mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-03 19:57:35 +00:00
3b9278f254
# What does this PR do? query_metrics currently has no implementation, meaning once a metric is emitted there is no way in llama stack to query it from the store. implement query_metrics for the meta_reference provider which follows a similar style to `query_traces`, using the trace_store to format an SQL query and execute it in this case the parameters for the query are `metric.METRIC_NAME, start_time, and end_time` and any other matchers if they are provided. this required client side changes since the client had no `query_metrics` or any associated resources, so any tests here will fail but I will provide manual execution logs for the new tests I am adding order the metrics by timestamp. Additionally add `unit` to the `MetricDataPoint` class since this adds much more context to the metric being queried. depends on https://github.com/llamastack/llama-stack-client-python/pull/260 ## Test Plan ``` import time import uuid def create_http_client(): from llama_stack_client import LlamaStackClient return LlamaStackClient(base_url="http://localhost:8321") client = create_http_client() response = client.telemetry.query_metrics(metric_name="total_tokens", start_time=0) print(response) ``` ``` ╰─ python3.12 ~/telemetry.py INFO:httpx:HTTP Request: POST http://localhost:8322/v1/telemetry/metrics/total_tokens "HTTP/1.1 200 OK" [TelemetryQueryMetricsResponse(data=None, metric='total_tokens', labels=[], values=[{'timestamp': 1753999514, 'value': 34.0, 'unit': 'tokens'}, {'timestamp': 1753999816, 'value': 34.0, 'unit': 'tokens'}, {'timestamp': 1753999881, 'value': 34.0, 'unit': 'tokens'}, {'timestamp': 1753999956, 'value': 34.0, 'unit': 'tokens'}, {'timestamp': 1754000200, 'value': 34.0, 'unit': 'tokens'}, {'timestamp': 1754000419, 'value': 36.0, 'unit': 'tokens'}, {'timestamp': 1754000714, 'value': 36.0, 'unit': 'tokens'}, {'timestamp': 1754000876, 'value': 36.0, 'unit': 'tokens'}, {'timestamp': 1754000908, 'value': 34.0, 'unit': 'tokens'}, {'timestamp': 1754001309, 'value': 584.0, 'unit': 'tokens'}, {'timestamp': 1754001311, 'value': 138.0, 'unit': 'tokens'}, {'timestamp': 1754001316, 'value': 349.0, 'unit': 'tokens'}, {'timestamp': 1754001318, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754001320, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754001341, 'value': 923.0, 'unit': 'tokens'}, {'timestamp': 1754001350, 'value': 354.0, 'unit': 'tokens'}, {'timestamp': 1754001462, 'value': 417.0, 'unit': 'tokens'}, {'timestamp': 1754001464, 'value': 158.0, 'unit': 'tokens'}, {'timestamp': 1754001475, 'value': 697.0, 'unit': 'tokens'}, {'timestamp': 1754001477, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754001479, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754001489, 'value': 298.0, 'unit': 'tokens'}, {'timestamp': 1754001541, 'value': 615.0, 'unit': 'tokens'}, {'timestamp': 1754001543, 'value': 119.0, 'unit': 'tokens'}, {'timestamp': 1754001548, 'value': 310.0, 'unit': 'tokens'}, {'timestamp': 1754001549, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754001551, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754001568, 'value': 714.0, 'unit': 'tokens'}, {'timestamp': 1754001800, 'value': 437.0, 'unit': 'tokens'}, {'timestamp': 1754001802, 'value': 200.0, 'unit': 'tokens'}, {'timestamp': 1754001806, 'value': 262.0, 'unit': 'tokens'}, {'timestamp': 1754001808, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754001810, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754001816, 'value': 82.0, 'unit': 'tokens'}, {'timestamp': 1754001923, 'value': 61.0, 'unit': 'tokens'}, {'timestamp': 1754001929, 'value': 391.0, 'unit': 'tokens'}, {'timestamp': 1754001939, 'value': 598.0, 'unit': 'tokens'}, {'timestamp': 1754001941, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754001942, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754001952, 'value': 252.0, 'unit': 'tokens'}, {'timestamp': 1754002053, 'value': 251.0, 'unit': 'tokens'}, {'timestamp': 1754002059, 'value': 375.0, 'unit': 'tokens'}, {'timestamp': 1754002062, 'value': 244.0, 'unit': 'tokens'}, {'timestamp': 1754002064, 'value': 111.0, 'unit': 'tokens'}, {'timestamp': 1754002065, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754002083, 'value': 719.0, 'unit': 'tokens'}, {'timestamp': 1754002302, 'value': 279.0, 'unit': 'tokens'}, {'timestamp': 1754002306, 'value': 218.0, 'unit': 'tokens'}, {'timestamp': 1754002308, 'value': 198.0, 'unit': 'tokens'}, {'timestamp': 1754002309, 'value': 69.0, 'unit': 'tokens'}, {'timestamp': 1754002311, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754002324, 'value': 481.0, 'unit': 'tokens'}, {'timestamp': 1754003161, 'value': 579.0, 'unit': 'tokens'}, {'timestamp': 1754003161, 'value': 69.0, 'unit': 'tokens'}, {'timestamp': 1754003169, 'value': 499.0, 'unit': 'tokens'}, {'timestamp': 1754003171, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754003173, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754003185, 'value': 422.0, 'unit': 'tokens'}, {'timestamp': 1754003448, 'value': 579.0, 'unit': 'tokens'}, {'timestamp': 1754003453, 'value': 422.0, 'unit': 'tokens'}, {'timestamp': 1754003589, 'value': 579.0, 'unit': 'tokens'}, {'timestamp': 1754003609, 'value': 279.0, 'unit': 'tokens'}, {'timestamp': 1754003614, 'value': 481.0, 'unit': 'tokens'}, {'timestamp': 1754003706, 'value': 303.0, 'unit': 'tokens'}, {'timestamp': 1754003706, 'value': 51.0, 'unit': 'tokens'}, {'timestamp': 1754003713, 'value': 426.0, 'unit': 'tokens'}, {'timestamp': 1754003714, 'value': 70.0, 'unit': 'tokens'}, {'timestamp': 1754003715, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754003724, 'value': 225.0, 'unit': 'tokens'}, {'timestamp': 1754004226, 'value': 516.0, 'unit': 'tokens'}, {'timestamp': 1754004228, 'value': 127.0, 'unit': 'tokens'}, {'timestamp': 1754004232, 'value': 281.0, 'unit': 'tokens'}, {'timestamp': 1754004234, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754004236, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754004244, 'value': 206.0, 'unit': 'tokens'}, {'timestamp': 1754004683, 'value': 338.0, 'unit': 'tokens'}, {'timestamp': 1754004690, 'value': 481.0, 'unit': 'tokens'}, {'timestamp': 1754004692, 'value': 124.0, 'unit': 'tokens'}, {'timestamp': 1754004692, 'value': 65.0, 'unit': 'tokens'}, {'timestamp': 1754004694, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754004703, 'value': 211.0, 'unit': 'tokens'}, {'timestamp': 1754004743, 'value': 338.0, 'unit': 'tokens'}, {'timestamp': 1754004749, 'value': 211.0, 'unit': 'tokens'}, {'timestamp': 1754005566, 'value': 481.0, 'unit': 'tokens'}, {'timestamp': 1754006101, 'value': 159.0, 'unit': 'tokens'}, {'timestamp': 1754006105, 'value': 272.0, 'unit': 'tokens'}, {'timestamp': 1754006109, 'value': 308.0, 'unit': 'tokens'}, {'timestamp': 1754006110, 'value': 61.0, 'unit': 'tokens'}, {'timestamp': 1754006112, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754006130, 'value': 705.0, 'unit': 'tokens'}, {'timestamp': 1754051825, 'value': 454.0, 'unit': 'tokens'}, {'timestamp': 1754051827, 'value': 152.0, 'unit': 'tokens'}, {'timestamp': 1754051834, 'value': 481.0, 'unit': 'tokens'}, {'timestamp': 1754051835, 'value': 55.0, 'unit': 'tokens'}, {'timestamp': 1754051837, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754051845, 'value': 102.0, 'unit': 'tokens'}, {'timestamp': 1754099929, 'value': 36.0, 'unit': 'tokens'}, {'timestamp': 1754510050, 'value': 598.0, 'unit': 'tokens'}, {'timestamp': 1754510052, 'value': 160.0, 'unit': 'tokens'}, {'timestamp': 1754510064, 'value': 725.0, 'unit': 'tokens'}, {'timestamp': 1754510065, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754510067, 'value': 133.0, 'unit': 'tokens'}, {'timestamp': 1754510083, 'value': 535.0, 'unit': 'tokens'}, {'timestamp': 1754596582, 'value': 36.0, 'unit': 'tokens'}])] ``` adding tests for each currently documented metric in llama stack using this new function. attached is also some manual testing integrations tests passing locally with replay mode and the linked client changes: <img width="1907" height="529" alt="Screenshot 2025-08-08 at 2 49 14 PM" src="https://github.com/user-attachments/assets/d482ab06-dcff-4f0c-a1f1-f870670ee9bc" /> --------- Signed-off-by: Charlie Doern <cdoern@redhat.com>
39 lines
2.5 KiB
JSON
39 lines
2.5 KiB
JSON
{
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://localhost:11434/api/generate",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "llama3.2:3b",
|
|
"raw": true,
|
|
"prompt": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nTest metrics generation 0<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
|
|
"options": {
|
|
"temperature": 0.0
|
|
},
|
|
"stream": false
|
|
},
|
|
"endpoint": "/api/generate",
|
|
"model": "llama3.2:3b"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "ollama._types.GenerateResponse",
|
|
"__data__": {
|
|
"model": "llama3.2:3b",
|
|
"created_at": "2025-08-11T15:56:06.703788Z",
|
|
"done": true,
|
|
"done_reason": "stop",
|
|
"total_duration": 2722294000,
|
|
"load_duration": 9736083,
|
|
"prompt_eval_count": 21,
|
|
"prompt_eval_duration": 113000000,
|
|
"eval_count": 324,
|
|
"eval_duration": 2598000000,
|
|
"response": "Here are some test metrics that can be used to evaluate the performance of a system:\n\n1. **Accuracy**: The proportion of correct predictions made by the model.\n2. **Precision**: The ratio of true positives (correctly predicted instances) to total positive predictions.\n3. **Recall**: The ratio of true positives to the sum of true positives and false negatives (missed instances).\n4. **F1-score**: The harmonic mean of precision and recall, providing a balanced measure of both.\n5. **Mean Squared Error (MSE)**: The average squared difference between predicted and actual values.\n6. **Mean Absolute Error (MAE)**: The average absolute difference between predicted and actual values.\n7. **Root Mean Squared Percentage Error (RMSPE)**: A variation of MSE that expresses the error as a percentage.\n8. **Coefficient of Determination (R-squared, R2)**: Measures how well the model explains the variance in the data.\n9. **Mean Absolute Percentage Error (MAPE)**: The average absolute percentage difference between predicted and actual values.\n10. **Mean Squared Logarithmic Error (MSLE)**: A variation of MSE that is more suitable for skewed distributions.\n\nThese metrics can be used to evaluate different aspects of a system's performance, such as:\n\n* Classification models: accuracy, precision, recall, F1-score\n* Regression models: MSE, MAE, RMSPE, R2, MSLE\n* Time series forecasting: MAPE, RMSPE\n\nNote that the choice of metric depends on the specific problem and data.",
|
|
"thinking": null,
|
|
"context": null
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|