Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
25 commits
Select commit Hold shift + click to select a range
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
2 changes: 1 addition & 1 deletion docs/evaluation.md
Original file line number Diff line number Diff line change
Expand Up @@ -164,7 +164,7 @@ from evaluation.metrics.agent_selection import AgentSelectionEvaluator

llm_service = AzureChatCompletion(
deployment_name=os.environ["AZURE_OPENAI_DEPLOYMENT_NAME"],
api_version="2024-12-01-preview",
api_version="2025-04-01-preview",
endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
)

Expand Down
6 changes: 3 additions & 3 deletions infra/main.bicep
Original file line number Diff line number Diff line change
Expand Up @@ -34,13 +34,13 @@ param appPlanName string = ''
param appName string = ''

@description('Gen AI model name and version to deploy')
@allowed(['gpt-4o;2024-08-06', 'gpt-4.1;2025-04-14'])
@allowed(['gpt-4o;2024-08-06','gpt-4.1;2025-04-14','gpt-5;2025-08-07','gpt-5-mini;2025-08-07','gpt-5-nano;2025-08-07','model-router;2025-08-07'])
param model string
@description('Tokens per minute capacity for the model. Units of 1000 (capacity = 100 means 100K tokens per minute)')
param modelCapacity int
// https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/deployment-types
@description('Specify the deployment type of the model. Only allow deployment types where data processing and data storage is within the specified Azure geography.')
@allowed(['Standard', 'DataZoneStandard'])
@description('Specify the deployment type of the model. "Standard" & "DataZoneStandard" only allow data processing and data storage within the specified Azure geography. GPT5 only supports "GlobalStandard" as of now. Please be aware that this can lead to data storage and data processing outside of your azure region!')
@allowed(['DataZoneStandard', 'Standard','GlobalStandard'])
param modelSku string

@description('Location to deploy AI Services')
Expand Down
694 changes: 677 additions & 17 deletions notebooks/end_to_end_run.ipynb

Large diffs are not rendered by default.

60,168 changes: 60,168 additions & 0 deletions notebooks/evaluations/evaluation-gpt4.ipynb

Large diffs are not rendered by default.

143,140 changes: 143,140 additions & 0 deletions notebooks/evaluations/evaluation-gpt5-mini-opt.ipynb

Large diffs are not rendered by default.

4,652 changes: 4,652 additions & 0 deletions notebooks/evaluations/evaluation-gpt5-mini.ipynb

Large diffs are not rendered by default.

39,180 changes: 39,180 additions & 0 deletions notebooks/evaluations/evaluation-gpt5-nano-opt.ipynb

Large diffs are not rendered by default.

78,774 changes: 78,774 additions & 0 deletions notebooks/evaluations/evaluation-gpt5-nano.ipynb

Large diffs are not rendered by default.

3,773 changes: 3,773 additions & 0 deletions notebooks/evaluations/evaluation-gpt5-opt.ipynb

Large diffs are not rendered by default.

47,156 changes: 47,156 additions & 0 deletions notebooks/evaluations/evaluation-gpt5.ipynb

Large diffs are not rendered by default.

2 changes: 1 addition & 1 deletion notebooks/evaluations/evaluation.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -214,7 +214,7 @@
"source": [
"llm_service = AzureChatCompletion(\n",
" deployment_name=os.environ[\"AZURE_OPENAI_DEPLOYMENT_NAME\"],\n",
" api_version=\"2024-12-01-preview\",\n",
" api_version=\"2025-04-01-preview\",\n",
" endpoint=os.environ[\"AZURE_OPENAI_ENDPOINT\"],\n",
")\n",
"\n",
Expand Down
Loading