AIknowlEDGE

AIknowlEDGE is a desktop application built with Electron.js and Python FastAPI to showcase Disconnected Containers.
Explore the docs »

View Demo · Report Bug · Request Feature

Containers let you run Azure AI services in your own environment, meeting security and data governance requirements. Disconnected containers let you run many of these services offline.

(back to top)

(back to top)

Follow these steps to run the project locally.

• Python 3.12+
• Docker
• VS Code
• Ollama

1. Clone the repository:

   git clone https://github.com/Azure-Samples/AI-knowlEDGE.git
   cd AIknowlEDGE
   

2. Install Docker and pull the container:

   docker pull mcr.microsoft.com/azure-cognitive-services/textanalytics/summarization:cpu

3. Get your Cognitive Services keys and endpoints:

   AZURE_DOCUMENT_ANALYSIS_ENDPOINT
   AZURE_DOCUMENT_ANALYSIS_KEY
   LANGUAGE_ENDPOINT
   LANGUAGE_KEY
   

4. Create a folder on your C:/ drive named ExtractiveModel.

5. Download the SLMs for the Summarization Service. Start Docker and run:

   docker run -v C:\ExtractiveModel:/models mcr.microsoft.com/azure-cognitive-services/textanalytics/summarization:cpu downloadModels=ExtractiveSummarization billing=LANGUAGE_ENDPOINT apikey=LANGUAGE_KEY
   

6. Set up the Python environment and install dependencies:

   cd backend
   python -m venv venv
   venv\Scripts\activate  # On Linux use `source venv/bin/activate`
   pip install -r requirements.txt

7. Create a docker-compose.yml with the following:

   version: "3.9"
   services:
     azure-form-recognizer-read:
       container_name: azure-form-recognizer-read
       image: mcr.microsoft.com/azure-cognitive-services/form-recognizer/read-3.1
       environment:
         - EULA=accept
         - billing=<document-intelligence-endpoint>
         - apiKey=<document-intelligence-key>
       ports:
         - "5000:5000"
       networks:
         - ocrvnet
   
     textanalytics:
       image: mcr.microsoft.com/azure-cognitive-services/textanalytics/summarization:cpu
       environment:
         - eula=accept
         - rai_terms=accept
         - billing=<language-endoint>
         - apikey=<language-key> 
       volumes:
         - "C:\\ExtractiveModel:/models"
       ports:
         - "5001:5000"
   
   networks:
     ocrvnet:
       driver: bridge

8. Create the container by running:

   docker-compose up

9. Make a .env file:

   AZURE_DOCUMENT_ANALYSIS_ENDPOINT=http://localhost:5000
   AZURE_DOCUMENT_ANALYSIS_KEY=<document-intelligence-key>
   LANGUAGE_ENDPOINT=http://localhost:5001
   LANGUAGE_KEY=<language-key>
   

10. Download Ollama and install at least one SLM and one embedding model:

    ollama pull phi3
    ollama pull nomic-embed-text

11. Start the application from VS Code: F5 or Run > Start Debugging

(back to top)

1. Start the FastAPI backend:

   cd backend
   uvicorn main:app --port 8000

2. Start the Streamlit app:

   cd frontend
   streamlit run app.py --server.port=8501

(back to top)

• Other Containers Integration
  • Speech service
  • Translation service
• Other Use Cases Integration
• Packaging
  • Single-click installation
  • Cross-platform installation

See the open issues for proposed features and known issues.

(back to top)

Contributions make open source great. We appreciate all contributions.

1. Fork this repo
2. Create a Feature Branch (git checkout -b feature/AmazingFeature)
3. Commit your changes (git commit -m 'Add some AmazingFeature')
4. Push to the branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

(back to top)

Distributed under the MIT License. See LICENSE.txt for more info.

(back to top)

• Raoui Lassoued LinkedIn
• Serge Retkowsky LinkedIn
• Farid El Attaoui LinkedIn
• Alibek Jakupov @ajakupov1 LinkedIn

Project Link: AIKnowlEDGE

(back to top)

• Microsoft France

(back to top)