Merge pull request #2 from fpgmaas/prod

Add building for CPU

.github/workflows/publish.yml

@@ -0,0 +1,39 @@
+name: Build and Push Docker Images
+
+on:
+  workflow_dispatch:
+
+jobs:
+  push-to-acr:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v2
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+
+      - name: Login to Azure Container Registry
+        uses: azure/docker-login@v1
+        with:
+          login-server: pypiscoutacr.azurecr.io
+          username: ${{ secrets.ACR_USERNAME }}
+          password: ${{ secrets.ACR_PASSWORD }}
+
+      - name: Build and Push Backend Docker image
+        uses: docker/build-push-action@v4
+        with:
+          context: .
+          file: ./DockerfileCPU
+          platforms: linux/amd64
+          push: true
+          tags: pypiscoutacr.azurecr.io/pypi-scout-backend:latest
+
+      - name: Build and Push Frontend Docker image
+        uses: docker/build-push-action@v4
+        with:
+          context: ./frontend
+          file: ./frontend/Dockerfile
+          platforms: linux/amd64
+          push: true
+          tags: pypiscoutacr.azurecr.io/pypi-scout-frontend:latest

Dockerfile

@@ -5,27 +5,31 @@ FROM python:3.10-slim-bookworm
 ENV POETRY_VERSION=1.6 \
     POETRY_VIRTUALENVS_CREATE=false
 
-# Install poetry
-RUN pip install "poetry==$POETRY_VERSION"
+# Install poetry and clean up
+RUN pip install "poetry==$POETRY_VERSION" && \
+    rm -rf /root/.cache/pip
 
-# Copy only requirements to cache them in docker layer
+# Set work directory
 WORKDIR /code
+
+# Copy only requirements to cache them in docker layer
 COPY poetry.lock pyproject.toml /code/
 
-# Project initialization:
-RUN poetry install --no-interaction --no-ansi --no-root --no-dev
+# Install project dependencies and clean up
+RUN poetry install --no-interaction --no-ansi --no-root --no-dev && \
+    rm -rf /root/.cache/pip
 
 # Copy Python code to the Docker image
 COPY pypi_scout /code/pypi_scout/
 
-ENV PYTHONPATH=/code
-
 # Copy the start script and make executable
 COPY start.sh /start.sh
 RUN chmod +x /start.sh
 
 # Make empty data directory
 RUN mkdir -p /code/data
 
+ENV PYTHONPATH=/code
+
 # Use the script as the entrypoint
 ENTRYPOINT ["/start.sh"]

DockerfileCPU

@@ -0,0 +1,34 @@
+# syntax=docker/dockerfile:1
+
+# Use a slim Python image as the base
+FROM python:3.10-slim-bookworm
+
+# Set environment variables
+ENV PYTHONUNBUFFERED=1
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    && apt-get clean && rm -rf /var/lib/apt/lists/*
+
+# Set working directory
+WORKDIR /code
+
+# Copy only requirements to cache them in docker layer
+COPY requirements-cpu.txt /code/requirements-cpu.txt
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements-cpu.txt
+
+# Copy the rest of the application code
+COPY pypi_scout /code/pypi_scout/
+
+# Copy the start script and make it executable
+COPY start.sh /start.sh
+RUN chmod +x /start.sh
+
+# Make empty data directory
+RUN mkdir -p /code/data
+
+# Use the script as the entrypoint
+ENTRYPOINT ["/start.sh"]

requirements-cpu.txt

@@ -0,0 +1,14 @@
+beautifulsoup4==4.12.3
+polars==0.20.31
+sentence-transformers==3.0.1
+lxml==5.2.2
+python-dotenv==1.0.1
+pinecone-client==4.0.0
+tqdm==4.66.4
+fastapi==0.111.0
+pydantic==2.7.4
+uvicorn==0.30.1
+gdown==5.2.0
+torch==2.0.1
+--index-url=https://download.pytorch.org/whl/cpu
+--extra-index-url=https://pypi.org/simple