Updates refs to LLMs

docs/AI-for-security/ai-security-assistant.asciidoc

@@ -47,7 +47,7 @@ You must create a generative AI connector before you can use AI Assistant. AI As
 .Recommended models
 [sidebar]
 --
-While AI Assistant is compatible with many different models, our testing found increased quality with Azure 32k, and faster, more cost-effective responses with Claude 3 Haiku and OpenAI GPT4 Turbo. For more information, refer to the <<llm-performance-matrix>>.
+While AI Assistant is compatible with many different models, refer to the <<llm-performance-matrix>> to select models that perform well with your desired use cases.
 --
 
 [discrete]

docs/AI-for-security/connect-to-azure-openai.asciidoc

@@ -68,9 +68,8 @@ Now, set up the Azure OpenAI model:
 
 . From within your Azure OpenAI deployment, select **Model deployments**, then click **Manage deployments**.
 . On the **Deployments** page, select **Create new deployment**.
-. Under **Select a model**, choose `gpt-4` or `gpt-4-32k`.
-** If you select `gpt-4`, set the **Model version** to `0125-Preview`. 
-** If you select `gpt-4-32k`, set the **Model version** to `default`.
+. Under **Select a model**, choose `gpt-4o` or `gpt-4 turbo`.
+. Set the model version to "Auto-update to default". 
 +
 IMPORTANT: The models available to you depend on https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#model-summary-table-and-region-availability[region availability]. For best results, use `GPT-4o 2024-05-13` with the maximum Tokens-Per-Minute (TPM) capacity. For more information on how different models perform for different tasks, refer to the <<llm-performance-matrix>>.
 +

docs/serverless/AI-for-security/ai-assistant.mdx

@@ -44,7 +44,7 @@ Elastic can automatically anonymize event data that you provide to AI Assistant
 You must create a generative AI connector before you can use AI Assistant. AI Assistant can connect to multiple large language model (LLM) providers so you can select the best model for your needs. To set up a connector, refer to <DocLink slug="/serverless/security/llm-connector-guides" text="LLM connector setup guides"/>.
 
 <DocCallOut title="Recommended models">
-While AI Assistant is compatible with many different models, our testing found increased quality with Azure 32k, and faster, more cost-effective responses with Claude 3 Haiku and OpenAI GPT4 Turbo. For more information, refer to the <DocLink slug="/serverless/security/llm-performance-matrix" text="LLM performance matrix"/>.
+While AI Assistant is compatible with many different models, refer to the <DocLink slug="/serverless/security/llm-performance-matrix" text="LLM performance matrix"/> to select models that perform well with your desired use cases.
 </DocCallOut>
 
 <div id="start-chatting"></div>

docs/serverless/AI-for-security/connect-to-azure-openai.mdx

@@ -47,8 +47,8 @@ Now, set up the Azure OpenAI model:
 
 1. From within your Azure OpenAI deployment, select **Model deployments**, then click **Manage deployments**.
 2. On the **Deployments** page, select **Create new deployment**.
-3. Under **Select a model**, choose `gpt-4` or `gpt-4-32k`.
-4. Set the **Model version** to `0125-Preview` for `gpt-4` or `default` for `gpt-4-32k`.
+3. Under **Select a model**, choose `gpt-4o` or `gpt-4 turbo`.
+4. Set the model version to "Auto-update to default". 
 5. Under **Deployment type**, select **Standard**.
 6. Name your deployment.
 7. Slide the **Tokens per Minute Rate Limit** to the maximum. The following example supports 80,000 TPM, but other regions might support higher limits.