Skip to content

Commit 28058f8

Browse files
committed
updates for data collection GA
1 parent d56ec92 commit 28058f8

File tree

2 files changed

+9
-13
lines changed

2 files changed

+9
-13
lines changed

articles/machine-learning/concept-data-collection.md

Lines changed: 5 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
---
2-
title: Inference data collection from models in production (preview)
2+
title: Inference data collection from models in production
33
titleSuffix: Azure Machine Learning
44
description: Collect inference data from models deployed on Azure Machine Learning to monitor their performance in production.
55
services: machine-learning
@@ -10,18 +10,16 @@ ms.subservice: mlops
1010
ms.reviewer: mopeakande
1111
reviewer: msakande
1212
ms.topic: conceptual
13-
ms.date: 05/09/2023
13+
ms.date: 04/15/2024
1414
ms.custom: devplatv2, event-tier1-build-2023, build-2023
1515
---
1616

17-
# Data collection from models in production (preview)
17+
# Data collection from models in production
1818

1919
[!INCLUDE [dev v2](includes/machine-learning-dev-v2.md)]
2020

2121
In this article, you'll learn about data collection from models that are deployed to Azure Machine Learning online endpoints.
2222

23-
[!INCLUDE [machine-learning-preview-generic-disclaimer](includes/machine-learning-preview-generic-disclaimer.md)]
24-
2523
Azure Machine Learning **Data collector** provides real-time logging of input and output data from models that are deployed to managed online endpoints or Kubernetes online endpoints. Azure Machine Learning stores the logged inference data in Azure blob storage. This data can then be seamlessly used for model monitoring, debugging, or auditing, thereby, providing observability into the performance of your deployed models.
2624

2725
Data collector provides:
@@ -43,9 +41,9 @@ Data collector can be configured at the deployment level, and the configuration
4341

4442
Data collector has the following limitations:
4543
- Data collector only supports logging for online (or real-time) Azure Machine Learning endpoints (Managed or Kubernetes).
46-
- The Data collector Python SDK only supports logging tabular data via `pandas DataFrames`.
44+
- The Data collector Python SDK only supports logging tabular data via pandas DataFrames.
4745

4846
## Next steps
4947

50-
- [How to collect data from models in production (preview)](how-to-collect-production-data.md)
48+
- [How to collect data from models in production](how-to-collect-production-data.md)
5149
- [What are Azure Machine Learning endpoints?](concept-endpoints.md)

articles/machine-learning/how-to-collect-production-data.md

Lines changed: 4 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
---
2-
title: Collect production data from models deployed for real-time inferencing (preview)
2+
title: Collect production data from models deployed for real-time inferencing
33
titleSuffix: Azure Machine Learning
44
description: Collect inference data from a model deployed to a real-time endpoint on Azure Machine Learning.
55
services: machine-learning
@@ -8,20 +8,18 @@ ms.subservice: mlops
88
ms.topic: how-to
99
author: ahughes-msft
1010
ms.author: alehughes
11-
ms.date: 01/29/2024
11+
ms.date: 04/15/2024
1212
ms.reviewer: mopeakande
1313
reviewer: msakande
1414
ms.custom: devplatv2, build-2023
1515
---
1616

17-
# Collect production data from models deployed for real-time inferencing (preview)
17+
# Collect production data from models deployed for real-time inferencing
1818

1919
[!INCLUDE [dev v2](includes/machine-learning-dev-v2.md)]
2020

2121
In this article, you learn how to use Azure Machine Learning **Data collector** to collect production inference data from a model that is deployed to an Azure Machine Learning managed online endpoint or a Kubernetes online endpoint.
2222

23-
[!INCLUDE [machine-learning-preview-generic-disclaimer](includes/machine-learning-preview-generic-disclaimer.md)]
24-
2523
You can enable data collection for new or existing online endpoint deployments. Azure Machine Learning data collector logs inference data in Azure Blob Storage. Data collected with the Python SDK is automatically registered as a data asset in your Azure Machine Learning workspace. This data asset can be used for model monitoring.
2624

2725
If you're interested in collecting production inference data for an MLflow model that is deployed to a real-time endpoint, see [Data collection for MLflow models](#collect-data-for-mlflow-models).
@@ -482,7 +480,7 @@ To view the collected data in Blob Storage from the studio UI:
482480

483481
If you're deploying an MLflow model to an Azure Machine Learning online endpoint, you can enable production inference data collection with single toggle in the studio UI. If data collection is toggled on, Azure Machine Learning auto-instruments your scoring script with custom logging code to ensure that the production data is logged to your workspace Blob Storage. Your model monitors can then use the data to monitor the performance of your MLflow model in production.
484482

485-
While you're configuring the deployment of your model, you can enable production data collection. Under the **Deployment** tab, select **Enabled** for **Data collection (preview)**.
483+
While you're configuring the deployment of your model, you can enable production data collection. Under the **Deployment** tab, select **Enabled** for **Data collection**.
486484

487485
After you've enabled data collection, production inference data will be logged to your Azure Machine Learning workspace Blob Storage and two data assets will be created with names `<endpoint_name>-<deployment_name>-model_inputs` and `<endpoint_name>-<deployment_name>-model_outputs`. These data assets are updated in real time as you use your deployment in production. Your model monitors can then use the data assets to monitor the performance of your model in production.
488486

0 commit comments

Comments
 (0)