Table Of Contents:
Table of Contents | ||
---|---|---|
|
...
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”
...
Create “App Service Plan” with required “Tags”
...
Once “App Service Plan” is created, it will show the overview as below:
...
Create “Web App” with the steps below:
...
Create “API Management Service”.
...
Configure API’s
...
Add required policy
...
Create GET & PUT operation
...
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
...
Create AKS Cluster
...
...
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 |
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.
...
Configure AI Service
...
Go to manage deployment
...
Create new model deployment
...
Increase the token limit to max for all
...
Create Content filter
...
Requested decreased restriction on open ai content filtering
Request Quota increase:
...
...
Document Intelligence
Create document intelligence service
...
...
Security:
API Manamagent: Only allow IP address of AC5 professional AKS cluster in api management
...
Swap the prod with prod-02
...
...