add docker config file

Dockerfile

@@ -0,0 +1,38 @@
+# Use NVIDIA CUDA as base image
+FROM nvidia/cuda:12.4.1-devel-ubuntu22.04
+
+# Set working directory
+WORKDIR /app
+
+# Set environment variables to non-interactive (this prevents some prompts)
+ENV DEBIAN_FRONTEND=non-interactive
+
+# Install required libraries, tools, and Python3
+RUN apt-get update && apt-get install -y libgl1 libglib2.0-0 ffmpeg curl git python3.10 python3-pip nvidia-cuda-toolkit
+ENV LD_LIBRARY_PATH=/usr/local/cuda/compat:$LD_LIBRARY_PATH
+
+# Install poetry
+RUN curl -sSL https://install.python-poetry.org | python3 -
+
+# Update PATH
+RUN echo 'export PATH="/root/.local/bin:$PATH"' >> /root/.bashrc
+ENV PATH="/root/.local/bin:$PATH"
+
+# Copy project files into the container
+COPY . /app
+
+# Install the package with poetry
+RUN poetry install
+
+# Install flash attention
+RUN poetry run pip install torch torchvision --index-url https://download.pytorch.org/whl/cu124
+RUN poetry run pip install flash-attn --no-build-isolation
+
+# Disable buffering for stdout and stderr to get the logs in real time
+ENV PYTHONUNBUFFERED=1
+
+# Expose the desired port
+EXPOSE 8000
+
+# Run the app
+CMD ["poetry", "run", "aana", "deploy", "aana_app_project.app:aana_app", "--host", "0.0.0.0"]

README.md

@@ -113,3 +113,32 @@ For example, if your application has `/summary` endpoint that accepts videos, yo
 ```bash
 curl -X POST http://127.0.0.1:8000/summary -Fbody='{"video":{"url":"https://www.youtube.com/watch?v=VhJFyyukAzA"}}'
 ```
+
+## Running inside the Docker
+
+To run the project via docker, a dockerfile and docker-compose config are available in the repo. you can run it via docker-compose or directly via docker as follows:
+
+### Deploying via docker-compose
+
+```bash
+CUDA_VISIBLE_DEVICES=0 docker-compose up
+```
+If your application needs GPU to run, you need to specify `CUDA_VISIBLE_DEVICES` in the command.
+The docker-compose config, would deploy a Postgres instance besides the application and link them to each other. If you already have a database somewhere you can edit the docker-compose config, remove the Postgres and set the Postgres address via the environment variables.
+The app would be available at `http://localhost:8000` in the host server and the Postgres would be accessible via port 15430.
+You can check the [Docker Compose Config](./docker-compose.yaml) to see all available variables you can set for running the application.
+
+### Deploying via docker
+
+To deploy the application by docker directly follow these steps:
+
+1. Build the docker image by running:
+
+```bash
+docker build --no-cache -t aana_app_project:latest .
+```
+
+2. Run the the image:
+```bash
+docker run --rm -it -v ~/.cache:/root/.cache -e CUDA_VISIBLE_DEVICES="0,1" -e DB_CONFIG=$DB_CONFIG -p 8000:8000 aana_app_project:latest
+```

docker-compose.yaml

@@ -0,0 +1,66 @@
+version: '3.8'
+
+services:
+  postgres:
+    restart: always
+    container_name: aana_app_project_db
+    image: postgres
+    command: postgres -c 'max_connections=1000'
+    healthcheck:
+      test: /usr/bin/pg_isready
+      timeout: 45s
+      interval: 10s
+      retries: 10
+    ports:
+      - '15430:15430'
+    expose:
+      - 15430
+    environment:
+      PGPASSWORD: '${POSTGRES_PASSWORD:-Yf?5nX39}'
+      PGUSER: '${POSTGRES_USER:-aana_db_user}'
+      PGDATABASE: '${POSTGRES_DB:-aana_db}'
+      POSTGRES_PASSWORD: '${POSTGRES_PASSWORD:-Yf?5nX39}'
+      POSTGRES_USER: '${POSTGRES_USER:-aana_db_user}'
+      POSTGRES_DB: '${POSTGRES_DB:-aana_db}'
+      PGPORT: '15430'
+      PGDATA: '/pgdata'
+    volumes:
+      - pg_data:/pgdata
+
+  aana_app_project_app:
+    restart: always
+    container_name: aana_app_project_app
+    depends_on:
+      postgres:
+        condition: service_healthy
+    ports:
+      - 8000:8000   # request server
+    expose:
+      - '8000'
+    build:
+      context: .
+      dockerfile: Dockerfile
+    deploy:
+      resources:
+        reservations:
+          devices:
+              - capabilities: ["gpu"]
+    environment:
+      CUDA_VISIBLE_DEVICES: '${CUDA_VISIBLE_DEVICES}'
+      HF_HUB_ENABLE_HF_TRANSFER: '${HF_HUB_ENABLE_HF_TRANSFER:-1}'
+      HF_TOKEN: '${HF_TOKEN}'
+      HF_DATASETS_CACHE: /root/.cache/huggingface
+      NUM_WORKERS: '${NUM_WORKERS:-2}'
+      TMP_DATA_DIR: /tmp/aana_data
+      DB_CONFIG: '{"datastore_type":"postgresql","datastore_config":{"host":"postgres","port":"15430","user":"${POSTGRES_USER:-aana_db_user}","password":"${POSTGRES_PASSWORD:-Yf?5nX39}","database":"${POSTGRES_DB:-aana_db}"}}'
+    volumes:
+      - app_data:/tmp/aana
+      - hf_datasets_cache:/root/.cache/huggingface
+
+volumes:
+  pg_data:
+    name: aana_app_project_postgres_data
+  app_data:
+    name: aana_app_project_app_data
+  hf_datasets_cache:
+    name: hf_datasets_cache