Async release

Dockerfile

@@ -1,6 +1,10 @@
+FROM python:3.11-slim as requirements-stage
+WORKDIR /tmp
+RUN pip install poetry
+COPY pyproject.toml ./poetry.lock* /tmp/
+RUN poetry export -f requirements.txt --output requirements.txt --without-hashes
+
 
-# Use the official lightweight Python image.
-# https://hub.docker.com/_/python
 FROM python:3.11-slim
 
 # Allow statements and log messages to immediately appear in the logs
@@ -9,18 +13,25 @@ ENV PYTHONUNBUFFERED True
 # Copy local code to the container image.
 ENV APP_HOME /app
 WORKDIR $APP_HOME
+
 COPY . ./
 
+COPY --from=requirements-stage /tmp/requirements.txt /app/requirements.txt
+
 RUN apt update && apt install -y ffmpeg
 
-# Install production dependencies.
-RUN pip install --no-cache-dir -r requirements.txt
+RUN pip install openai-whisper
 
-EXPOSE 5000
+# openai-whisper model in not compatible with the newer 2.0.0 numpy release
+RUN pip install --upgrade numpy<2
+
+RUN pip install --no-cache-dir -r /app/requirements.txt
+
+EXPOSE 8000
 
 # Run the web service on container startup. Here we use the gunicorn
 # webserver, with one worker process and 8 threads.
 # For environments with multiple CPU cores, increase the number of workers
 # to be equal to the cores available.
 # Timeout is set to 0 to disable the timeouts of the workers to allow Cloud Run to handle instance scaling.
-CMD exec gunicorn --bind 0.0.0.0:5000 --workers 1 --threads 8 --timeout 0 app:app
+CMD exec uvicorn --bind 0.0.0.0:8000 --workers 1 --threads 8 --timeout 0 app.server:app