UNDERCODE COMMUNITY
2.68K subscribers
1.23K photos
31 videos
2.65K files
80K links
🦑 Undercode Cyber World!
@UndercodeCommunity


1️⃣ World first platform which Collect & Analyzes every New hacking method.
+ AI Pratice
@Undercode_Testing

2️⃣ Cyber & Tech NEWS:
@Undercode_News

3️⃣ CVE @Daily_CVE

Web & Services:
Undercode.help
Download Telegram
Forwarded from UNDERCODE TESTING
🦑 AI-Chat-App-Hack-Vision integrating GPT-4 and Vision:

Overview
This project combines GPT-4 with Vision Studio using Azure services. It uses the sample nature dataset from Vision Studio and is inspired by the [Azure Search OpenAI Demo](https://github.com/Azure/azure-search-openai-demo).

Requirements

Azure Account
1. Azure Free Account: Sign up for free Azure credits.
2. Permissions:
- Role-Based Access Control (RBAC):
- Microsoft.Authorization/roleAssignments/write permissions.
- Subscription or resource group access is mandatory.
- Azure OpenAI Access:
- Request access via [this form](https://aka.ms/oai/access).

Local Environment
1. Tools:
- Azure Developer CLI
- Python 3.9–3.11 (ensure python --version works).
- Node.js 14+
- Git
- PowerShell 7+ (Windows only).

2. Setup:
- Install dependencies.
- Ensure Python and PowerShell paths are configured.



Azure Deployment

Steps
1. Prepare Local Code:
- Create a folder and navigate to it in your terminal.
- Authenticate: azd auth login.
- Initialize project:
azd init -t https://github.com/mattgotteiner/AI-Chat-App-Hack-Vision.

2. Deploy Resources:
- Run azd up to provision and deploy all resources.
- Monitor for costs! Stop unused resources to avoid charges:
- azd down or delete resources manually.
- After deployment, access the app via the provided URL.

Deployment Details
- Resources Deployed:
- Azure App Service (Basic Tier, 1 CPU core, 1.75 GB RAM).
- Azure OpenAI (Standard tier, GPT-4 model).
- Azure AI Search (Standard tier, 1 replica).
- Azure Blob Storage (ZRS).
- Azure Monitor (Pay-as-you-go).

- Cost Optimization:
- Use free SKUs where possible.
- Refer to the [Azure Pricing Calculator](https://azure.microsoft.com/en-us/pricing/calculator/) for estimates.



Running Locally
1. Ensure successful deployment with azd up.
2. Authenticate: azd auth login.
3. Start app:
- Navigate to the app directory.
- Run ./start.ps1 or use VS Code's "Run & Debug".
- Open [http://localhost:50505](http://localhost:50505) in your browser.

Clean Up
To avoid unnecessary costs:
1. Run azd down.
2. Confirm cleanup by entering y when prompted.

For more details, refer to the [project repository](https://github.com/mattgotteiner/AI-Chat-App-Hack-Vision).