fix: Updates to change the Azure OpenAI model from gpt-35-turbo to gpt-4o

.env.sample

@@ -22,8 +22,8 @@ AZURE_SEARCH_DATASOURCE_NAME=
 # Azure OpenAI for generating the answer and computing the embedding of the documents
 AZURE_OPENAI_RESOURCE=
 AZURE_OPENAI_API_KEY=
-AZURE_OPENAI_MODEL=gpt-35-turbo
-AZURE_OPENAI_MODEL_NAME=gpt-35-turbo
+AZURE_OPENAI_MODEL=gpt-4o
+AZURE_OPENAI_MODEL_NAME=gpt-4o
 AZURE_OPENAI_EMBEDDING_MODEL=text-embedding-ada-002
 AZURE_OPENAI_TEMPERATURE=0
 AZURE_OPENAI_TOP_P=1.0

README.md

@@ -194,10 +194,10 @@ Select either "PostgreSQL" or "Cosmos DB":
 
 When Deployment is complete, follow steps in [Set Up Authentication in Azure App Service](./docs/azure_app_service_auth_setup.md) to add app authentication to your web app running on Azure App Service
 
-**Note**: The default configuration deploys an OpenAI Model "gpt-35-turbo" with version 0613. However, not all
-locations support this version. If you're deploying to a location that doesn't support version 0613, you'll need to
+**Note**: The default configuration deploys an OpenAI Model "gpt-4o" with version 2024-05-13. However, not all
+locations support this version. If you're deploying to a location that doesn't support version 2024-05-13, you'll need to
 switch to a lower version. To find out which versions are supported in different regions, visit the
-[GPT-35 Turbo Model Availability](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#gpt-35-turbo-model-availability) page.
+[GPT-4o Model Availability](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models?tabs=global-standard%2Cstandard-chat-completions#global-standard-model-availability) page.
 
 ### Testing the deployment
 1. Navigate to the admin site, where you can upload documents. It will be located at:

code/backend/batch/utilities/helpers/env_helper.py

@@ -174,10 +174,10 @@ def __load_config(self, **kwargs) -> None:
         else:
             # Otherwise, fallback to individual environment variables
             self.AZURE_OPENAI_MODEL = os.getenv(
-                "AZURE_OPENAI_MODEL", "gpt-35-turbo-16k"
+                "AZURE_OPENAI_MODEL", "gpt-4o"
             )
             self.AZURE_OPENAI_MODEL_NAME = os.getenv(
-                "AZURE_OPENAI_MODEL_NAME", "gpt-35-turbo-16k"
+                "AZURE_OPENAI_MODEL_NAME", "gpt-4o"
             )
 
         self.AZURE_OPENAI_VISION_MODEL = os.getenv("AZURE_OPENAI_VISION_MODEL", "gpt-4")

code/tests/functional/tests/backend_api/default/test_conversation.py

@@ -65,7 +65,7 @@ def completions_mocking(httpserver: HTTPServer, app_config: AppConfig):
             "id": "chatcmpl-6v7mkQj980V1yBec6ETrKPRqFjNw9",
             "object": "chat.completion",
             "created": 1679072642,
-            "model": "gpt-35-turbo",
+            "model": "gpt-4o",
             "usage": {
                 "prompt_tokens": 40,
                 "completion_tokens": 50,

code/tests/functional/tests/backend_api/default/test_post_prompt_tool.py

@@ -100,7 +100,7 @@ def completions_mocking(httpserver: HTTPServer, app_config: AppConfig):
             "id": "chatcmpl-6v7mkQj980V1yBec6ETrKPRqFjNw9",
             "object": "chat.completion",
             "created": 1679072642,
-            "model": "gpt-35-turbo",
+            "model": "gpt-4o",
             "usage": {
                 "prompt_tokens": 40,
                 "completion_tokens": 50,
@@ -132,7 +132,7 @@ def test_post_responds_successfully_when_not_filtered(
             "id": "chatcmpl-6v7mkQj980V1yBec6ETrKPRqFjNw9",
             "object": "chat.completion",
             "created": 1679072642,
-            "model": "gpt-35-turbo",
+            "model": "gpt-4o",
             "usage": {
                 "prompt_tokens": 40,
                 "completion_tokens": 50,
@@ -193,7 +193,7 @@ def test_post_responds_successfully_when_filtered(
             "id": "chatcmpl-6v7mkQj980V1yBec6ETrKPRqFjNw9",
             "object": "chat.completion",
             "created": 1679072642,
-            "model": "gpt-35-turbo",
+            "model": "gpt-4o",
             "usage": {
                 "prompt_tokens": 40,
                 "completion_tokens": 50,
@@ -254,7 +254,7 @@ def test_post_makes_correct_call_to_openai_from_post_prompt_tool(
             "id": "chatcmpl-6v7mkQj980V1yBec6ETrKPRqFjNw9",
             "object": "chat.completion",
             "created": 1679072642,
-            "model": "gpt-35-turbo",
+            "model": "gpt-4o",
             "usage": {
                 "prompt_tokens": 40,
                 "completion_tokens": 50,

code/tests/functional/tests/backend_api/integrated_vectorization_custom_conversation/test_iv_question_answer_tool.py

@@ -63,7 +63,7 @@ def completions_mocking(httpserver: HTTPServer, app_config: AppConfig):
             "id": "chatcmpl-6v7mkQj980V1yBec6ETrKPRqFjNw9",
             "object": "chat.completion",
             "created": 1679072642,
-            "model": "gpt-35-turbo",
+            "model": "gpt-4o",
             "usage": {
                 "prompt_tokens": 40,
                 "completion_tokens": 50,

docs/LOCAL_DEPLOYMENT.md

@@ -191,8 +191,8 @@ Execute the above [shell command](#L81) to run the function locally. You may nee
 |AZURE_SEARCH_USE_INTEGRATED_VECTORIZATION ||Whether to use [Integrated Vectorization](https://learn.microsoft.com/en-us/azure/search/vector-search-integrated-vectorization)|
 |AZURE_OPENAI_RESOURCE||the name of your Azure OpenAI resource|
 |AZURE_OPENAI_MODEL||The name of your model deployment|
-|AZURE_OPENAI_MODEL_NAME|gpt-35-turbo|The name of the model|
-|AZURE_OPENAI_MODEL_VERSION|0613|The version of the model to use|
+|AZURE_OPENAI_MODEL_NAME|gpt-4o|The name of the model|
+|AZURE_OPENAI_MODEL_VERSION|2024-05-13|The version of the model to use|
 |AZURE_OPENAI_API_KEY||One of the API keys of your Azure OpenAI resource|
 |AZURE_OPENAI_EMBEDDING_MODEL|text-embedding-ada-002|The name of your Azure OpenAI embeddings model deployment|
 |AZURE_OPENAI_EMBEDDING_MODEL_NAME|text-embedding-ada-002|The name of the embeddings model (can be found in Azure AI Studio)|

docs/TEAMS_LOCAL_DEPLOYMENT.md

@@ -65,7 +65,7 @@ Or use the [Azure Functions VS Code extension](https://marketplace.visualstudio.
 |AZURE_SEARCH_FILTER||Filter to apply to search queries.|
 |AZURE_OPENAI_RESOURCE||the name of your Azure OpenAI resource|
 |AZURE_OPENAI_MODEL||The name of your model deployment|
-|AZURE_OPENAI_MODEL_NAME|gpt-35-turbo|The name of the model|
+|AZURE_OPENAI_MODEL_NAME|gpt-4o|The name of the model|
 |AZURE_OPENAI_API_KEY||One of the API keys of your Azure OpenAI resource|
 |AZURE_OPENAI_EMBEDDING_MODEL|text-embedding-ada-002|The name of you Azure OpenAI embeddings model deployment|
 |AZURE_OPENAI_TEMPERATURE|0|What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. A value of 0 is recommended when using your data.|

docs/model_configuration.md

@@ -15,11 +15,11 @@ This document outlines the necessary steps and configurations required for setti
 
 ### LLM
 - `AZURE_OPENAI_MODEL`: The Azure OpenAI Model Deployment Name
-    - example: `my-gpt-35-turbo-16k`
+    - example: `my-gpt-4o`
 - `AZURE_OPENAI_MODEL_NAME`: The Azure OpenAI Model Name
-    - example: `gpt-35-turbo-16k`
+    - example: `gpt-4o`
 - `AZURE_OPENAI_MODEL_VERSION`: The Azure OpenAI Model Version
-    - example: `0613`
+    - example: `2024-05-13`
 - `AZURE_OPENAI_MODEL_CAPACITY`: The Tokens per Minute Rate Limit (thousands)
     - example: `30`
 

infra/main.bicep

@@ -125,13 +125,13 @@ param azureOpenAIResourceName string = 'openai-${resourceToken}'
 param azureOpenAISkuName string = 'S0'
 
 @description('Azure OpenAI Model Deployment Name')
-param azureOpenAIModel string = 'gpt-35-turbo-16k'
+param azureOpenAIModel string = 'gpt-4o'
 
 @description('Azure OpenAI Model Name')
-param azureOpenAIModelName string = 'gpt-35-turbo-16k'
+param azureOpenAIModelName string = 'gpt-4o'
 
 @description('Azure OpenAI Model Version')
-param azureOpenAIModelVersion string = '0613'
+param azureOpenAIModelVersion string = '2024-05-13'
 
 @description('Azure OpenAI Model Capacity - See here for more info  https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/quota')
 param azureOpenAIModelCapacity int = 30

infra/main.bicepparam

@@ -32,9 +32,9 @@ param azureSearchOffsetColumn = readEnvironmentVariable('AZURE_SEARCH_OFFSET_COL
 
 // OpenAI parameters
 param azureOpenAIApiVersion = readEnvironmentVariable('AZURE_OPENAI_API_VERSION', '2024-02-01')
-param azureOpenAIModel = readEnvironmentVariable('AZURE_OPENAI_MODEL', 'gpt-35-turbo-16k')
-param azureOpenAIModelName = readEnvironmentVariable('AZURE_OPENAI_MODEL_NAME', 'gpt-35-turbo-16k')
-param azureOpenAIModelVersion = readEnvironmentVariable('AZURE_OPENAI_MODEL_VERSION', '0613')
+param azureOpenAIModel = readEnvironmentVariable('AZURE_OPENAI_MODEL', 'gpt-4o')
+param azureOpenAIModelName = readEnvironmentVariable('AZURE_OPENAI_MODEL_NAME', 'gpt-4o')
+param azureOpenAIModelVersion = readEnvironmentVariable('AZURE_OPENAI_MODEL_VERSION', '2024-05-13')
 param azureOpenAIModelCapacity = int(readEnvironmentVariable('AZURE_OPENAI_MODEL_CAPACITY', '30'))
 param useAdvancedImageProcessing = bool(readEnvironmentVariable('USE_ADVANCED_IMAGE_PROCESSING', 'false'))
 param advancedImageProcessingMaxImages = int(readEnvironmentVariable('ADVANCED_IMAGE_PROCESSING_MAX_IMAGES', '1'))