Room 2202, 22/F,
Mega Trade Centre,
1 Mei Wan Street,
Tsuen Wan, New Territories
Tel: 91375571

Invoice Number h-i2020063491648
Invoice Date 19.10.2023
Total Due $150,000.00
Global Technology Integrator Limited

Unit 3603-3609, 36/F, 1 Hung To Road, Kwun Tong, Kowloon, Hong Kong.

Objective: To leverage AI technologies to enhance the azure AOAI support tools and improve vpg's ability to serve consumers.
Duration : 3 months

Remark: 100% payment in advance upon order confirmation and PO received
Remark: Please settle payment on or before 31 Oct 2023

Hrs/Qty Service Rate/PriceAdjustSub Total
1 GTI Azure Open AI Implementation and Managed Service

Setup Environment
Setting up the development environment, which includes creating an Azure account, setting up Azure Search service, and getting access to OpenAI API.
Data Ingestion and Indexing
Define the data source ( Azure Blob storage) and create an indexing pipeline to ingest and index data. Define a suitable schema for the data, which represents the structure of your data in Azure Search.
Integration with OpenAI API
Set up the OpenAI API to leverage the GPT model. This includes getting the appropriate API key and ensuring the project can successfully make requests to the API.
Query Processing
Develop the logic to process user queries. This would involve receiving user inputs, sending the input to the OpenAI API for processing, receiving the processed input back, and then using this processed input to perform a search operation on the Azure Search index.
Search Results Retrieval
Define the logic to retrieve and present the search results from Azure Search service based on the processed input.
UI/UX Development
Create interface for users to input their queries in natural language and to display the search results.
**UI/UX Design will no cover in thise SOW
Conduct thorough testing of the system to ensure all components are working as expected. This includes unit tests, integration tests, and end-to-end tests
Azure services will be implement with

1. **Azure Cognitive Search**: This is the core service for this project. Azure Cognitive Search is a search-as-a-service cloud solution that gives developers APIs and tools for adding a rich search experience over private, heterogenous content in web, mobile, and enterprise applications.

2. **Azure Blob Storage**: This could be used for storing and retrieving large amounts of unstructured data, such as documents or media files. If you plan to use a large dataset for your search index, Azure Blob Storage would be ideal for this purpose.

3. **Azure Functions**: These can be used to create serverless applications that can handle integration between OpenAI API and Azure Cognitive Search. Azure Functions can be triggered by events, making it suitable for handling real-time processing and transformations.

4. **Azure App Service**: This is a fully managed platform for building, deploying, and scaling web apps. You can host your front-end application here.

5. **Azure Cognitive Services (Language Service)**: These services could be useful for additional natural language processing capabilities, text analytics, sentiment analysis, etc.

6. **Azure Key Vault**: This service could be used for securely storing and managing sensitive information like OpenAI API key, Azure Search keys, etc.

7. **Azure Active Directory**: For adding secure login for your application.

8. **Azure DevOps**: This service provides developer services for support with planning work, collaborating on code development, and building and deploying applications.

9. **Azure Monitor**: This service can be used to collect, analyze, and act on telemetry data from your Azure and on-premises environments. It helps to understand how your applications are performing and proactively identifies issues affecting them and the resources they depend on.
*Remarks: The actual services required may vary based on your exact use case, application architecture, and specific requirements. Be sure to assess each service for its appropriateness to your needs.

1 Annual Managed Services Offering (Optional)

Token Basis Support Offering:
- Service Provision Time:
Included 20 x Tokens supporting service ( 8x5 )
Office Hour : 9:30am-5:30pm
Non-Office Hour: 5:31pm-09:29am
Each service token is equivalent to 4 man-hours
A minimum chargeable of 1 service token per remote support service
The service token can be use on:

- Incident base remote support :
Number of Token (Office Hour) : _____1_____ Token
Number of Token (Non-Office Hour) : ____1.5_____ Token

- TAM advisory solution :
Number of Token (Office Hour) : _____0.5_____ Token

- On-site support (only on demand or critical infrastructure incident) :
Number of Token (Office Hour) : _____ 1.5_____ Token
Number of Token (Non-Office Hour) : _____ 2_____ Token

Service Time:
- 15mins response by email acknowledgment
- 2hrs response for remote, phone and email support

Service Scope:
a. Support Services
- Azure OpenAI Services
- Azure cognitive services
- Azure Monitoring
o URL monitoring
o Usage Monitoring
o VM backup status monitoring
o VPN health status monitoring
o VM health status and performance monitoring
- Azure Backup Management
- Azure component provisioning or configuration according to predefined procedure or design, including
o Virtual Machine
o Virtual Network
o Virtual Network Peering
o Public IP address
o Azure Firewall
o Network security group
o Azure Site Recovery
o Azure Storage
o Azure Key Vault
o Azure Backup
- Software installation (Remote) - Proxy Server and Authentication Service, NFS service and Cache service

Sub Total $150,000.00
Tax $0.00
Total Due $150,000.00

*Cheques should be crossed and made payable to “Hazedawn Limited”
*Company bank account - Bank of China - 012-720-0-003526-8

Hazedawn Limited
FPS ID: 160462198