-
ffmpeg (for audio processing)
brew install ffmpeg
cd gen-ai-gl/apps
poetry run python -m audio_to_text.cli.cli --audio audio_to_text/sample_files/first.wavExport the following environment variables:
export STREAMLIT_SERVER_PORT=8502
export STREAMLIT_SERVER_HEADLESS=true
export HUGGINGFACE_API_TOKEN=<HUGGING_FACE_API_ACCESS_TOKEN>Then run:
cd gen-ai-gl/apps
poetry run streamlit run main.pyClick to expand Docker instructions
# Set environment variables (edit as needed)
export PORT=8501
export HUGGINGFACE_API_TOKEN=<your_hf_token>
export OPENAI_API_KEY=<your_openai_key>
# Start the app
make upThe app will be available at: http://localhost:8501
| Command | Description |
|---|---|
make up |
Build & start containers |
make down |
Stop & remove containers |
make stop |
Stop containers |
make clean |
Prune containers/images/networks |
make ps |
List all containers |
make logs |
Show container logs |
Port: Set
PORTenv variable to change the exposed port (default: 8501).API Keys: Set
HUGGINGFACE_API_TOKENandOPENAI_API_KEYas needed.Headless Mode:
STREAMLIT_SERVER_HEADLESS=trueis set by default in Docker Compose.
gen-ai-gl/ ├── apps/ │ ├── audio_to_text/ │ ├── image_to_text/ │ ├── learning_assistant/ │ ├── ui/ │ └── utils/ ├── Dockerfile ├── docker-compose.yaml ├── Makefile └── README.md