Skip to content

Commit 43e0779

Browse files
JamesJBarnettJamesJBarnett
authored
Merge pull request #2516 from santiagxf/santiagxf/quality-review
Quality general review
2 parents 4025a6c + 6dc7c33 commit 43e0779

File tree

13 files changed

+44
-39
lines changed

13 files changed

+44
-39
lines changed

‎articles/ai-foundry/model-inference/how-to/inference.md‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -26,9 +26,9 @@ Azure AI services expose multiple endpoints depending on the type of work you're
2626
> * Azure AI model inference endpoint
2727
> * Azure OpenAI endpoint
2828
29-
The **Azure AI inference endpoint** allows customers to use a single endpoint with the same authentication and schema to generate inference for the deployed models in the resource. All the models support this capability. This endpoint follows the [Azure AI model inference API](../../../ai-studio/reference/reference-model-inference-api.md).
29+
The **Azure AI inference endpoint** (usually with the form `https://<resource-name>.services.ai.azure.com/models`) allows customers to use a single endpoint with the same authentication and schema to generate inference for the deployed models in the resource. All the models support this capability. This endpoint follows the [Azure AI model inference API](../../../ai-studio/reference/reference-model-inference-api.md).
3030

31-
**Azure OpenAI** models deployed to AI services also support the Azure OpenAI API. This endpoint exposes the full capabilities of OpenAI models and supports more features like assistants, threads, files, and batch inference.
31+
**Azure OpenAI** models deployed to AI services also support the Azure OpenAI API (usually with the form `https://<resource-name>.openai.azure.com`). This endpoint exposes the full capabilities of OpenAI models and supports more features like assistants, threads, files, and batch inference.
3232

3333
To learn more about how to apply the **Azure OpenAI endpoint** see [Azure OpenAI service documentation](../../../ai-services/openai/overview.md).
3434

‎articles/ai-foundry/model-inference/includes/code-create-chat-client-entra.md‎

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -26,7 +26,7 @@ from azure.ai.inference import ChatCompletionsClient
2626
from azure.identity import AzureDefaultCredential
2727

2828
model = ChatCompletionsClient(
29-
endpoint=os.environ["AZUREAI_ENDPOINT_URL"],
29+
endpoint="https://<resource>.services.ai.azure.com/models",
3030
credential=AzureDefaultCredential(),
3131
model="mistral-large-2407",
3232
)
@@ -48,7 +48,7 @@ import { isUnexpected } from "@azure-rest/ai-inference";
4848
import { AzureDefaultCredential } from "@azure/identity";
4949

5050
const client = new ModelClient(
51-
process.env.AZUREAI_ENDPOINT_URL,
51+
"https://<resource>.services.ai.azure.com/models",
5252
new AzureDefaultCredential(),
5353
"mistral-large-2407"
5454
);
@@ -80,7 +80,7 @@ Then, you can use the package to consume the model. The following example shows
8080

8181
```csharp
8282
ChatCompletionsClient client = new ChatCompletionsClient(
83-
new Uri(Environment.GetEnvironmentVariable("AZURE_INFERENCE_ENDPOINT")),
83+
new Uri("https://<resource>.services.ai.azure.com/models"),
8484
new AzureDefaultCredential(includeInteractiveCredentials: true),
8585
"mistral-large-2407"
8686
);
@@ -108,7 +108,7 @@ Then, you can use the package to consume the model. The following example shows
108108
```java
109109
ChatCompletionsClient client = new ChatCompletionsClientBuilder()
110110
.credential(new DefaultAzureCredential()))
111-
.endpoint("{endpoint}")
111+
.endpoint("https://<resource>.services.ai.azure.com/models")
112112
.model("mistral-large-2407")
113113
.buildClient();
114114
```
@@ -122,7 +122,7 @@ Use the reference section to explore the API design and which parameters are ava
122122
__Request__
123123

124124
```HTTP/1.1
125-
POST models/chat/completions?api-version=2024-04-01-preview
125+
POST https://<resource>.services.ai.azure.com/models/chat/completions?api-version=2024-05-01-preview
126126
Authorization: Bearer <bearer-token>
127127
Content-Type: application/json
128128
```

‎articles/ai-foundry/model-inference/includes/code-create-chat-client.md‎

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -26,7 +26,7 @@ from azure.ai.inference import ChatCompletionsClient
2626
from azure.core.credentials import AzureKeyCredential
2727

2828
model = ChatCompletionsClient(
29-
endpoint=os.environ["AZUREAI_ENDPOINT_URL"],
29+
endpoint="https://<resource>.services.ai.azure.com/models",
3030
credential=AzureKeyCredential(os.environ["AZUREAI_ENDPOINT_KEY"]),
3131
)
3232
```
@@ -49,7 +49,7 @@ import { isUnexpected } from "@azure-rest/ai-inference";
4949
import { AzureKeyCredential } from "@azure/core-auth";
5050

5151
const client = new ModelClient(
52-
process.env.AZUREAI_ENDPOINT_URL,
52+
"https://<resource>.services.ai.azure.com/models",
5353
new AzureKeyCredential(process.env.AZUREAI_ENDPOINT_KEY)
5454
);
5555
```
@@ -76,7 +76,7 @@ Then, you can use the package to consume the model. The following example shows
7676

7777
```csharp
7878
ChatCompletionsClient client = new ChatCompletionsClient(
79-
new Uri(Environment.GetEnvironmentVariable("AZURE_INFERENCE_ENDPOINT")),
79+
new Uri("https://<resource>.services.ai.azure.com/models"),
8080
new AzureKeyCredential(Environment.GetEnvironmentVariable("AZURE_INFERENCE_CREDENTIAL"))
8181
);
8282
```
@@ -114,7 +114,7 @@ Use the reference section to explore the API design and which parameters are ava
114114
__Request__
115115

116116
```HTTP/1.1
117-
POST models/chat/completions?api-version=2024-04-01-preview
117+
POST https://<resource>.services.ai.azure.com/models/chat/completions?api-version=2024-05-01-preview
118118
Authorization: Bearer <bearer-token>
119119
Content-Type: application/json
120120
```

‎articles/ai-foundry/model-inference/includes/code-create-chat-completion.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -77,7 +77,7 @@ for (ChatChoice choice : chatCompletions.getChoices()) {
7777
__Request__
7878

7979
```HTTP/1.1
80-
POST models/chat/completions?api-version=2024-04-01-preview
80+
POST https://<resource>.services.ai.azure.com/models/chat/completions?api-version=2024-05-01-preview
8181
Authorization: Bearer <bearer-token>
8282
Content-Type: application/json
8383
```

‎articles/ai-foundry/model-inference/includes/code-create-embeddings-client.md‎

Lines changed: 7 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -26,7 +26,7 @@ from azure.ai.inference import EmbeddingsClient
2626
from azure.core.credentials import AzureKeyCredential
2727

2828
client = EmbeddingsClient(
29-
endpoint=os.environ["AZUREAI_ENDPOINT_URL"],
29+
endpoint="https://<resource>.services.ai.azure.com/models",
3030
credential=AzureKeyCredential(os.environ["AZUREAI_ENDPOINT_KEY"]),
3131
)
3232
```
@@ -39,7 +39,7 @@ from azure.ai.inference import EmbeddingsClient
3939
from azure.identity import AzureDefaultCredential
4040

4141
client = EmbeddingsClient(
42-
endpoint=os.environ["AZUREAI_ENDPOINT_URL"],
42+
endpoint="https://<resource>.services.ai.azure.com/models",
4343
credential=AzureDefaultCredential(),
4444
)
4545
```
@@ -62,7 +62,7 @@ import { isUnexpected } from "@azure-rest/ai-inference";
6262
import { AzureKeyCredential } from "@azure/core-auth";
6363

6464
const client = new ModelClient(
65-
process.env.AZUREAI_ENDPOINT_URL,
65+
"https://<resource>.services.ai.azure.com/models",
6666
new AzureKeyCredential(process.env.AZUREAI_ENDPOINT_KEY)
6767
);
6868
```
@@ -75,7 +75,7 @@ import { isUnexpected } from "@azure-rest/ai-inference";
7575
import { AzureDefaultCredential } from "@azure/identity";
7676

7777
const client = new ModelClient(
78-
process.env.AZUREAI_ENDPOINT_URL,
78+
"https://<resource>.services.ai.azure.com/models",
7979
new AzureDefaultCredential()
8080
);
8181
```
@@ -108,7 +108,7 @@ Then, you can use the package to consume the model. The following example shows
108108

109109
```csharp
110110
EmbeddingsClient client = new EmbeddingsClient(
111-
new Uri(Environment.GetEnvironmentVariable("AZURE_INFERENCE_ENDPOINT")),
111+
new Uri("https://<resource>.services.ai.azure.com/models"),
112112
new AzureKeyCredential(Environment.GetEnvironmentVariable("AZURE_INFERENCE_CREDENTIAL"))
113113
);
114114
```
@@ -117,7 +117,7 @@ For endpoint with support for Microsoft Entra ID (formerly Azure Active Director
117117

118118
```csharp
119119
EmbeddingsClient client = new EmbeddingsClient(
120-
new Uri(Environment.GetEnvironmentVariable("AZURE_INFERENCE_ENDPOINT")),
120+
new Uri("https://<resource>.services.ai.azure.com/models"),
121121
new DefaultAzureCredential(includeInteractiveCredentials: true)
122122
);
123123
```
@@ -131,7 +131,7 @@ Use the reference section to explore the API design and which parameters are ava
131131
__Request__
132132

133133
```HTTP/1.1
134-
POST models/embeddings?api-version=2024-04-01-preview
134+
POST https://<resource>.services.ai.azure.com/models/embeddings?api-version=2024-05-01-preview
135135
Authorization: Bearer <bearer-token>
136136
Content-Type: application/json
137137
```

‎articles/ai-foundry/model-inference/includes/code-create-embeddings.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -53,7 +53,7 @@ Console.WriteLine($"Response: {response.Data.Embeddings}");
5353
__Request__
5454

5555
```HTTP/1.1
56-
POST models/embeddings?api-version=2024-04-01-preview
56+
POST https://<resource>.services.ai.azure.com/models/embeddings?api-version=2024-05-01-preview
5757
Authorization: Bearer <bearer-token>
5858
Content-Type: application/json
5959
```

‎articles/ai-foundry/model-inference/includes/code-manage-content-filtering.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -122,7 +122,7 @@ try {
122122
__Request__
123123

124124
```HTTP/1.1
125-
POST /chat/completions?api-version=2024-04-01-preview
125+
POST /chat/completions?api-version=2024-05-01-preview
126126
Authorization: Bearer <bearer-token>
127127
Content-Type: application/json
128128
```

‎articles/ai-foundry/model-inference/includes/how-to-prerequisites.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -9,7 +9,7 @@ author: santiagxf
99

1010
* An Azure subscription. If you're using [GitHub Models](https://docs.github.com/en/github-models/), you can upgrade your experience and create an Azure subscription in the process. Read [Upgrade from GitHub Models to Azure AI model inference](../how-to/quickstart-github-models.md) if that's your case.
1111

12-
* An Azure AI services resource. For more information, see [Create an Azure AI Services resource](../../../ai-services/multi-service-resource.md?context=/azure/ai-services/model-inference/context/context).
12+
* An Azure AI services resource. For more information, see [Create an Azure AI Services resource](../how-to/quickstart-create-resources.md).
1313

1414
* The endpoint URL and key.
1515

‎articles/ai-foundry/model-inference/includes/use-chat-completions/rest.md‎

Lines changed: 6 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -28,18 +28,18 @@ To use chat completion models in your application, you need:
2828

2929
## Use chat completions
3030

31-
To use the text embeddings, use the route `/chat/completions` along with your credential indicated in `api-key`. `Authorization` header is also supported with the format `Bearer <key>`.
31+
To use the text embeddings, use the route `/chat/completions` appended to the base URL along with your credential indicated in `api-key`. `Authorization` header is also supported with the format `Bearer <key>`.
3232

3333
```http
34-
POST /chat/completions
34+
POST https://<resource>.services.ai.azure.com/models/chat/completions?api-version=2024-05-01-preview
3535
Content-Type: application/json
3636
api-key: <key>
3737
```
3838

3939
If you have configured the resource with **Microsoft Entra ID** support, pass you token in the `Authorization` header:
4040

4141
```http
42-
POST /chat/completions
42+
POST https://<resource>.services.ai.azure.com/models/chat/completions?api-version=2024-05-01-preview
4343
Content-Type: application/json
4444
Authorization: Bearer <token>
4545
```
@@ -287,8 +287,7 @@ Some models can create JSON outputs. Set `response_format` to `json_object` to e
287287
The Azure AI Model Inference API allows you to pass extra parameters to the model. The following code example shows how to pass the extra parameter `logprobs` to the model.
288288

289289
```http
290-
POST /chat/completions HTTP/1.1
291-
Host: <ENDPOINT_URI>
290+
POST https://<resource>.services.ai.azure.com/models/chat/completions?api-version=2024-05-01-preview
292291
Authorization: Bearer <TOKEN>
293292
Content-Type: application/json
294293
extra-parameters: pass-through
@@ -565,7 +564,7 @@ Now, create a chat completion request with the image:
565564

566565
```json
567566
{
568-
"model": "mistral-large-2407",
567+
"model": "phi-3.5-vision-instruct",
569568
"messages": [
570569
{
571570
"role": "user",
@@ -597,7 +596,7 @@ The response is as follows, where you can see the model's usage statistics:
597596
"id": "0a1234b5de6789f01gh2i345j6789klm",
598597
"object": "chat.completion",
599598
"created": 1718726686,
600-
"model": "mistral-large-2407",
599+
"model": "phi-3.5-vision-instruct",
601600
"choices": [
602601
{
603602
"index": 0,

‎articles/ai-foundry/model-inference/includes/use-embeddings/rest.md‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -28,18 +28,18 @@ To use embedding models in your application, you need:
2828

2929
## Use embeddings
3030

31-
To use the text embeddings, use the route `/embeddings` along with your credential indicated in `api-key`. `Authorization` header is also supported with the format `Bearer <key>`.
31+
To use the text embeddings, use the route `/embeddings` appended to the base URL along with your credential indicated in `api-key`. `Authorization` header is also supported with the format `Bearer <key>`.
3232

3333
```http
34-
POST /embeddings
34+
POST https://<resource>.services.ai.azure.com/models/embeddings?api-version=2024-05-01-preview
3535
Content-Type: application/json
3636
api-key: <key>
3737
```
3838

3939
If you have configured the resource with **Microsoft Entra ID** support, pass you token in the `Authorization` header:
4040

4141
```http
42-
POST /embeddings
42+
POST https://<resource>.services.ai.azure.com/models/embeddings?api-version=2024-05-01-preview
4343
Content-Type: application/json
4444
Authorization: Bearer <token>
4545
```

0 commit comments

Comments
 (0)