Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

Table Of Contents:

Table of Contents
stylenone

...

Purpose 

The purpose of this document is to provide a detailed This document aims to deliver a comprehensive overview of AI Services Deployment. The document consists of a detailed process, with It outlines a thorough process that includes procedures for Infrastructure Deployment , and Configuration with using AC5.x Professional.

...

Scope

This process covers aspects of encompasses the deployment of AI Services in within the production environment and its connectivity to integration with AC 5.x Professional.

...

Infrastructure Deployment in Azure

  1. Create a “Resource Group” with required “Tags”

...

  1. Create “App Service Plan” with required “Tags”

...

  1. Once “App Service Plan” is created, it will show the overview as below:

...

  1. Create “Web App” with the steps below:

...

  1. Create “API Management Service”.

...

  1. Configure API’s 

...

Add required policy

...

Create GET & PUT operation 

...

  1. App Reg and integration 

...

Create new App reg 

...

Update the inbound policy for extract unstructured data async  and change the client id according to the created details 

...

  1. Create AKS Cluster

...

Image RemovedImage Removed

...

  1. Configure Milvus

Code Block
attu:

...



  enabled: true

...



  service:

...



    type: LoadBalancer

...





extraConfigFiles:

...



  user.yaml: |+

...



    common:

...



      security:

...



        authorizationEnabled: true

...





service:

...



  type: LoadBalancer

...



 

...



minio:

...



  persistence:

...



    size: 50Gi

...





pulsar:

...



  bookkeeper:

...



    volumes:

...



      journal:

...



        size: 50Gi

...



      ledgers:

...



        size: 50Gi

...


kafka:

...



  persistence:

...



    size: 50Gi

Image RemovedImage RemovedImage RemovedImage AddedImage AddedImage Added

Default username and password

...

To onboard new clients we need to add new clients in app reg and also create the database of the same. 

...

  1. Configure AI Service 

...

Go to manage deployment

...

Create new model deployment

...

Increase the token limit to max for all

...

Image RemovedCreate Content filter

...

Requested decreased restriction on open ai content filtering

https://customervoice.microsoft.com/Pages/ResponsePage.aspx?id=v4j5cvGGr0GRqy180BHbR7en2Ais5pxKtso_Pz4b1_xUMlBQNkZMR0lFRldORTdVQzQ0TEI5Q1ExOSQlQCN0PWcu

Request Quota increase:

...

    ...

    1. Document Intelligence 

    Create document intelligence service 

    ...

    https://learn.microsoft.com/en-us/rest/api/aiservices/document-models/list-models?view=rest-aiservices-v4.0%20(2024-07-31-preview)&tabs=HTTP

    ...

    Security: 

    1. API Manamagent: Only allow IP address of AC5 professional AKS cluster in api management 

    ...

    1. Swap the prod with prod-02

    ...

    ...