You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/ai-foundry/foundry-models/how-to/quickstart-github-models.md
+18-13Lines changed: 18 additions & 13 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -38,34 +38,39 @@ To get the key and endpoint:
38
38
39
39
1. Go to [GitHub Models](https://github.com/marketplace/models) and select a model to land on its playground. This article uses Mistral Large 24.11.
40
40
41
-
1.Select **Use this model** from the playground
41
+
1.Type in some prompts or use some of the suggested prompts to interact with the model in the playground.
42
42
43
-
1.In the playground for your model, select **Use this model**. This action opens up a window to "Get started with Models in your codebase".
43
+
1.Select **Use this model** from the playground. This action opens up a window to "Get started with Models in your codebase".
44
44
45
45
1. In the "Configure authentication" step, select **Get Azure AI key** from the "Azure AI" section.
46
46
47
47
:::image type="content" source="../media/quickstart-github-models/github-models-get-production-key.png" alt-text="A screenshot showing how to get the Azure AI production key from the playground of a GitHub Model." lightbox="../media/quickstart-github-models/github-models-get-production-key.png":::
48
48
49
-
1.The Azure AI Foundry homepage opens up if you're already signed in to your Azure account, otherwise you land on the Azure AI Foundry sign in page.
49
+
1.If you're already signed in to your Azure account, skip this step. However, if you don't have an Azure account or you're not signed in to your account, follow these steps:
50
50
51
-
1. If you're not yet signed in to your Azure account, select **Sign in to get started**to open the sign in window.
51
+
1. If you don't have an Azure account, select **Create my account**and follow the steps to create one.
52
52
53
-
- If you don't have an Azure account, select **Create one** and follow the steps to create a paid account.
53
+
1. Alternatively, if you have an Azure account, select **Sign back in**. If your existing account is a free account, you first have to upgrade to a standard plan.
54
54
55
-
- Alternatively, if you have an existing account, sign in. If your existing account is a free account, you first have to upgrade to a standard plan.
55
+
1. Return to the model's playground and select **Get Azure AI key** again.
56
+
57
+
1. Sign in to your Azure account.
56
58
57
-
- Return to the model's playground and select **Get Azure AI key** again. This time, you land on the Azure AI Foundry homepage.
59
+
1. You're taken to [Azure AI Foundry > GitHub](https://ai.azure.com/GitHub), and the page loads with your model's details. It might take one or two minutes to load your model details in Azure AI Foundry.
60
+
61
+
1. For [Foundry Models from partners and community](../../concepts/models-from-partners.md), you need to subscribe to Azure Marketplace. This requirement applies to Mistral-Large-2411, for example. Select **Agree and Proceed** to accept the terms.
58
62
59
-
1.Go to the "Explore models and capabilities" section of the homepage to search for and select the **Mistral Large 24.11**model. This action opens up the model card where you can see the model's details.
63
+
1.Select the **Deploy**button to deploy the model to your account.
60
64
61
-
1.Select **Use this model** to deploy the model to your account. This process begins by creating an Azure AI Foundry project to use for your deployment.
65
+
1.When your deployment is ready, you land on your project's **Overview** page, where you can see the Azure AI Foundry project's endpoint.
62
66
63
-
1.When your deployment is ready, the endpoint's target URI and API key appear in the deployment's details page. Use these values in your code to use the model in your production environment.
67
+
1.Go to the **Models + endpoints** tab in the left pane of the Azure AI Foundry portal and select the deployed model. The endpoint's target URI and API key are visible on the deployment's details page. Use these values in your code to use the model in your production environment.
64
68
69
+
:::image type="content" source="../media/quickstart-github-models/github-models-get-production-key.png" alt-text="Screenshot showing how to get the URL and key associated with the deployment." lightbox="../media/quickstart-github-models/github-models-get-production-key.png":::
65
70
66
71
## Use the new endpoint
67
72
68
-
You can use any of the supported SDKs to get predictions from the endpoint. The following SDKs are officially supported:
73
+
To use your deployed model with code, you need the model's endpoint URL and key, which you saw in the previous section. You can use any of the supported SDKs to get predictions from the endpoint. The following SDKs are officially supported:
69
74
70
75
* OpenAI SDK
71
76
* Azure OpenAI SDK
@@ -86,7 +91,7 @@ Use the parameter `model="<deployment-name>` to route your request to this deplo
86
91
87
92
## Explore additional features
88
93
89
-
Azure AI Foundry Models supports additional features that aren't available in GitHub Models, including:
94
+
Azure AI Foundry Models supports extra features that aren't available in GitHub Models, including:
90
95
91
96
*[Explore the model catalog](https://ai.azure.com/github/models) to see more models.
0 commit comments