Provision An Azure AI Services Resource
About
Azure AI Services is a
set of services that you can use into your apps as building blocks of AI
capabilities. Cloud-based services that incorporate AI capabilities are called
Azure AI services. You should consider AI services as a collection of separate
services that you can use as building blocks to create complex, intelligent
applications rather than as a single solution.
Azure AI services
include:
- Azure AI Document
Intelligence - An Optical Character Recognition (OCR)
solution that can extract semantic meaning from forms, such as invoices,
receipts, and others.
- Azure AI Immersive Reader
- A reading solution that supports people of all ages and abilities.
- Azure AI Search
- A cloud-scale search solution that uses AI services to extract insights from
data and documents.
- Azure OpenAI
- An Azure Cognitive Service that provides access to the capabilities of OpenAI
GPT-4.
Provision an Azure AI Services
Resource
Azure AI services include
a wide range of AI capabilities that you can use in your applications. In order
to utilize any of the AI services, you must set up the necessary resources in
an Azure subscription to specify an endpoint where the service can be used,
supply access keys for verified access, and handle invoicing for the use of the
service by your application.
Options For Azure Resources
For many of the available
AI services, you can choose between the following provisioning options:
- Multi-Service Resource- An
AI services resource that supports several distinct AI services can be provisioned.
With this method, you may use a single point of invoicing for all service usage
and manage a single set of access credentials to use numerous services at a
single endpoint.
- Single-Service Resource- It
is possible to provide each AI service separately. With this method, you may
maintain access credentials for each service separately and utilize different
endpoints for each service. Additionally, it allows you to handle each
service's billing independently. Single-service resources are an excellent
option to test a service before utilizing it in a production application
because they typically offer a free tier (with usage constraints).
- Training and Prediction Resources-
Some
AI services offer (or require) different resources for model training and
prediction, although the majority can be used with just one Azure resource. In
most situations, this allows you to use a dedicated service-specific resource
to train a model and a generic AI services resource to make the model available
to applications for inferencing. It also allows you to manage billing for
training custom models independently from model consumption by applications.
Conclusion
We have successfully
learnt about provisioning an AI Service resource.
Comments
Post a Comment