FilterConditionValueArray []any

LogicalOperators []stringOptional

Logical operators connecting conditions. Length must be len(conditions) - 1

One of the following:

const FilterLogicalOperatorAnd FilterLogicalOperator = "AND"

const FilterLogicalOperatorOr FilterLogicalOperator = "OR"

LatestOnly boolOptional

When True, the widget computes against rows from only the most recent active evaluation in the group (by EvaluationORM.created_at). Only applicable for evaluation group dashboards. Composes with evaluation_ids (latest within the subset). Cannot be combined with per-aggregation evaluation_ids; the use case enforces these rules.

Result EvaluationDashboardWidgetResultResponseOptional

Computed result for this widget

ID string

Unique identifier of the widget result

ComputationStatus string

Status: pending, completed, or failed

WidgetID string

Widget ID this result belongs to

ComputedAt TimeOptional

When computation completed

formatdate-time

ComputedResult map[string, any]Optional

Computed result data. Metric: {type: ‘metric’, data: 42}, Series: {type: ‘series’, data: [{x: ‘A’, y: 10}, …]}

ErrorMessage stringOptional

Error message if computation failed

type EvaluationWidgetTypeEnum string

Widget types for dashboard visualizations

One of the following:

const EvaluationWidgetTypeEnumBar EvaluationWidgetTypeEnum = "bar"

const EvaluationWidgetTypeEnumHistogram EvaluationWidgetTypeEnum = "histogram"

const EvaluationWidgetTypeEnumDonut EvaluationWidgetTypeEnum = "donut"

const EvaluationWidgetTypeEnumScatter EvaluationWidgetTypeEnum = "scatter"

const EvaluationWidgetTypeEnumMetric EvaluationWidgetTypeEnum = "metric"

const EvaluationWidgetTypeEnumTable EvaluationWidgetTypeEnum = "table"

const EvaluationWidgetTypeEnumMarkdown EvaluationWidgetTypeEnum = "markdown"

const EvaluationWidgetTypeEnumHeading EvaluationWidgetTypeEnum = "heading"

const EvaluationWidgetTypeEnumTimeseries EvaluationWidgetTypeEnum = "timeseries"

type Filter struct{…}

Filter clause with conditions connected by logical operators.

Conditions are evaluated left-to-right without precedence (no nesting/parentheses). Example: condition1 AND condition2 OR condition3 evaluates as ((condition1 AND condition2) OR condition3)

Example: { “conditions”: [ {“column”: “score”, “operator”: ”>”, “value”: 0.5}, {“column”: “category”, “operator”: ”=”, “value”: “test”} ], “logicalOperators”: [“AND”] }

Conditions []FilterCondition

Column string

Column name to filter on

Operator string

Comparison operator

One of the following:

const FilterConditionOperatorEquals FilterConditionOperator = "="

const FilterConditionOperatorNotEquals FilterConditionOperator = "!="

const FilterConditionOperatorGreater FilterConditionOperator = ">"

const FilterConditionOperatorLess FilterConditionOperator = "<"

const FilterConditionOperatorGreaterOrEquals FilterConditionOperator = ">="

const FilterConditionOperatorLessOrEquals FilterConditionOperator = "<="

const FilterConditionOperatorIn FilterConditionOperator = "IN"

const FilterConditionOperatorNotIn FilterConditionOperator = "NOT IN"

const FilterConditionOperatorLike FilterConditionOperator = "LIKE"

const FilterConditionOperatorNotLike FilterConditionOperator = "NOT LIKE"

const FilterConditionOperatorIsNull FilterConditionOperator = "IS NULL"

const FilterConditionOperatorIsNotNull FilterConditionOperator = "IS NOT NULL"

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Value FilterConditionValueUnionOptional

Value to compare against. Not required for IS NULL / IS NOT NULL operators.

One of the following:

string

float64

bool

type FilterConditionValueArray []any

LogicalOperators []stringOptional

Logical operators connecting conditions. Length must be len(conditions) - 1

One of the following:

const FilterLogicalOperatorAnd FilterLogicalOperator = "AND"

const FilterLogicalOperatorOr FilterLogicalOperator = "OR"

type MetricQuery struct{…}

Query that returns a single metric value (used for metric widgets).

Used for widget type: metric. Enforces exactly 1 aggregation in select. Returns: {“type”: “metric”, “data”: …}

Example SQL equivalent: SELECT AVG(score) as average_score FROM evaluation_items

Select []SelectItem

Expression SelectItemExpressionUnion

Reference to a column from evaluation_items.data

Example: {“type”: “COLUMN”, “column”: “category”}

One of the following:

type SelectItemExpressionColumn struct{…}

Reference to a column from evaluation_items.data

Example: {“type”: “COLUMN”, “column”: “category”}

Column string

Column name from evaluation_items.data

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Type stringOptional

type SelectItemExpressionAggregation struct{…}

Aggregation function to apply

Examples: {“type”: “AGGREGATION”, “function”: “AVG”, “column”: “score”} {“type”: “AGGREGATION”, “function”: “COUNT”, “column”: ”*”} {“type”: “AGGREGATION”, “function”: “PERCENTILE”, “column”: “score”, “params”: {“percentile”: 95}}

Column string

Column to aggregate, or '' for COUNT()

Function string

Supported aggregation functions

One of the following:

const SelectItemExpressionAggregationFunctionCount SelectItemExpressionAggregationFunction = "COUNT"

const SelectItemExpressionAggregationFunctionSum SelectItemExpressionAggregationFunction = "SUM"

const SelectItemExpressionAggregationFunctionAvg SelectItemExpressionAggregationFunction = "AVG"

const SelectItemExpressionAggregationFunctionMin SelectItemExpressionAggregationFunction = "MIN"

const SelectItemExpressionAggregationFunctionMax SelectItemExpressionAggregationFunction = "MAX"

const SelectItemExpressionAggregationFunctionStddev SelectItemExpressionAggregationFunction = "STDDEV"

const SelectItemExpressionAggregationFunctionVariance SelectItemExpressionAggregationFunction = "VARIANCE"

const SelectItemExpressionAggregationFunctionPercentile SelectItemExpressionAggregationFunction = "PERCENTILE"

const SelectItemExpressionAggregationFunctionCountDistinct SelectItemExpressionAggregationFunction = "COUNT_DISTINCT"

const SelectItemExpressionAggregationFunctionPercentage SelectItemExpressionAggregationFunction = "PERCENTAGE"

EvaluationIDs []stringOptional

Optional subset of evaluation IDs for per-aggregation filtering in evaluation group dashboards.

Params map[string, any]Optional

Function parameters (e.g., {‘percentile’: 95} for PERCENTILE, {‘percentage_filters’: Filter} for PERCENTAGE)

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Type stringOptional

Alias stringOptional

Optional alias for the selected item

EvaluationIDs []stringOptional

Optional subset of evaluation IDs to compute on. Only applicable for evaluation group dashboards. If omitted, computes on all evaluations in the group.

Filter FilterOptional

Filter conditions (WHERE clause)

Conditions []FilterCondition

Column string

Column name to filter on

Operator string

Comparison operator

One of the following:

const FilterConditionOperatorEquals FilterConditionOperator = "="

const FilterConditionOperatorNotEquals FilterConditionOperator = "!="

const FilterConditionOperatorGreater FilterConditionOperator = ">"

const FilterConditionOperatorLess FilterConditionOperator = "<"

const FilterConditionOperatorGreaterOrEquals FilterConditionOperator = ">="

const FilterConditionOperatorLessOrEquals FilterConditionOperator = "<="

const FilterConditionOperatorIn FilterConditionOperator = "IN"

const FilterConditionOperatorNotIn FilterConditionOperator = "NOT IN"

const FilterConditionOperatorLike FilterConditionOperator = "LIKE"

const FilterConditionOperatorNotLike FilterConditionOperator = "NOT LIKE"

const FilterConditionOperatorIsNull FilterConditionOperator = "IS NULL"

const FilterConditionOperatorIsNotNull FilterConditionOperator = "IS NOT NULL"

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Value FilterConditionValueUnionOptional

Value to compare against. Not required for IS NULL / IS NOT NULL operators.

One of the following:

string

float64

bool

type FilterConditionValueArray []any

LogicalOperators []stringOptional

Logical operators connecting conditions. Length must be len(conditions) - 1

One of the following:

const FilterLogicalOperatorAnd FilterLogicalOperator = "AND"

const FilterLogicalOperatorOr FilterLogicalOperator = "OR"

LatestOnly boolOptional

When True, the widget computes against rows from only the most recent active evaluation in the group (by EvaluationORM.created_at). Only applicable for evaluation group dashboards. Composes with evaluation_ids (latest within the subset). Cannot be combined with per-aggregation evaluation_ids; the use case enforces these rules.

type SelectItem struct{…}

Column in SELECT clause

Expression SelectItemExpressionUnion

Reference to a column from evaluation_items.data

Example: {“type”: “COLUMN”, “column”: “category”}

One of the following:

type SelectItemExpressionColumn struct{…}

Reference to a column from evaluation_items.data

Example: {“type”: “COLUMN”, “column”: “category”}

Column string

Column name from evaluation_items.data

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Type stringOptional

type SelectItemExpressionAggregation struct{…}

Aggregation function to apply

Examples: {“type”: “AGGREGATION”, “function”: “AVG”, “column”: “score”} {“type”: “AGGREGATION”, “function”: “COUNT”, “column”: ”*”} {“type”: “AGGREGATION”, “function”: “PERCENTILE”, “column”: “score”, “params”: {“percentile”: 95}}

Column string

Column to aggregate, or '' for COUNT()

Function string

Supported aggregation functions

One of the following:

const SelectItemExpressionAggregationFunctionCount SelectItemExpressionAggregationFunction = "COUNT"

const SelectItemExpressionAggregationFunctionSum SelectItemExpressionAggregationFunction = "SUM"

const SelectItemExpressionAggregationFunctionAvg SelectItemExpressionAggregationFunction = "AVG"

const SelectItemExpressionAggregationFunctionMin SelectItemExpressionAggregationFunction = "MIN"

const SelectItemExpressionAggregationFunctionMax SelectItemExpressionAggregationFunction = "MAX"

const SelectItemExpressionAggregationFunctionStddev SelectItemExpressionAggregationFunction = "STDDEV"

const SelectItemExpressionAggregationFunctionVariance SelectItemExpressionAggregationFunction = "VARIANCE"

const SelectItemExpressionAggregationFunctionPercentile SelectItemExpressionAggregationFunction = "PERCENTILE"

const SelectItemExpressionAggregationFunctionCountDistinct SelectItemExpressionAggregationFunction = "COUNT_DISTINCT"

const SelectItemExpressionAggregationFunctionPercentage SelectItemExpressionAggregationFunction = "PERCENTAGE"

EvaluationIDs []stringOptional

Optional subset of evaluation IDs for per-aggregation filtering in evaluation group dashboards.

Params map[string, any]Optional

Function parameters (e.g., {‘percentile’: 95} for PERCENTILE, {‘percentage_filters’: Filter} for PERCENTAGE)

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Type stringOptional

Alias stringOptional

Optional alias for the selected item

type SeriesQuery struct{…}

Query that returns a series of records (used for table/bar/histogram/donut/scatter widgets).

Used for widget types: table, bar, histogram, donut, scatter. Returns: {“type”: “series”, “data”: […]}

Example SQL equivalent: SELECT category, AVG(score) as avg_score, COUNT(*) as count FROM evaluation_items WHERE score > 0.5 AND category = ‘test’ GROUP BY category ORDER BY avg_score DESC LIMIT 100

Select []SelectItem

Expression SelectItemExpressionUnion

Reference to a column from evaluation_items.data

Example: {“type”: “COLUMN”, “column”: “category”}

One of the following:

type SelectItemExpressionColumn struct{…}

Reference to a column from evaluation_items.data

Example: {“type”: “COLUMN”, “column”: “category”}

Column string

Column name from evaluation_items.data

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Type stringOptional

type SelectItemExpressionAggregation struct{…}

Aggregation function to apply

Examples: {“type”: “AGGREGATION”, “function”: “AVG”, “column”: “score”} {“type”: “AGGREGATION”, “function”: “COUNT”, “column”: ”*”} {“type”: “AGGREGATION”, “function”: “PERCENTILE”, “column”: “score”, “params”: {“percentile”: 95}}

Column string

Column to aggregate, or '' for COUNT()

Function string

Supported aggregation functions

One of the following:

const SelectItemExpressionAggregationFunctionCount SelectItemExpressionAggregationFunction = "COUNT"

const SelectItemExpressionAggregationFunctionSum SelectItemExpressionAggregationFunction = "SUM"

const SelectItemExpressionAggregationFunctionAvg SelectItemExpressionAggregationFunction = "AVG"

const SelectItemExpressionAggregationFunctionMin SelectItemExpressionAggregationFunction = "MIN"

const SelectItemExpressionAggregationFunctionMax SelectItemExpressionAggregationFunction = "MAX"

const SelectItemExpressionAggregationFunctionStddev SelectItemExpressionAggregationFunction = "STDDEV"

const SelectItemExpressionAggregationFunctionVariance SelectItemExpressionAggregationFunction = "VARIANCE"

const SelectItemExpressionAggregationFunctionPercentile SelectItemExpressionAggregationFunction = "PERCENTILE"

const SelectItemExpressionAggregationFunctionCountDistinct SelectItemExpressionAggregationFunction = "COUNT_DISTINCT"

const SelectItemExpressionAggregationFunctionPercentage SelectItemExpressionAggregationFunction = "PERCENTAGE"

EvaluationIDs []stringOptional

Optional subset of evaluation IDs for per-aggregation filtering in evaluation group dashboards.

Params map[string, any]Optional

Function parameters (e.g., {‘percentile’: 95} for PERCENTILE, {‘percentage_filters’: Filter} for PERCENTAGE)

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Type stringOptional

Alias stringOptional

Optional alias for the selected item

EvaluationIDs []stringOptional

Optional subset of evaluation IDs to compute on. Only applicable for evaluation group dashboards. If omitted, computes on all evaluations in the group.

Filter FilterOptional

Filter conditions (WHERE clause)

Conditions []FilterCondition

Column string

Column name to filter on

Operator string

Comparison operator

One of the following:

const FilterConditionOperatorEquals FilterConditionOperator = "="

const FilterConditionOperatorNotEquals FilterConditionOperator = "!="

const FilterConditionOperatorGreater FilterConditionOperator = ">"

const FilterConditionOperatorLess FilterConditionOperator = "<"

const FilterConditionOperatorGreaterOrEquals FilterConditionOperator = ">="

const FilterConditionOperatorLessOrEquals FilterConditionOperator = "<="

const FilterConditionOperatorIn FilterConditionOperator = "IN"

const FilterConditionOperatorNotIn FilterConditionOperator = "NOT IN"

const FilterConditionOperatorLike FilterConditionOperator = "LIKE"

const FilterConditionOperatorNotLike FilterConditionOperator = "NOT LIKE"

const FilterConditionOperatorIsNull FilterConditionOperator = "IS NULL"

const FilterConditionOperatorIsNotNull FilterConditionOperator = "IS NOT NULL"

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’

Value FilterConditionValueUnionOptional

Value to compare against. Not required for IS NULL / IS NOT NULL operators.

One of the following:

string

float64

bool

type FilterConditionValueArray []any

LogicalOperators []stringOptional

Logical operators connecting conditions. Length must be len(conditions) - 1

One of the following:

const FilterLogicalOperatorAnd FilterLogicalOperator = "AND"

const FilterLogicalOperatorOr FilterLogicalOperator = "OR"

GroupBy []stringOptional

Columns to group by

LatestOnly boolOptional

When True, the widget computes against rows from only the most recent active evaluation in the group (by EvaluationORM.created_at). Only applicable for evaluation group dashboards. Composes with evaluation_ids (latest within the subset). Cannot be combined with per-aggregation evaluation_ids; the use case enforces these rules.

Limit int64Optional

Max rows to return

minimum1

OrderBy []SeriesQueryOrderByOptional

Sort order

Column string

Column name to sort by

Direction stringOptional

Sort direction

One of the following:

const SeriesQueryOrderByDirectionAsc SeriesQueryOrderByDirection = "ASC"

const SeriesQueryOrderByDirectionDesc SeriesQueryOrderByDirection = "DESC"

Source stringOptional

Column source: ‘data’ or ‘task_result_cache’