Enable build and push of Dockerfile.

.github/workflows/package.yaml

@@ -0,0 +1,55 @@
+name: Create and publish a Docker image
+
+on:
+  push:
+    branches:
+      - 'main'
+    tags:
+      - 'v*'
+
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}
+
+jobs:
+  build-and-push-image:
+    runs-on: ubuntu-latest
+
+    permissions:
+      contents: read
+      packages: write
+      attestations: write
+      id-token: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Log in to the Container registry
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+
+      - name: Build and push Docker image
+        id: push
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+
+      - name: Generate artifact attestation
+        uses: actions/attest-build-provenance@v1
+        with:
+          subject-name: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME}}
+          subject-digest: ${{ steps.push.outputs.digest }}
+          push-to-registry: true

Dockerfile

@@ -0,0 +1,28 @@
+FROM python:3.10-slim
+
+RUN pip3 install --no-cache-dir --upgrade \
+    pip \
+    virtualenv
+
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    software-properties-common \
+    git
+
+    ENV VIRTUAL_ENV=/home/venv
+
+COPY . /home/appuser/document-to-podcast
+WORKDIR /home/appuser/document-to-podcast
+
+RUN virtualenv ${VIRTUAL_ENV}
+RUN . ${VIRTUAL_ENV}/bin/activate && pip install torch torchaudio --index-url https://download.pytorch.org/whl/cpu
+RUN . ${VIRTUAL_ENV}/bin/activate && pip install /home/appuser/document-to-podcast
+RUN . ${VIRTUAL_ENV}/bin/activate && python demo/download_models.py
+
+RUN groupadd --gid 1000 appuser \
+    && useradd --uid 1000 --gid 1000 -ms /bin/bash appuser
+
+USER appuser
+
+EXPOSE 8501
+ENTRYPOINT ["./demo/run.sh"]

demo/download_models.py

@@ -0,0 +1,13 @@
+"""
+Used when building the Dockerfile to download the models that are used in the hosted demo
+"""
+
+from document_to_podcast.inference.model_loaders import (
+    load_llama_cpp_model,
+    load_parler_tts_model_and_tokenizer,
+)
+
+load_llama_cpp_model(
+    model_id="allenai/OLMoE-1B-7B-0924-Instruct-GGUF/olmoe-1b-7b-0924-instruct-q8_0.gguf"
+)
+load_parler_tts_model_and_tokenizer("parler-tts/parler-tts-mini-v1")

demo/run.sh

@@ -0,0 +1,28 @@
+#!/bin/bash
+
+# Adapted from https://docs.streamlit.io/deploy/tutorials/kubernetes
+
+APP_PID=
+stopRunningProcess() {
+    # Based on https://linuxconfig.org/how-to-propagate-a-signal-to-child-processes-from-a-bash-script
+    if test ! "${APP_PID}" = '' && ps -p ${APP_PID} > /dev/null ; then
+       > /proc/1/fd/1 echo "Stopping ${COMMAND_PATH} which is running with process ID ${APP_PID}"
+
+       kill -TERM ${APP_PID}
+       > /proc/1/fd/1 echo "Waiting for ${COMMAND_PATH} to process SIGTERM signal"
+
+        wait ${APP_PID}
+        > /proc/1/fd/1 echo "All processes have stopped running"
+    else
+        > /proc/1/fd/1 echo "${COMMAND_PATH} was not started when the signal was sent or it has already been stopped"
+    fi
+}
+
+trap stopRunningProcess EXIT TERM
+
+source ${VIRTUAL_ENV}/bin/activate
+
+streamlit run ${HOME}/document-to-podcast/demo/app.py &
+APP_ID=${!}
+
+wait ${APP_ID}