fix: Updated Client Advisor to use gpt-4o-mini model

[Harsh-Microsoft]

Purpose

This pull request includes several updates to the ClientAdvisor/AzureFunction and related deployment files. The changes primarily focus on updating dependencies, refactoring code for better readability and maintainability, and modifying deployment configurations.

Code Refactoring and Improvements:

• Replaced Chat Completions API with Assistants API in function_app.py.
• Modified the greeting method in ChatWithDataPlugin to use input directly instead of splitting it, and updated the function name to GreetingsResponse.
• Added error handling in get_answers_from_calltranscripts to catch exceptions and return error messages.

Dependency Updates:

• Updated openai version to 1.64.0 and semantic_kernel version to 1.21.3 in requirements.txt.

Deployment Configuration Changes:

• Changed the Azure OpenAI model name from gpt-4 to gpt-4o-mini in multiple deployment files (deploy_app_service.bicep, deploy_azure_function.bicep, deploy_azure_open_ai.bicep, main.bicep). [1] [2] [3] [4]
• Restricted Azure OpenAI location to specific regions where the gpt-4o-mini model is available in main.bicep.

Prompt and Response Adjustments:

• Updated various prompt messages to improve clarity and guidance in function_app.py and main.bicep. [1] [2] [3] [4]

Does this introduce a breaking change?

• Yes
• No

Golden Path Validation

• I have tested the primary workflows (the "golden path") to ensure they function correctly without errors.

Deployment Validation

• I have validated the deployment process successfully and all services are running as expected with this change.

What to Check

Verify that the following are valid

• ...

Other Information