diff --git a/docs/content/patterns/artificial intelligence/_index.md b/docs/content/patterns/artificial intelligence/_index.md index 9fd7b12e1..5f505d814 100644 --- a/docs/content/patterns/artificial intelligence/_index.md +++ b/docs/content/patterns/artificial intelligence/_index.md @@ -40,4 +40,4 @@ Running AI workloads on Azure infrastructure involves monitoring each of the com ### AI Specialized Workload Patterns -#### GPT-RAG (coming soon) +#### [GPT-RAG](./rag/) diff --git a/docs/content/patterns/artificial intelligence/rag/_index.md b/docs/content/patterns/artificial intelligence/rag/_index.md new file mode 100644 index 000000000..47325a2da --- /dev/null +++ b/docs/content/patterns/artificial intelligence/rag/_index.md @@ -0,0 +1,20 @@ +--- +title: GPT-RAG +geekdocCollapseSection: true +--- + +## Overview + +The Retrieval-Augmented Generation (RAG) pattern is an industry-standard approach to building applications that use large language models to reason over specific or proprietary data that is not already known to the large language model. + +This page provides the alert settings for AI RAG pattern setup. It contains relevant metrics and threshold recommendations for key services involved in a RAG pattern architecture.For a reference architecture design of RAG, see [GPT-RAG](https://github.com/Azure/GPT-RAG). + +Below is a basic architecture of RAG implementation + +![RAG Basic Architecture](https://github.com/Azure/GPT-RAG/blob/main/media/architecture-GPT-RAG-Basic.png?raw=true) + +We may update these settings as we continue to work with a breadth of customers. + +## Alerts + +{{< ragMetricAlerts >}} diff --git a/docs/layouts/shortcodes/ragMetricAlerts.html b/docs/layouts/shortcodes/ragMetricAlerts.html new file mode 100644 index 000000000..3bc9f6ab3 --- /dev/null +++ b/docs/layouts/shortcodes/ragMetricAlerts.html @@ -0,0 +1,95 @@ +
Alert Name | +Component | +Metric | +Aggregation | +Operator | +Threshold | +Window | +Frequency | +Severity | +Scope | +Support for Multiple Resources | +Verified | +References | +
---|---|---|---|---|---|---|---|---|---|---|---|---|
+ {{ $data.Get "name" }} + | ++ {{ .properties.metricNamespace }} + | ++ {{ .properties.metricName }} + | ++ {{ .properties.timeAggregation }} + | ++ {{ .properties.operator }} + | ++ {{ if eq .properties.criterionType "DynamicThresholdCriterion" }} + dynamic + {{ else }} + {{ .properties.threshold }} + {{ end }} + | ++ {{ .properties.windowSize }} + | ++ {{ .properties.evaluationFrequency }} + | ++ {{ .properties.severity }} + | ++ {{ $data.Get "scope" }} + | ++ {{ if ($data.Get "multiResource") }} + Yes + {{ else }} + No + {{ end }} + | ++ {{ if .verified }} + Y + {{ else }} + N + {{ end }} + | ++ {{ range .references }} + {{ .name }} + {{ end }} + | +