Page Comparison

- [Introduction](#introduction)
  - [Configuration Philosophy](#configuration-philosophy)
- [Prerequisites](#prerequisites)
- [Determine Configuration Values](#determine-configuration-values)
- [Configure the Azure OpenAI Models](#configure-the-azure-openai-models)

# Introduction
This guide describes how to configure Azure to generateproduce the prerequisitesvalues required to enableconfigure the Ayfie Personal Assistant feature.

## Configuration Philosophy
As we will learn in the next section, one is to set Personal Assistant up with three or four models: an Embeddings model, a Main model, a High Quality model, and optionally, a High Quality Plus model. The Embeddings model is always the same and the two High Quality models are normally easy to determine; they are whichever models that, at the time, are considered to produce the most correct and accurate responses to user prompts. Deciding which model to use as the Main model can be a bit trickier. It is assumed that one already has an Azure subscription and access to Azure OpenAI as described in One may want to select a model with a lower cost or, if the model to be used as the High Quality models is a bit slow, then one may opt for a model with a faster response time as the Main model.

This is further complicated by the fact that various factors, such as pricing and model performance, are subject to change over time. New models or new versions of existing models are also constantly being released. This means that the conditions that led to one configuration at installation time might be very different a few months later. For an overview of released models and their regional availability, as well as links to pricing information, check out [Azure OpenAI Service Documentation](https://learn.microsoft.com/en-us/azure/ai-services/openai/overview).

The configuration recommendation provided in the following section reflects the current advantages of GPT-4o mini, which include its lower cost and faster response time over the more correct and accurate GPT-4 and GPT-4o models. We advise periodically reviewing this documentation to determine if evolving conditions warrant a reconfiguration.

# Prerequisites
These are the prerequisites that must be fulfilled before setting up Personal Assistant:
- **Obtain an Azure Subscription** - One must have an active Azure subscription. If one don’t have one, one can sign up for an Azure subscription on the [Azure website](https://azure.microsoft.com/en-us/).
- **Get Azure OpenAI Approval** - The Azure subscription needs to be approved for [Azure Open AI](https://learn.microsoft.com/en-us/azure/ai-services/openai/overview). How to do that is described in [Ayfie Personal Assistant - How to Request Access to the Azure OpenAI Service](https://ayfie-dev.atlassian.net/wiki/spaces/SAGA/pages/3443523634/Ayfie+Personal+Assistant+-+How+to+Request+Access+to+the+Azure+OpenAI+Service).

 Once the prerequisites are above have been completed, one can then start configuring Ayfie Personal Assistant.

# Determine Configuration Values
One needs to providedetermine the following entitiesconfiguration values:
- **Deployment Name**
- **API Address**
- **API Key**

for each of the following 3 Azure OpenAI models:
- **Main Model**
- **High Quality Model**
- **Embeddings Model**

and optionally for the following Azure OpenAI model:
- **High Quality Plus Model**

The intended difference between the Main Model, High Quality Model and the High Quality Plus Model is the quality of the chat responses when users toggle between the twothree in the Personal Assistant UI. The normalrecommended approach isat to set the Maintime Modelof up with GPT-3.5 and the High Quality Model with GPT-4. However, it is fully possibly this writing, is to set boththe ofMain themModel up with for instance GPT 3.5 which would mean that toggling between the two in the UI would have no effect

There are two GPT-4 alternatives for *GPT-4o mini*, the High Quality model:Model Thewith lightweight model *gptGPT-4* that is suitable for resource-constrained scenarios where cost and responseHigh timeQuality arePlus critical,Model or alternatively the more resource rich *gpt-4-32k* model that offers higher performance, accuracy, and the ability to handle larger sets of documents. Consider your specific requirements, performance needs, and cost constraints to choose the most appropriate modelwith *GPT-4o* and to set either the High Quality Model or High Quality Plus Model as the default model in the UI.

The thirdlast model is for creating embeddings. Embeddings are numerical representations of words that are learned from large amounts of text data. Currently, there is only one supported modelonly the *text-embedding-ada-002* model should be used.

Each of the 34 models requires an API address and an API key. However, unless one chose to spread the models across geographical regions, all 34 models will be reached via the same API address and ancan use the same API key.

GivenThese are the limitedcurrently optionsrecommended forsettings:
each- setting,Main theModel configurationDeployment of the prerequisites in Azure described in the next section, has a very predictable outcome:
- Main Name: ***gpt-4o-mini*** (only available in some regions)
- High Quality Model Deployment Name: ***gpt-35-turbo4***
- High Quality Plus Model Deployment Name: ***gpt-44o*** or **gpt-4-32k** (only available in some regions)
- Embeddings Model Deployment Name: ***text-embedding-ada-002***
- API Address: *the same one for all*
three
- API Key: *the same one for all*
three

# Configure the Azure OpenAI Models
For more information, consult [Azure OpenAI Service Documentation](https://learn.microsoft.com/en-us/azure/ai-services/openai/overview).

Follow these steps to set up the deployments for the 3 Azure OpenAI models:
- Log in to the Azure portal at [portal.azure.com](https://portal.azure.com/)
- Make sure the account that is logged in has at least one subscription
- Go to *Azure OpenAI*
  - Click *Create*, to create a Resource
    - In *Project Details*, select *Subscription*
    - In *Project Details*, select *Resource Group*
    - In *Instance Details*, select *Region*.  Not all models are available in all regions, consult with [Azure OpenAI Service models](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models) for availability. EU country customers should for legal reason select a region that is within EU. Choose a region that has the models one wants to use *Sweden Central* would normally be a good choice as this region currently offers most models. Please note that the standalone Personal Assistant purchased from Azure Marketplace and the Locator integrated version addressed in this documentation, compete for the same token per minutes quotas if they share both subscription and region. Please contact Ayfie Support for advise on which region to select in case of quota conflicts.
    - In *Instance Details*, set the *Name*
    - In *Instance Details*, select *Pricing Tier*
    - Click *Next* to go to the *Network* tab
    - In *Type*, select *All networks, including internet can access this resource.*
    - Click *Next* to go to the *Tags* tab
    - Click *Next* to go to the *Review + submit* tab
    - Click *Create*
  - When Resource is created, select the resource in *Azure OpenAI*
  - Click *Click here to view endpoints*.Keys and Endpoint* in the left menu under *Resource Management*
    - **Copy the value of *Language APIsEndpoint*, it will be required later as the API Address**
    - **Copy the value of *KEY 1*, it will be required later as the API Key** (optionally *KEY 2*, both keys are valid)
  - Click *Go to Azure OpenAI StudioModel deployments* in the left menu under *Resource Management*
  - Click *Manage Deployments* (this will open a new portal). This  - Click *Management->Deployments*guide is based on the old look. Make sure to switch to it in the top menu.
  - Click *Create new deployment* to create Main model
    - Select the model (*gpt-4o-mini* recommended)
    - Select (typicallythe Model Version (Set to *gpt2024-35-turbo07-18 (Default)*)
    - Set the *Deployment Name* (must be same as model name)
      - **Copy the *Deployment Name*, it will be required later**
    - InSet *AdvancedDeployment Options*, setType* to Standard (will ensure that the data stays and is processed within the selected region)
    - Set *Tokens per Minute Rate Limit (thousands)* to the maximum value
    - Set *Content Filter* to the value.appropriate value or use the default value
  - Click *Create new deployment* to create High Quality model
    - Select the model (*gpt-4* recommended)
    - Select the Model Version (*1106-Preview* recommended)
    - Set the *Deployment Name* (must be same as model name).
      - **Copy the *Deployment Name*, it will be required later**
    - InSet *AdvancedDeployment Options*, setType* to Standard (will ensure that the data stays and is processed within the selected region)
    - Set *Tokens per Minute Rate Limit (thousands)* to the maximum value
    - Set *Content value.Filter* to the appropriate value or use the default value
  - Click *Create new deployment* to create Embeddings model
    - Select the model (must be *text-embedding-ada-002*)
    - Select the Model Version (*2 (Default)* recommended)
    - Set the *Deployment Name* (must be same as model name)
      - **Copy the *Deployment Name*, it will be required later**
    - Set *Deployment Type* to Standard (will ensure that the data stays and is processed within the selected region)
    - Set *Tokens per Minute Rate Limit (thousands)* to the maximum value
    - Set *Content Filter* to the appropriate value or use the default value.
  - If one are to configure the High Quality Plus Model, click *Create new deployment* to create the High Quality Plus model
    - Select the model (*gpt-4o* recommended)
   - In *Advanced Options*, set - Select the Model Version (*2024-05-13* recommended)
    - Set the *Deployment Name* (must be same as model name).
      - **Copy the *Deployment Name*, it will be required later**
    - Set *Deployment Type* to Standard (will ensure that the data stays and is processed within the selected region)
    - Set *Tokens per Minute Rate Limit (in thousands)* to the maximum value
    - Set *Content Filter* to the appropriate value or use the default value