日本語版はこちら / Japanese version here
AzureUpdatePPTX is a multilingual tool that automatically retrieves Azure updates and generates PowerPoint presentations with AI-powered summaries.
- Automatic retrieval of Azure updates (up to 90 days)
- AI-powered summarization of Azure updates in 9 languages using Azure OpenAI
- Automatic PowerPoint presentation generation
- Browser language detection and multilingual support
- Support for Japanese, English, Korean, Chinese (Simplified/Traditional), Thai, Vietnamese, Indonesian, and Hindi
- SEO optimization with robots.txt and sitemap.xml support
- Azure OpenAI (with GPT-4o model deployment)
$ docker run --rm -p 8000:8000 --env API_KEY=<your_api_key> --env API_ENDPOINT=https://example.com/deployments/gpt-4o/?api-version=2024-08-01-preview koudaiii/azureupdatepptxOr using environment file:
$ cp .env.sample .env
$ docker run --rm -p 8000:8000 --env-file .env koudaiii/azureupdatepptxAccess the application at http://localhost:8000
-
Clone the repository:
git clone https://github.com/koudaiii/AzureUpdatePPTX.git -
Navigate to the project directory:
cd AzureUpdatePPTX -
Copy the environment sample and configure Azure OpenAI credentials:
cp .env.sample .envEdit
.envfile and set your Azure OpenAI API Key and API Endpoint. -
Install dependencies:
script/bootstrap -
Start the development server:
script/server
Access the application at http://localhost:8000
The application automatically detects browser language and supports:
- Japanese (ja): 日本語 - Default
- English (en): English
- Korean (ko): 한국어
- Chinese Simplified (zh-cn): 中文(简体)
- Chinese Traditional (zh-tw): 中文(繁體)
- Thai (th): ไทย
- Vietnamese (vi): Tiếng Việt
- Indonesian (id): Bahasa Indonesia
- Hindi (hi): हिन्दी
The application includes SEO optimization features:
- robots.txt: Available at
/robots.txt- Allows search engine crawling - sitemap.xml: Available at
/sitemap.xml- Includes all language variants with proper priorities - Meta tags: Automatic addition of SEO meta tags, Open Graph, and Twitter Card metadata
- Language detection: Browser-based language detection with fallback to English
These static files are automatically generated during Docker build process and served by Streamlit.
Run all tests using:
python test_runner.pyContributions are welcome! Please report issues before submitting pull requests.
This project is licensed under the MIT License.