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: sdk/ai/azure-ai-projects/CHANGELOG.md
+30-1Lines changed: 30 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,5 +1,34 @@
1
1
# Release History
2
2
3
+
## 1.0.0 (Unreleased)
4
+
5
+
First stable version of the client library. The client library now uses version `v1` of the
6
+
AI Foundry [data plane REST APIs](https://aka.ms/azsdk/azure-ai-projects/ga-rest-api-reference).
7
+
8
+
### Breaking changes
9
+
10
+
* Features that are still in preview were removed from this stable release. This includes:
11
+
* Evaluation operations (property `.evaluations`)
12
+
* Red-Team operations (property `.red_teams`)
13
+
* Class `PromptTemplate`.
14
+
* Package function `enable_telemetry()`
15
+
* Classes were renamed:
16
+
* Class `Sku` was renamed `ModelDeploymentSku`
17
+
* Class `SasCredential` was renamed `BlobReferenceSasCredential`
18
+
* Class `AssetCredentialResponse` was renamed `DatasetCredential`
19
+
* Method `.inference.get_azure_openai_client()` was renamed `.get_openai_client()`. The `.inference` property was removed.
20
+
The method is documented as returning an object of type `OpenAI`, but it still returns an object of the derived type `AzureOpenAI`.
21
+
The function implementation has not changed.
22
+
* Method `.telemetry.get_connection_string()` was renamed `.telemetry.get_application_insights_connection_string()`
23
+
24
+
### Sample updates
25
+
26
+
* Added a new Dataset sample named `sample_datasets_download.py` to show how you can download all files referenced by a certain Dataset (following a question in [this GitHub issue](https://github.com/Azure/azure-sdk-for-python/issues/41960))
27
+
* Two samples added showing how to do a `responses` operation using an authenticated Azure OpenAI client created
28
+
using `get_openai_client()`.
29
+
* Existing inference samples that used the package function `enable_telemetry()` were updated to remove this call,
30
+
and instead add the necessary tracing configuration calls to the sample.
31
+
3
32
## 1.0.0b12 (2025-06-23)
4
33
5
34
### Breaking changes
@@ -8,7 +37,7 @@
8
37
`.inference.get_embeddings_client()` and `.inference.get_image_embeddings_client()`.
9
38
For guidance on obtaining an authenticated `azure-ai-inference` client for your AI Foundry Project,
10
39
refer to the updated samples in the `samples\inference` directory. For example,
11
-
[sample_chat_completions_with_azure_ai_inference_client.py](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/ai/azure-ai-projects/samples/inference/sample_chat_completions_with_azure_ai_inference_client.py). Alternatively, use the `.inference.get_azure_openai_client()` method to perform chat completions with an Azure OpenAI client.
40
+
`sample_chat_completions_with_azure_ai_inference_client.py`. Alternatively, use the `.inference.get_azure_openai_client()` method to perform chat completions with an Azure OpenAI client.
12
41
* Method argument name changes:
13
42
* In method `.indexes.create_or_update()` argument `body` was renamed `index`.
14
43
* In method `.datasets.create_or_update()` argument `body` was renamed `dataset_version`.
Copy file name to clipboardExpand all lines: sdk/ai/azure-ai-projects/README.md
+23-86Lines changed: 23 additions & 86 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -9,18 +9,8 @@ resources in your Azure AI Foundry Project. Use it to:
9
9
***Enumerate connected Azure resources** in your Foundry project using the `.connections` operations.
10
10
***Upload documents and create Datasets** to reference them using the `.datasets` operations.
11
11
***Create and enumerate Search Indexes** using the `.indexes` operations.
12
-
***Read a Prompty file or string** and render messages for inference clients, using the `PromptTemplate` class.
13
-
***Run Evaluations** to assess the performance of generative AI applications, using the `evaluations` operations.
14
-
***Enable OpenTelemetry tracing** using the `enable_telemetry` function.
15
12
16
-
The client library uses version `2025-05-15-preview` of the AI Foundry [data plane REST APIs](https://aka.ms/azsdk/azure-ai-projects/rest-api-reference).
17
-
18
-
> **Note:** There have been significant updates with the release of version 1.0.0b11, including breaking changes.
19
-
please see new code snippets below and the samples folder. Agents are now implemented in a separate package `azure-ai-agents`
20
-
which will get installed automatically when you install `azure-ai-projects`. You can continue using ".agents"
21
-
operations on the `AIProjectsClient` to create, run and delete agents, as before.
22
-
See [full set of Agents samples](https://github.com/Azure/azure-sdk-for-python/tree/main/sdk/ai/azure-ai-agents/samples)
23
-
in their new location. Also see the [change log for the 1.0.0b11 release](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/ai/azure-ai-projects/CHANGELOG.md).
13
+
The client library uses the version `v1` of the AI Foundry [data plane REST APIs](https://aka.ms/azsdk/azure-ai-projects/ga-rest-api-reference).
@@ -30,7 +20,7 @@ in their new location. Also see the [change log for the 1.0.0b11 release](https:
30
20
31
21
## Reporting issues
32
22
33
-
To report an issue with the client library, or request additional features, please open a GitHub issue [here](https://github.com/Azure/azure-sdk-for-python/issues). Mention the package name "azure-ai-projects" in the title or content.
23
+
To report an issue with the client library, or request additional features, please open a [GitHub issue here](https://github.com/Azure/azure-sdk-for-python/issues). Mention the package name "azure-ai-projects" in the title or content.
34
24
35
25
## Getting started
36
26
@@ -137,7 +127,7 @@ Update the `api_version` value with one found in the "Data plane - inference" ro
137
127
print(
138
128
"Get an authenticated Azure OpenAI client for the parent AI Services resource, and perform a chat completion operation:"
139
129
)
140
-
with project_client.inference.get_azure_openai_client(api_version="2024-10-21") as client:
130
+
with project_client.get_openai_client(api_version="2024-10-21") as client:
141
131
142
132
response = client.chat.completions.create(
143
133
model=model_deployment_name,
@@ -154,9 +144,7 @@ with project_client.inference.get_azure_openai_client(api_version="2024-10-21")
154
144
print(
155
145
"Get an authenticated Azure OpenAI client for a connected Azure OpenAI service, and perform a chat completion operation:"
156
146
)
157
-
with project_client.inference.get_azure_openai_client(
Evaluation in Azure AI Project client library provides quantitive, AI-assisted quality and safety metrics to asses performance and Evaluate LLM Models, GenAI Application and Agents. Metrics are defined as evaluators. Built-in or custom evaluators can provide comprehensive evaluation insights.
331
+
## Tracing
335
332
336
-
The code below shows some evaluation operations. Full list of sample can be found under "evaluation" folder in the [package samples][samples]
The AI Projects client library can be configured to emit OpenTelemetry traces for all its REST API calls. These can be viewed in the "Tracing" tab in your AI Foundry Project page, once you add an Application Insights resource and configured your application appropriately. Agent operations (via the `.agents` property) can also be instrumented, as well as OpenAI client library operations (client created by calling `get_openai_client()` method). For local debugging purposes, traces can also be omitted to the console. For more information see:
348
334
349
-
print("Create an evaluation")
350
-
evaluation: Evaluation = Evaluation(
351
-
display_name="Sample Evaluation Test",
352
-
description="Sample evaluation for testing",
353
-
# Sample Dataset Id : azureai://accounts/<account_name>/projects/<project_name>/data/<dataset_name>/versions/<version>
354
-
data=InputDataset(id=dataset.id if dataset.id else""),
for evaluation in project_client.evaluations.list():
394
-
print(evaluation)
395
-
```
396
-
397
-
<!-- END SNIPPET -->
335
+
*[Trace AI applications using OpenAI SDK](https://learn.microsoft.com/azure/ai-foundry/how-to/develop/trace-application)
336
+
* Chat-completion samples with console or Azure Monitor tracing enabled. See `samples\inference\azure-openai` folder.
337
+
* The Tracing section in the [README.md file of the azure-ai-agents package](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/ai/azure-ai-agents/README.md#tracing).
398
338
399
339
## Troubleshooting
400
340
@@ -465,7 +405,7 @@ For more information, see [Configure logging in the Azure libraries for Python](
465
405
466
406
### Reporting issues
467
407
468
-
To report an issue with the client library, or request additional features, please open a GitHub issue [here](https://github.com/Azure/azure-sdk-for-python/issues). Mention the package name "azure-ai-projects" in the title or content.
408
+
To report an issue with the client library, or request additional features, please open a [GitHub issue here](https://github.com/Azure/azure-sdk-for-python/issues). Mention the package name "azure-ai-projects" in the title or content.
469
409
470
410
## Next steps
471
411
@@ -492,6 +432,3 @@ additional questions or comments.
0 commit comments