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-services/openai/how-to/dotnet-migration.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -19,7 +19,7 @@ manager: nitinme
19
19
20
20
## Setup
21
21
22
-
Stable releases of `Azure.AI.OpenAI` are associated with a corresponding stable Azure OpenAI in Azure AI Model Inference API version label, for example, `2024-10-21`.
22
+
Stable releases of `Azure.AI.OpenAI` are associated with a corresponding stable Azure OpenAI in Azure AI Foundry Models API version label, for example, `2024-10-21`.
Copy file name to clipboardExpand all lines: articles/ai-services/openai/how-to/migration-javascript.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -13,7 +13,7 @@ manager: nitinme
13
13
14
14
# Migrating to the OpenAI JavaScript API library 4.x
15
15
16
-
As of June 2024, we recommend migrating to the OpenAI JavaScript API library 4.x, the latest version of the official OpenAI JavaScript client library that supports the Azure OpenAI in Azure AI Model Inference API version `2022-12-01` and later. This article helps you bring you up to speed on the changes specific to Azure OpenAI.
16
+
As of June 2024, we recommend migrating to the OpenAI JavaScript API library 4.x, the latest version of the official OpenAI JavaScript client library that supports the Azure OpenAI in Azure AI Foundry Models API version `2022-12-01` and later. This article helps you bring you up to speed on the changes specific to Azure OpenAI.
Copy file name to clipboardExpand all lines: articles/ai-services/openai/includes/api-versions/new-inference-preview.md
+18-18Lines changed: 18 additions & 18 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -21,7 +21,7 @@ Generates text-to-speech audio from the input text.
21
21
| Name | In | Required | Type | Description |
22
22
|------|------|----------|------|-----------|
23
23
| endpoint | path | Yes | string<br>url | Supported Azure OpenAI endpoints (protocol and hostname, for example: `https://aoairesource.openai.azure.com`. Replace "aoairesource" with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com |
24
-
| api-version | query | No || The explicit Azure AI Model Inference API version to use for this request.<br>`latest` if not otherwise specified. |
24
+
| api-version | query | No || The explicit Azure AI Foundry Models API version to use for this request.<br>`latest` if not otherwise specified. |
25
25
26
26
### Request Header
27
27
@@ -102,7 +102,7 @@ Transcribes audio into the input language.
102
102
| Name | In | Required | Type | Description |
103
103
|------|------|----------|------|-----------|
104
104
| endpoint | path | Yes | string<br>url | Supported Azure OpenAI endpoints (protocol and hostname, for example: `https://aoairesource.openai.azure.com`. Replace "aoairesource" with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com |
105
-
| api-version | query | No || The explicit Azure AI Model Inference API version to use for this request.<br>`latest` if not otherwise specified. |
105
+
| api-version | query | No || The explicit Azure AI Foundry Models API version to use for this request.<br>`latest` if not otherwise specified. |
106
106
107
107
### Request Header
108
108
@@ -218,7 +218,7 @@ Creates a chat completion.
218
218
| Name | In | Required | Type | Description |
219
219
|------|------|----------|------|-----------|
220
220
| endpoint | path | Yes | string<br>url | Supported Azure OpenAI endpoints (protocol and hostname, for example: `https://aoairesource.openai.azure.com`. Replace "aoairesource" with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com |
221
-
| api-version | query | No || The explicit Azure AI Model Inference API version to use for this request.<br>`latest` if not otherwise specified. |
221
+
| api-version | query | No || The explicit Azure AI Foundry Models API version to use for this request.<br>`latest` if not otherwise specified. |
222
222
223
223
### Request Header
224
224
@@ -355,7 +355,7 @@ Creates a completion.
355
355
| Name | In | Required | Type | Description |
356
356
|------|------|----------|------|-----------|
357
357
| endpoint | path | Yes | string<br>url | Supported Azure OpenAI endpoints (protocol and hostname, for example: `https://aoairesource.openai.azure.com`. Replace "aoairesource" with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com |
358
-
| api-version | query | No || The explicit Azure AI Model Inference API version to use for this request.<br>`latest` if not otherwise specified. |
358
+
| api-version | query | No || The explicit Azure AI Foundry Models API version to use for this request.<br>`latest` if not otherwise specified. |
359
359
360
360
### Request Header
361
361
@@ -468,7 +468,7 @@ Creates an embedding vector representing the input text.
468
468
| Name | In | Required | Type | Description |
469
469
|------|------|----------|------|-----------|
470
470
| endpoint | path | Yes | string<br>url | Supported Azure OpenAI endpoints (protocol and hostname, for example: `https://aoairesource.openai.azure.com`. Replace "aoairesource" with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com |
471
-
| api-version | query | No || The explicit Azure AI Model Inference API version to use for this request.<br>`latest` if not otherwise specified. |
471
+
| api-version | query | No || The explicit Azure AI Foundry Models API version to use for this request.<br>`latest` if not otherwise specified. |
472
472
473
473
### Request Header
474
474
@@ -706,7 +706,7 @@ POST {endpoint}/openai/v1/images/generations?api-version=preview
706
706
| Name | In | Required | Type | Description |
707
707
|------|------|----------|------|-----------|
708
708
| endpoint | path | Yes | string<br>url | Supported Azure OpenAI endpoints (protocol and hostname, for example: `https://aoairesource.openai.azure.com`. Replace "aoairesource" with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com |
709
-
| api-version | query | No || The explicit Azure AI Model Inference API version to use for this request.<br>`latest` if not otherwise specified. |
709
+
| api-version | query | No || The explicit Azure AI Foundry Models API version to use for this request.<br>`latest` if not otherwise specified. |
710
710
711
711
### Request Header
712
712
@@ -846,7 +846,7 @@ Creates a model response.
846
846
| Name | In | Required | Type | Description |
847
847
|------|------|----------|------|-----------|
848
848
| endpoint | path | Yes | string<br>url | Supported Azure OpenAI endpoints (protocol and hostname, for example: `https://aoairesource.openai.azure.com`. Replace "aoairesource" with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com |
849
-
| api-version | query | No || The explicit Azure AI Model Inference API version to use for this request.<br>`latest` if not otherwise specified. |
849
+
| api-version | query | No || The explicit Azure AI Foundry Models API version to use for this request.<br>`latest` if not otherwise specified. |
850
850
851
851
### Request Header
852
852
@@ -930,7 +930,7 @@ Retrieves a model response with the given ID.
930
930
| Name | In | Required | Type | Description |
931
931
|------|------|----------|------|-----------|
932
932
| endpoint | path | Yes | string<br>url | Supported Azure OpenAI endpoints (protocol and hostname, for example: `https://aoairesource.openai.azure.com`. Replace "aoairesource" with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com |
933
-
| api-version | query | No || The explicit Azure AI Model Inference API version to use for this request.<br>`latest` if not otherwise specified. |
933
+
| api-version | query | No || The explicit Azure AI Foundry Models API version to use for this request.<br>`latest` if not otherwise specified. |
934
934
| response_id | path | Yes | string ||
935
935
| include[]| query | No | array ||
936
936
@@ -974,7 +974,7 @@ Deletes a response by ID.
974
974
| Name | In | Required | Type | Description |
975
975
|------|------|----------|------|-----------|
976
976
| endpoint | path | Yes | string<br>url | Supported Azure OpenAI endpoints (protocol and hostname, for example: `https://aoairesource.openai.azure.com`. Replace "aoairesource" with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com |
977
-
| api-version | query | No || The explicit Azure AI Model Inference API version to use for this request.<br>`latest` if not otherwise specified. |
977
+
| api-version | query | No || The explicit Azure AI Foundry Models API version to use for this request.<br>`latest` if not otherwise specified. |
978
978
| response_id | path | Yes | string ||
979
979
980
980
### Request Header
@@ -1017,7 +1017,7 @@ Returns a list of input items for a given response.
1017
1017
| Name | In | Required | Type | Description |
1018
1018
|------|------|----------|------|-----------|
1019
1019
| endpoint | path | Yes | string<br>url | Supported Azure OpenAI endpoints (protocol and hostname, for example: `https://aoairesource.openai.azure.com`. Replace "aoairesource" with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com |
1020
-
| api-version | query | No || The explicit Azure AI Model Inference API version to use for this request.<br>`latest` if not otherwise specified. |
1020
+
| api-version | query | No || The explicit Azure AI Foundry Models API version to use for this request.<br>`latest` if not otherwise specified. |
1021
1021
| response_id | path | Yes | string ||
1022
1022
| limit | query | No | integer | A limit on the number of objects to be returned. Limit can range between 1 and 100, and the<br>default is 20. |
1023
1023
| order | query | No | string<br>Possible values: `asc`, `desc`| Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and`desc`<br>for descending order. |
@@ -1062,7 +1062,7 @@ POST {endpoint}/openai/v1/video/generations/jobs?api-version=preview
1062
1062
| Name | In | Required | Type | Description |
1063
1063
|------|------|----------|------|-----------|
1064
1064
| endpoint | path | Yes | string<br>url | Supported Azure OpenAI endpoints (protocol and hostname, for example: `https://aoairesource.openai.azure.com`. Replace "aoairesource" with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com |
1065
-
| api-version | query | No || The explicit Azure AI Model Inference API version to use for this request.<br>`latest` if not otherwise specified. |
1065
+
| api-version | query | No || The explicit Azure AI Foundry Models API version to use for this request.<br>`latest` if not otherwise specified. |
1066
1066
1067
1067
### Request Header
1068
1068
@@ -1149,7 +1149,7 @@ GET {endpoint}/openai/v1/video/generations/jobs?api-version=preview
1149
1149
| Name | In | Required | Type | Description |
1150
1150
|------|------|----------|------|-----------|
1151
1151
| endpoint | path | Yes | string<br>url | Supported Azure OpenAI endpoints (protocol and hostname, for example: `https://aoairesource.openai.azure.com`. Replace "aoairesource" with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com |
1152
-
| api-version | query | No || The explicit Azure AI Model Inference API version to use for this request.<br>`latest` if not otherwise specified. |
1152
+
| api-version | query | No || The explicit Azure AI Foundry Models API version to use for this request.<br>`latest` if not otherwise specified. |
1153
1153
| before | query | No | string ||
1154
1154
| after | query | No | string ||
1155
1155
| limit | query | Yes | integer ||
@@ -1195,7 +1195,7 @@ GET {endpoint}/openai/v1/video/generations/jobs/{job-id}?api-version=preview
1195
1195
| Name | In | Required | Type | Description |
1196
1196
|------|------|----------|------|-----------|
1197
1197
| endpoint | path | Yes | string<br>url | Supported Azure OpenAI endpoints (protocol and hostname, for example: `https://aoairesource.openai.azure.com`. Replace "aoairesource" with your Azure OpenAI resource name). https://{your-resource-name}.openai.azure.com |
1198
-
| api-version | query | No || The explicit Azure AI Model Inference API version to use for this request.<br>`latest` if not otherwise specified. |
1198
+
| api-version | query | No || The explicit Azure AI Foundry Models API version to use for this request.<br>`latest` if not otherwise specified. |
1199
1199
| job-id | path | Yes | string | The ID of the video generation job to use for the Azure OpenAI request. |
| best_of | integer | Generates `best_of` completions server-side and returns the "best" (the one with the highest log probability per token). Results cannot be streamed.<br><br>When used with `n`, `best_of` controls the number of candidate completions and `n` specifies how many to return â€"`best_of` must be greater than `n`.<br><br>**Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for `max_tokens` and `stop`. | No | 1 |
1977
+
| best_of | integer | Generates `best_of` completions server-side and returns the "best" (the one with the highest log probability per token). Results cannot be streamed.<br><br>When used with `n`, `best_of` controls the number of candidate completions and `n` specifies how many to return –`best_of` must be greater than `n`.<br><br>**Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for `max_tokens` and `stop`. | No | 1 |
1978
1978
| echo | boolean | Echo back the prompt in addition to the completion | No | False |
1979
1979
| frequency_penalty | number | Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. | No | 0 |
1980
1980
| logit_bias | object | Modify the likelihood of specified tokens appearing in the completion.<br><br>Accepts a JSON object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.<br><br>As an example, you can pass `{"50256": -100}` to prevent the <|endoftext|> token from being generated. | No | None |
0 commit comments