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
update bicep and readme to remove deployment name (#9)
* change bicep files and readme to use AZURE_AI_AGENT_MODEL_NAME instead of AZURE_AI_CHAT_MODEL_NAME
* update bicep files to remove references to AZURE_AI_CHAT_DEPLOYMENT_NAME and have the deployment names default to the model name
* add Quota Recommendations section to the readme
The default for the model capacity in deployment is 50k tokens. For optimal performance, it is recommended to increase to 100k tokens. You can change the capacity by following the steps in [setting capacity and deployment SKU](docs/deploy_customization.md#customizing-model-deployments).
36
+
37
+
* Navigate to the [Azure AI Foundry Portal](https://ai.azure.com/)
38
+
* Select the AI Project you are using for this template if you are not already in the project.
39
+
* Select Management center from the bottom left navigation menu
40
+
* Select Quota, click the GlobalStandard dropdown and select the model and region you are using for this accelerator to see your available quota. Please note GPT-4o mini and text-embedding-ada-002 are used as default.
41
+
* Request more quota or delete any unused model deployments as needed.
33
42
34
43
#### Bringing an existing AI project resource
35
44
@@ -86,14 +95,12 @@ At this point you could make changes to the code if required. However, no change
86
95
87
96
#### Configure your Agent (optional)
88
97
<!-- TODO where do we want this? probably after downloading the code -->
89
-
For options on customizing the deployment to disable resources, change resource names, or customize the models, you can follow these steps in [deployment customizations](docs/deploy_customization.md) now.
90
-
91
-
If you want to personalize your agent, you can change the default configuration for your agent. This can include changing the model, adding tools, and uploading files to the agent. More information can be found in [Customizing Model Deployments](docs/deploy_customization.md#customizing-model-deployments).
98
+
If you want to personalize your agent, you can change the default configuration for your agent. This can include changing the model, adding tools, and uploading files to the agent. For more information on the Azure OpenAI models and non-Microsoft models that can be used in your deployment, view the [list of models supported by Azure AI Agent Service](https://learn.microsoft.com/azure/ai-services/agents/concepts/model-region-support).
92
99
93
-
To change the model, set the following environment variables:
100
+
To specify the model (e.g. gpt-4o-mini, gpt-4o) that is deployed for the agent when `azd up` is called, set the following environment variables:
Change the chat model format (either OpenAI or Microsoft):
52
+
Change the agent model name:
53
53
54
54
```shell
55
-
azd env setAZURE_AI_CHAT_MODEL_FORMAT Microsoft
55
+
azd env setAZURE_AI_AGENT_MODEL_NAME gpt-4o-mini
56
56
```
57
57
58
-
Change the chat model name:
58
+
Set the version of the agent model:
59
59
60
60
```shell
61
-
azd env set AZURE_AI_CHAT_MODEL_NAME Phi-3.5-MoE-instruct
62
-
```
63
-
64
-
Set the version of the chat model:
65
-
66
-
```shell
67
-
azd env set AZURE_AI_CHAT_MODEL_VERSION 2
61
+
azd env set AZURE_AI_AGENT_MODEL_VERSION 2024-07-18
68
62
```
69
63
70
64
### Setting capacity and deployment SKU
71
65
72
66
For quota regions, you may find yourself needing to modify the default capacity and deployment SKU. The default tokens per minute deployed in this template is 50,000.
73
67
74
-
Change the capacity (in thousands of tokens per minute) of the chat deployment:
68
+
Change the capacity (in thousands of tokens per minute) of the agent deployment:
75
69
76
70
```shell
77
-
azd env setAZURE_AI_CHAT_DEPLOYMENT_CAPACITY 50
71
+
azd env setAZURE_AI_AGENT_DEPLOYMENT_CAPACITY 50
78
72
```
79
73
80
-
Change the SKU of the chat deployment:
74
+
Change the SKU of the agent deployment:
81
75
82
76
```shell
83
-
azd env setAZURE_AI_CHAT_DEPLOYMENT_SKU Standard
77
+
azd env setAZURE_AI_AGENT_DEPLOYMENT_SKU Standard
84
78
```
85
79
86
80
Change the capacity (in thousands of tokens per minute) of the embeddings deployment:
0 commit comments