link fixes

Author: aahill

articles/ai-foundry/openai/concepts/content-filter-groundedness.md

@@ -10,4 +10,4 @@ ms.service: azure-ai-openai
 
 # Groundedness detection filter
 
-[!INCLUDE [groundedness-detection-overview](../../content-safety/includes/groundedness-detection-overview.md)]
+[!INCLUDE [groundedness-detection-overview](../../../ai-services/content-safety/includes/groundedness-detection-overview.md)]

articles/ai-foundry/openai/concepts/content-filter-prompt-shields.md

@@ -15,7 +15,7 @@ Prompt shields are a feature of the Azure OpenAI content filtering system that h
 
 Prompt shields analyzes LLM inputs and detects adversarial user input attacks.
 
-[!INCLUDE [prompt-shield-attack-info](../../content-safety/includes/prompt-shield-attack-info.md)]
+[!INCLUDE [prompt-shield-attack-info](../../../ai-services/content-safety/includes/prompt-shield-attack-info.md)]
 
 ## Spotlighting for prompt shields
 

articles/ai-foundry/openai/concepts/content-filter-protected-material.md

@@ -16,4 +16,4 @@ The Protected material text filter flags known text content (for example, song l
 
 The Protected material code filter flags protected code content (from known GitHub repositories, including software libraries, source code, algorithms, and other proprietary programming content) that might be output by large language models.
 
-[!INCLUDE [protected-material-examples](../../content-safety/includes/protected-material-examples.md)]
+[!INCLUDE [protected-material-examples](.../../../ai-services/content-safety/includes/protected-material-examples.md)]

articles/ai-foundry/openai/concepts/content-filter-severity-levels.md

@@ -21,6 +21,6 @@ Content filtering ensures that AI-generated outputs align with ethical guideline
 > The text content filtering models for the hate, sexual, violence, and self-harm categories have been specifically trained and tested on the following languages: English, German, Japanese, Spanish, French, Italian, Portuguese, and Chinese. However, the service can work in many other languages, but the quality might vary. In all cases, you should do your own testing to ensure that it works for your application.
 
 
-[!INCLUDE [severity-levels text, four-level](../../content-safety/includes/severity-levels-text-four.md)]
+[!INCLUDE [severity-levels text, four-level](.../../../ai-services/content-safety/includes/severity-levels-text-four.md)]
 
-[!INCLUDE [severity-levels image](../../content-safety/includes/severity-levels-image.md)]
+[!INCLUDE [severity-levels image](.../../../ai-services/content-safety/includes/severity-levels-image.md)]