Skip to content

Commit efe4d10

Browse files
authored
Merge pull request #242 from microsoft/aitemplate_updates
fix: update yaml, readme and bicep
2 parents 07eb495 + c6d572b commit efe4d10

File tree

5 files changed

+40
-40
lines changed

5 files changed

+40
-40
lines changed

README.md

Lines changed: 9 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -70,14 +70,14 @@ Please check the link [Azure Products by Region](https://azure.microsoft.com/en-
7070

7171
- Embedding model capacity
7272

73-
### Quota Recommendations
74-
- Please deploy with minimum **30k tokens**.
75-
- For optimal performance, it is recommended to increase token to **100K**
76-
- You can also view the Quotas tab in [Azure OpenAI studio](https://oai.azure.com/)
77-
to understand how much capacity you have.
78-
79-
![image](./docs/Images/ReadMe/quotaImage.png)
80-
73+
### [Optional]: Quota Recommendations
74+
- The default for the GPT model capacity in deployment is **30k tokens**.
75+
- For optimal performance, it is recommended to increase to **100k tokens**.
76+
- Navigate to the [Azure AI Foundry portal](https://ai.azure.com/)
77+
- Select the AI Project you are using for this accelerator if you are not already in the project.
78+
- Select `Management center` from the bottom left navigation menu
79+
- Select `Quota`, click the `GlobalStandard` dropdown and select the GPT model and region you are using for this accelerator to see your available quota.
80+
- Request more quota or delete any unused model deployments as needed.
8181

8282

8383
### **Options**
@@ -211,7 +211,7 @@ azd env set AZURE_ENV_MODEL_NAME gpt-4o-mini
211211
Change the Model Capacity (choose a number based on available GPT model capacity in your subscription)
212212
213213
```shell
214-
azd env set AZURE_ENV_MODEL_CAPACITY 100
214+
azd env set AZURE_ENV_MODEL_CAPACITY 30
215215
```
216216
217217
Change the Embedding Model

azure.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@
44
environment:
55
name: conversation-knowledge-mining
66
location: eastus
7-
7+
name: conversation-knowledge-mining
88
metadata:
99
1010

infra/main.bicep

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -50,7 +50,7 @@ var gptModelVersion = '2024-02-15-preview'
5050
@description('Capacity of the GPT deployment:')
5151
// You can increase this, but capacity is limited per model/region, so you will get errors if you go over
5252
// https://learn.microsoft.com/en-us/azure/ai-services/openai/quotas-limits
53-
param gptDeploymentCapacity int = 100
53+
param gptDeploymentCapacity int = 30
5454

5555
@minLength(1)
5656
@description('Name of the Text Embedding model to deploy:')

infra/main.bicepparam

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -5,6 +5,6 @@ param contentUnderstandingLocation = readEnvironmentVariable('AZURE_ENV_CU_LOCAT
55
param secondaryLocation = readEnvironmentVariable('AZURE_ENV_SECONDARY_LOCATION', 'eastus2')
66
param deploymentType = readEnvironmentVariable('AZURE_ENV_MODEL_DEPLOYMENT_TYPE', 'GlobalStandard')
77
param gptModelName = readEnvironmentVariable('AZURE_ENV_MODEL_NAME', 'gpt-4o-mini')
8-
param gptDeploymentCapacity = int(readEnvironmentVariable('AZURE_ENV_MODEL_CAPACITY', '100'))
8+
param gptDeploymentCapacity = int(readEnvironmentVariable('AZURE_ENV_MODEL_CAPACITY', '30'))
99
param embeddingModel = readEnvironmentVariable('AZURE_ENV_EMBEDDING_MODEL_NAME', 'text-embedding-ada-002')
1010
param embeddingDeploymentCapacity = int(readEnvironmentVariable('AZURE_ENV_EMBEDDING_MODEL_CAPACITY', '80'))

infra/main.json

Lines changed: 28 additions & 28 deletions
Original file line numberDiff line numberDiff line change
@@ -4,8 +4,8 @@
44
"metadata": {
55
"_generator": {
66
"name": "bicep",
7-
"version": "0.31.92.45157",
8-
"templateHash": "11629204665350113499"
7+
"version": "0.33.93.31351",
8+
"templateHash": "10535791601593705798"
99
}
1010
},
1111
"parameters": {
@@ -66,7 +66,7 @@
6666
},
6767
"gptDeploymentCapacity": {
6868
"type": "int",
69-
"defaultValue": 100,
69+
"defaultValue": 30,
7070
"minValue": 10,
7171
"metadata": {
7272
"description": "Capacity of the GPT deployment:"
@@ -129,8 +129,8 @@
129129
"metadata": {
130130
"_generator": {
131131
"name": "bicep",
132-
"version": "0.31.92.45157",
133-
"templateHash": "14275103612814336681"
132+
"version": "0.33.93.31351",
133+
"templateHash": "4123789684929590981"
134134
}
135135
},
136136
"parameters": {
@@ -221,8 +221,8 @@
221221
"metadata": {
222222
"_generator": {
223223
"name": "bicep",
224-
"version": "0.31.92.45157",
225-
"templateHash": "5910651074687744132"
224+
"version": "0.33.93.31351",
225+
"templateHash": "4388214478635448075"
226226
}
227227
},
228228
"parameters": {
@@ -365,8 +365,8 @@
365365
"metadata": {
366366
"_generator": {
367367
"name": "bicep",
368-
"version": "0.31.92.45157",
369-
"templateHash": "15158547531678904427"
368+
"version": "0.33.93.31351",
369+
"templateHash": "7803735516770365352"
370370
}
371371
},
372372
"parameters": {
@@ -1057,8 +1057,8 @@
10571057
"metadata": {
10581058
"_generator": {
10591059
"name": "bicep",
1060-
"version": "0.31.92.45157",
1061-
"templateHash": "8276956277243695834"
1060+
"version": "0.33.93.31351",
1061+
"templateHash": "14620142974675285735"
10621062
}
10631063
},
10641064
"parameters": {
@@ -1241,8 +1241,8 @@
12411241
"metadata": {
12421242
"_generator": {
12431243
"name": "bicep",
1244-
"version": "0.31.92.45157",
1245-
"templateHash": "15083329960647515030"
1244+
"version": "0.33.93.31351",
1245+
"templateHash": "3100365088410602500"
12461246
}
12471247
},
12481248
"parameters": {
@@ -1289,7 +1289,7 @@
12891289
"resources": [
12901290
{
12911291
"copy": {
1292-
"name": "list",
1292+
"name": "database::list",
12931293
"count": "[length(variables('containers'))]"
12941294
},
12951295
"type": "Microsoft.DocumentDB/databaseAccounts/sqlDatabases/containers",
@@ -1447,8 +1447,8 @@
14471447
"metadata": {
14481448
"_generator": {
14491449
"name": "bicep",
1450-
"version": "0.31.92.45157",
1451-
"templateHash": "5779941490382286977"
1450+
"version": "0.33.93.31351",
1451+
"templateHash": "6170430466600233564"
14521452
}
14531453
},
14541454
"parameters": {
@@ -1621,8 +1621,8 @@
16211621
"metadata": {
16221622
"_generator": {
16231623
"name": "bicep",
1624-
"version": "0.31.92.45157",
1625-
"templateHash": "9223261981384212100"
1624+
"version": "0.33.93.31351",
1625+
"templateHash": "509460209037223451"
16261626
}
16271627
},
16281628
"parameters": {
@@ -1704,8 +1704,8 @@
17041704
"metadata": {
17051705
"_generator": {
17061706
"name": "bicep",
1707-
"version": "0.31.92.45157",
1708-
"templateHash": "2728825545778646651"
1707+
"version": "0.33.93.31351",
1708+
"templateHash": "16955379019952955448"
17091709
}
17101710
},
17111711
"parameters": {
@@ -1800,8 +1800,8 @@
18001800
"metadata": {
18011801
"_generator": {
18021802
"name": "bicep",
1803-
"version": "0.31.92.45157",
1804-
"templateHash": "10011942677204719320"
1803+
"version": "0.33.93.31351",
1804+
"templateHash": "7630355864427423039"
18051805
}
18061806
},
18071807
"parameters": {
@@ -2036,8 +2036,8 @@
20362036
"metadata": {
20372037
"_generator": {
20382038
"name": "bicep",
2039-
"version": "0.31.92.45157",
2040-
"templateHash": "8269871966991453242"
2039+
"version": "0.33.93.31351",
2040+
"templateHash": "17601259288614778920"
20412041
}
20422042
},
20432043
"parameters": {
@@ -2287,8 +2287,8 @@
22872287
"metadata": {
22882288
"_generator": {
22892289
"name": "bicep",
2290-
"version": "0.31.92.45157",
2291-
"templateHash": "7009743990995290371"
2290+
"version": "0.33.93.31351",
2291+
"templateHash": "18414416216987649125"
22922292
}
22932293
},
22942294
"parameters": {
@@ -2399,8 +2399,8 @@
23992399
"metadata": {
24002400
"_generator": {
24012401
"name": "bicep",
2402-
"version": "0.31.92.45157",
2403-
"templateHash": "14810546478282650129"
2402+
"version": "0.33.93.31351",
2403+
"templateHash": "2717758861842552802"
24042404
}
24052405
},
24062406
"parameters": {

0 commit comments

Comments
 (0)