feat(api): some updates to query metrics

Author: stainless-app[bot]

.stats.yml

@@ -1,4 +1,4 @@
-configured_endpoints: 106
+configured_endpoints: 107
 openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/llamastack%2Fllama-stack-client-f252873ea1e1f38fd207331ef2621c511154d5be3f4076e59cc15754fc58eee4.yml
 openapi_spec_hash: 10cbb4337a06a9fdd7d08612dd6044c3
-config_hash: ddcbd66d7ac80290da208232a746e30f
+config_hash: 17fe64b23723fc54f2ee61c80223c3e3

api.md

@@ -509,12 +509,14 @@ Types:
 ```python
 from llama_stack_client.types import (
     Event,
+    Metric,
     QueryCondition,
     QuerySpansResponse,
     SpanWithStatus,
     Trace,
     TelemetryGetSpanResponse,
     TelemetryGetSpanTreeResponse,
+    TelemetryQueryMetricsResponse,
     TelemetryQuerySpansResponse,
     TelemetryQueryTracesResponse,
 )
@@ -526,6 +528,7 @@ Methods:
 - <code title="post /v1/telemetry/spans/{span_id}/tree">client.telemetry.<a href="./src/llama_stack_client/resources/telemetry.py">get_span_tree</a>(span_id, \*\*<a href="src/llama_stack_client/types/telemetry_get_span_tree_params.py">params</a>) -> <a href="./src/llama_stack_client/types/telemetry_get_span_tree_response.py">TelemetryGetSpanTreeResponse</a></code>
 - <code title="get /v1/telemetry/traces/{trace_id}">client.telemetry.<a href="./src/llama_stack_client/resources/telemetry.py">get_trace</a>(trace_id) -> <a href="./src/llama_stack_client/types/trace.py">Trace</a></code>
 - <code title="post /v1/telemetry/events">client.telemetry.<a href="./src/llama_stack_client/resources/telemetry.py">log_event</a>(\*\*<a href="src/llama_stack_client/types/telemetry_log_event_params.py">params</a>) -> None</code>
+- <code title="post /v1/telemetry/metrics/{metric_name}">client.telemetry.<a href="./src/llama_stack_client/resources/telemetry.py">query_metrics</a>(metric_name, \*\*<a href="src/llama_stack_client/types/telemetry_query_metrics_params.py">params</a>) -> <a href="./src/llama_stack_client/types/telemetry_query_metrics_response.py">TelemetryQueryMetricsResponse</a></code>
 - <code title="post /v1/telemetry/spans">client.telemetry.<a href="./src/llama_stack_client/resources/telemetry.py">query_spans</a>(\*\*<a href="src/llama_stack_client/types/telemetry_query_spans_params.py">params</a>) -> <a href="./src/llama_stack_client/types/telemetry_query_spans_response.py">TelemetryQuerySpansResponse</a></code>
 - <code title="post /v1/telemetry/traces">client.telemetry.<a href="./src/llama_stack_client/resources/telemetry.py">query_traces</a>(\*\*<a href="src/llama_stack_client/types/telemetry_query_traces_params.py">params</a>) -> <a href="./src/llama_stack_client/types/telemetry_query_traces_response.py">TelemetryQueryTracesResponse</a></code>
 - <code title="post /v1/telemetry/spans/export">client.telemetry.<a href="./src/llama_stack_client/resources/telemetry.py">save_spans_to_dataset</a>(\*\*<a href="src/llama_stack_client/types/telemetry_save_spans_to_dataset_params.py">params</a>) -> None</code>

src/llama_stack_client/resources/telemetry.py

@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 from typing import List, Type, Iterable, cast
+from typing_extensions import Literal
 
 import httpx
 
@@ -11,6 +12,7 @@
     telemetry_query_spans_params,
     telemetry_query_traces_params,
     telemetry_get_span_tree_params,
+    telemetry_query_metrics_params,
     telemetry_save_spans_to_dataset_params,
 )
 from .._types import NOT_GIVEN, Body, Query, Headers, NoneType, NotGiven
@@ -32,6 +34,7 @@
 from ..types.telemetry_query_spans_response import TelemetryQuerySpansResponse
 from ..types.telemetry_query_traces_response import TelemetryQueryTracesResponse
 from ..types.telemetry_get_span_tree_response import TelemetryGetSpanTreeResponse
+from ..types.telemetry_query_metrics_response import TelemetryQueryMetricsResponse
 
 __all__ = ["TelemetryResource", "AsyncTelemetryResource"]
 
@@ -219,6 +222,68 @@ def log_event(
             cast_to=NoneType,
         )
 
+    def query_metrics(
+        self,
+        metric_name: str,
+        *,
+        query_type: Literal["range", "instant"],
+        start_time: int,
+        end_time: int | NotGiven = NOT_GIVEN,
+        granularity: str | NotGiven = NOT_GIVEN,
+        label_matchers: Iterable[telemetry_query_metrics_params.LabelMatcher] | NotGiven = NOT_GIVEN,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> TelemetryQueryMetricsResponse:
+        """
+        Query metrics.
+
+        Args:
+          query_type: The type of query to perform.
+
+          start_time: The start time of the metric to query.
+
+          end_time: The end time of the metric to query.
+
+          granularity: The granularity of the metric to query.
+
+          label_matchers: The label matchers to apply to the metric.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not metric_name:
+            raise ValueError(f"Expected a non-empty value for `metric_name` but received {metric_name!r}")
+        return self._post(
+            f"/v1/telemetry/metrics/{metric_name}",
+            body=maybe_transform(
+                {
+                    "query_type": query_type,
+                    "start_time": start_time,
+                    "end_time": end_time,
+                    "granularity": granularity,
+                    "label_matchers": label_matchers,
+                },
+                telemetry_query_metrics_params.TelemetryQueryMetricsParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers,
+                extra_query=extra_query,
+                extra_body=extra_body,
+                timeout=timeout,
+                post_parser=DataWrapper[TelemetryQueryMetricsResponse]._unwrapper,
+            ),
+            cast_to=cast(Type[TelemetryQueryMetricsResponse], DataWrapper[TelemetryQueryMetricsResponse]),
+        )
+
     def query_spans(
         self,
         *,
@@ -561,6 +626,68 @@ async def log_event(
             cast_to=NoneType,
         )
 
+    async def query_metrics(
+        self,
+        metric_name: str,
+        *,
+        query_type: Literal["range", "instant"],
+        start_time: int,
+        end_time: int | NotGiven = NOT_GIVEN,
+        granularity: str | NotGiven = NOT_GIVEN,
+        label_matchers: Iterable[telemetry_query_metrics_params.LabelMatcher] | NotGiven = NOT_GIVEN,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
+    ) -> TelemetryQueryMetricsResponse:
+        """
+        Query metrics.
+
+        Args:
+          query_type: The type of query to perform.
+
+          start_time: The start time of the metric to query.
+
+          end_time: The end time of the metric to query.
+
+          granularity: The granularity of the metric to query.
+
+          label_matchers: The label matchers to apply to the metric.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        if not metric_name:
+            raise ValueError(f"Expected a non-empty value for `metric_name` but received {metric_name!r}")
+        return await self._post(
+            f"/v1/telemetry/metrics/{metric_name}",
+            body=await async_maybe_transform(
+                {
+                    "query_type": query_type,
+                    "start_time": start_time,
+                    "end_time": end_time,
+                    "granularity": granularity,
+                    "label_matchers": label_matchers,
+                },
+                telemetry_query_metrics_params.TelemetryQueryMetricsParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers,
+                extra_query=extra_query,
+                extra_body=extra_body,
+                timeout=timeout,
+                post_parser=DataWrapper[TelemetryQueryMetricsResponse]._unwrapper,
+            ),
+            cast_to=cast(Type[TelemetryQueryMetricsResponse], DataWrapper[TelemetryQueryMetricsResponse]),
+        )
+
     async def query_spans(
         self,
         *,
@@ -736,6 +863,9 @@ def __init__(self, telemetry: TelemetryResource) -> None:
         self.log_event = to_raw_response_wrapper(
             telemetry.log_event,
         )
+        self.query_metrics = to_raw_response_wrapper(
+            telemetry.query_metrics,
+        )
         self.query_spans = to_raw_response_wrapper(
             telemetry.query_spans,
         )
@@ -763,6 +893,9 @@ def __init__(self, telemetry: AsyncTelemetryResource) -> None:
         self.log_event = async_to_raw_response_wrapper(
             telemetry.log_event,
         )
+        self.query_metrics = async_to_raw_response_wrapper(
+            telemetry.query_metrics,
+        )
         self.query_spans = async_to_raw_response_wrapper(
             telemetry.query_spans,
         )
@@ -790,6 +923,9 @@ def __init__(self, telemetry: TelemetryResource) -> None:
         self.log_event = to_streamed_response_wrapper(
             telemetry.log_event,
         )
+        self.query_metrics = to_streamed_response_wrapper(
+            telemetry.query_metrics,
+        )
         self.query_spans = to_streamed_response_wrapper(
             telemetry.query_spans,
         )
@@ -817,6 +953,9 @@ def __init__(self, telemetry: AsyncTelemetryResource) -> None:
         self.log_event = async_to_streamed_response_wrapper(
             telemetry.log_event,
         )
+        self.query_metrics = async_to_streamed_response_wrapper(
+            telemetry.query_metrics,
+        )
         self.query_spans = async_to_streamed_response_wrapper(
             telemetry.query_spans,
         )

src/llama_stack_client/types/__init__.py

@@ -7,6 +7,7 @@
 from .tool import Tool as Tool
 from .model import Model as Model
 from .trace import Trace as Trace
+from .metric import Metric as Metric
 from .shared import (
     Message as Message,
     Document as Document,
@@ -142,6 +143,7 @@
 from .telemetry_query_traces_params import TelemetryQueryTracesParams as TelemetryQueryTracesParams
 from .scoring_function_list_response import ScoringFunctionListResponse as ScoringFunctionListResponse
 from .telemetry_get_span_tree_params import TelemetryGetSpanTreeParams as TelemetryGetSpanTreeParams
+from .telemetry_query_metrics_params import TelemetryQueryMetricsParams as TelemetryQueryMetricsParams
 from .telemetry_query_spans_response import TelemetryQuerySpansResponse as TelemetryQuerySpansResponse
 from .tool_runtime_list_tools_params import ToolRuntimeListToolsParams as ToolRuntimeListToolsParams
 from .eval_evaluate_rows_alpha_params import EvalEvaluateRowsAlphaParams as EvalEvaluateRowsAlphaParams
@@ -152,6 +154,7 @@
 from .list_post_training_jobs_response import ListPostTrainingJobsResponse as ListPostTrainingJobsResponse
 from .scoring_function_register_params import ScoringFunctionRegisterParams as ScoringFunctionRegisterParams
 from .telemetry_get_span_tree_response import TelemetryGetSpanTreeResponse as TelemetryGetSpanTreeResponse
+from .telemetry_query_metrics_response import TelemetryQueryMetricsResponse as TelemetryQueryMetricsResponse
 from .tool_runtime_list_tools_response import ToolRuntimeListToolsResponse as ToolRuntimeListToolsResponse
 from .inference_batch_completion_params import InferenceBatchCompletionParams as InferenceBatchCompletionParams
 from .synthetic_data_generation_response import SyntheticDataGenerationResponse as SyntheticDataGenerationResponse

src/llama_stack_client/types/chat_completion_response_stream_chunk.py

@@ -3,11 +3,12 @@
 from typing import List, Optional
 from typing_extensions import Literal
 
+from .metric import Metric
 from .._models import BaseModel
 from .shared.content_delta import ContentDelta
 from .shared.shared_token_log_probs import SharedTokenLogProbs
 
-__all__ = ["ChatCompletionResponseStreamChunk", "Event", "Metric"]
+__all__ = ["ChatCompletionResponseStreamChunk", "Event"]
 
 
 class Event(BaseModel):
@@ -27,17 +28,6 @@ class Event(BaseModel):
     """Optional reason why generation stopped, if complete"""
 
 
-class Metric(BaseModel):
-    metric: str
-    """The name of the metric"""
-
-    value: float
-    """The numeric value of the metric"""
-
-    unit: Optional[str] = None
-    """(Optional) The unit of measurement for the metric value"""
-
-
 class ChatCompletionResponseStreamChunk(BaseModel):
     event: Event
     """The event containing the new content"""

src/llama_stack_client/types/metric.py

@@ -0,0 +1,18 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Optional
+
+from .._models import BaseModel
+
+__all__ = ["Metric"]
+
+
+class Metric(BaseModel):
+    metric: str
+    """The name of the metric"""
+
+    value: float
+    """The numeric value of the metric"""
+
+    unit: Optional[str] = None
+    """(Optional) The unit of measurement for the metric value"""

src/llama_stack_client/types/shared/batch_completion.py

@@ -3,21 +3,11 @@
 from typing import List, Optional
 from typing_extensions import Literal
 
+from ..metric import Metric
 from ..._models import BaseModel
 from .shared_token_log_probs import SharedTokenLogProbs
 
-__all__ = ["BatchCompletion", "Batch", "BatchMetric"]
-
-
-class BatchMetric(BaseModel):
-    metric: str
-    """The name of the metric"""
-
-    value: float
-    """The numeric value of the metric"""
-
-    unit: Optional[str] = None
-    """(Optional) The unit of measurement for the metric value"""
+__all__ = ["BatchCompletion", "Batch"]
 
 
 class Batch(BaseModel):
@@ -30,7 +20,7 @@ class Batch(BaseModel):
     logprobs: Optional[List[SharedTokenLogProbs]] = None
     """Optional log probabilities for generated tokens"""
 
-    metrics: Optional[List[BatchMetric]] = None
+    metrics: Optional[List[Metric]] = None
     """(Optional) List of metrics associated with the API response"""
 
 

src/llama_stack_client/types/shared/chat_completion_response.py

@@ -2,22 +2,12 @@
 
 from typing import List, Optional
 
+from ..metric import Metric
 from ..._models import BaseModel
 from .completion_message import CompletionMessage
 from .shared_token_log_probs import SharedTokenLogProbs
 
-__all__ = ["ChatCompletionResponse", "Metric"]
-
-
-class Metric(BaseModel):
-    metric: str
-    """The name of the metric"""
-
-    value: float
-    """The numeric value of the metric"""
-
-    unit: Optional[str] = None
-    """(Optional) The unit of measurement for the metric value"""
+__all__ = ["ChatCompletionResponse"]
 
 
 class ChatCompletionResponse(BaseModel):