cmind/ragmanager/v1/rag_deployment_observability_service.proto
Package: cmind.ragmanager.v1
Enums
MetricsStep
| Value | Number | Description |
|---|---|---|
METRICS_STEP_UNSPECIFIED | 0 | |
METRICS_STEP_1M | 1 | |
METRICS_STEP_5M | 2 | |
METRICS_STEP_15M | 3 | |
METRICS_STEP_30M | 4 | |
METRICS_STEP_1H | 5 | |
METRICS_STEP_2H | 6 | |
METRICS_STEP_6H | 7 | |
METRICS_STEP_12H | 8 | |
METRICS_STEP_1D | 9 |
Messages
GetRagDeploymentMetricsRequest
GetRagDeploymentMetricsRequest identifies the rag deployment by id (== the deployment's StackID). Authorization keys on id; tenant_id is carried for parity with the rest of the rag surface. start_time / end_time are unix seconds (0 == service-chosen default window), matching GetModelDeploymentMetricsRequest.
| Field | Type | Number | Description |
|---|---|---|---|
id | string | 1 | |
tenantId | string | 2 | |
startTime | uint32 | 3 | |
endTime | uint32 | 4 | |
step | MetricsStep | 5 |
GetRagDeploymentMetricsResponse
| Field | Type | Number | Description |
|---|---|---|---|
timeRange | MetricsTimeRange | 1 | |
metrics | RagDeploymentMetrics | 2 |
MetricsTimeRange
| Field | Type | Number | Description |
|---|---|---|---|
start | uint32 | 1 | |
end | uint32 | 2 | |
step | MetricsStep | 3 |
MetricPoint
| Field | Type | Number | Description |
|---|---|---|---|
timestamp | uint32 | 1 | |
value | double | 2 |
RagDeploymentMetrics
RagDeploymentMetrics parallels ModelDeploymentMetrics. total_tokens is prompt + completion only (embedding / rerank are surfaced separately), matching the legacy /timeseries contract this ports.
| Field | Type | Number | Description |
|---|---|---|---|
totalRequests | repeated MetricPoint | 1 | |
total4xxErrors | repeated MetricPoint | 2 | |
total5xxErrors | repeated MetricPoint | 3 | |
p50Latency | repeated MetricPoint | 4 | |
p90Latency | repeated MetricPoint | 5 | |
p99Latency | repeated MetricPoint | 6 | |
totalPromptTokens | repeated MetricPoint | 7 | |
totalCompletionTokens | repeated MetricPoint | 8 | |
totalEmbeddingTokens | repeated MetricPoint | 9 | |
totalTokens | repeated MetricPoint | 10 | |
totalRerankTokens | repeated MetricPoint | 11 |
Services
RagDeploymentObservabilityService
RagDeploymentObservabilityService serves the rag-deployment counterpart of ModelDeploymentObservabilityService. It mirrors that service's metric shape (request volume / errors / latency percentiles + token series) but sources the data by rag deployment id instead of model deployment name and is tenant-scoped via the per-deployment can_read gate rather than the platform-wide can_manage_models one.
GetRagDeploymentMetrics
Request: GetRagDeploymentMetricsRequest
Response: GetRagDeploymentMetricsResponse