Update OpenAI and Azure OpenAI connector setup guides (#5358)

* Update OpenAI connector setup guide * Updates Azure OpenAI guide * adds serverless changes * updates verbiage * minor update * Update docs/serverless/assistant/connect-to-openai.mdx Co-authored-by: Nastasha Solomon <[email protected]> * Update docs/assistant/connect-to-openai.asciidoc Co-authored-by: Nastasha Solomon <[email protected]> * Update docs/assistant/azure-openai-setup.asciidoc Co-authored-by: Nastasha Solomon <[email protected]> * Update docs/serverless/assistant/connect-to-azure-openai.mdx Co-authored-by: Nastasha Solomon <[email protected]> --------- Co-authored-by: Nastasha Solomon <[email protected]>
elastic · Jun 10, 2024 · ee612dc · ee612dc
1 parent ea8158c
commit ee612dc
Show file tree

Hide file tree

Showing 4 changed files with 9 additions and 7 deletions.
diff --git a/docs/assistant/azure-openai-setup.asciidoc b/docs/assistant/azure-openai-setup.asciidoc
@@ -72,7 +72,7 @@ Now, set up the Azure OpenAI model:
 ** If you select `gpt-4`, set the **Model version** to `0125-Preview`. 
 ** If you select `gpt-4-32k`, set the **Model version** to `default`.
 +
-IMPORTANT: The models available to you will 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 4 Turbo version 0125-preview` or `GPT 4-32k` with the maximum Tokens-Per-Minute (TPM) capacity. In most regions, the GPT 4 Turbo model offers the largest supported context window.
+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>>.
 +
 . Under **Deployment type**, select **Standard**.
 . Name your deployment.

diff --git a/docs/assistant/connect-to-openai.asciidoc b/docs/assistant/connect-to-openai.asciidoc
@@ -12,7 +12,7 @@ This page provides step-by-step instructions for setting up an OpenAI connector
 
 Before creating an API key, you must choose a model. Refer to the https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4[OpenAI docs] to select a model. Take note of the specific model name (for example `gpt-4-turbo`); you'll need it when configuring {kib}.
 
-NOTE: `GPT-4 Turbo` offers increased performance. `GPT-4` and `GPT-3.5` are also supported. 
+NOTE: `GPT-4o` offers increased performance over previous versions. For more information on how different models perform for different tasks, refer to the <<llm-performance-matrix>>.
 
 [discrete]
 === Create an API key
@@ -51,6 +51,7 @@ To integrate with {kib}:
 . Provide a name for your connector, such as `OpenAI (GPT-4 Turbo Preview)`, to help keep track of the model and version you are using.
 . Under **Select an OpenAI provider**, choose **OpenAI**.
 . The **URL** field can be left as default.
+. Under **Default model**, specify which https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4[model] you want to use.
 . Paste the API key that you created into the corresponding field.
 . Click **Save**.
 

diff --git a/docs/serverless/assistant/connect-to-azure-openai.mdx b/docs/serverless/assistant/connect-to-azure-openai.mdx
@@ -56,7 +56,7 @@ Now, set up the Azure OpenAI model:
 8. Click **Create**.
 
 <DocCallOut title="Important" color="warning">
-The models available to you will depend on [region availability](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#model-summary-table-and-region-availability). For best results, use `GPT 4 Turbo version 0125-preview` or `GPT 4-32k` with the maximum Tokens-Per-Minute (TPM) capacity. In most regions, the GPT 4 Turbo model offers the largest supported context window.
+The models available to you will depend on [region availability](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#model-summary-table-and-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 <DocLink id="llm-performance-matrix" text="LLM performance matrix"/>.
 </DocCallOut>
 
 The following video demonstrates these steps.

diff --git a/docs/serverless/assistant/connect-to-openai.mdx b/docs/serverless/assistant/connect-to-openai.mdx
@@ -18,7 +18,7 @@ This page provides step-by-step instructions for setting up an OpenAI connector
 Before creating an API key, you must choose a model. Refer to the [OpenAI docs](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4) to select a model. Take note of the specific model name (for example `gpt-4-turbo`); you'll need it when configuring ((kib)).
 
 <DocCallOut title="Note">
-`GPT-4 Turbo` offers increased performance. `GPT-4` and `GPT-3.5` are also supported.
+`GPT-4o` offers increased performance over previous versions. For more information on how different models perform for different tasks, refer to the <DocLink id="llm-performance-matrix" text="LLM performance matrix"/>.
 </DocCallOut>
 
 ### Create an API key
@@ -43,9 +43,10 @@ To integrate with ((kib)):
 2. Navigate to **Stack Management → Connectors → Create Connector → OpenAI**.
 3. Provide a name for your connector, such as `OpenAI (GPT-4 Turbo Preview)`, to help keep track of the model and version you are using.
 4. Under **Select an OpenAI provider**, choose **OpenAI**.
-5. The **URL** field can generally be left unchanged.
-6. Enter the API key that you previously created in the corresponding field.
-7. Click **Save**.
+5. The **URL** field can be left as default.
+6. Under **Default model**, specify which [model](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4) you want to use.
+7. Paste the API key that you created into the corresponding field.
+8. Click **Save**.
 
 The following video demonstrates these steps.