Merge pull request #3 from FBruzzesi/dockering

Dockering

Author: JurijWollert

.dockerignore

@@ -0,0 +1,34 @@
+# Folders
+.ipynb_checkpoints/
+.mypy_cache/
+.ruff_cache/
+.venv/
+data/
+docker/
+nbs/
+models/
+db/
+
+.git/
+.github/
+docker/
+docs/
+kubernetes/
+
+# Files
+.dockerignore
+.gitignore
+.pre-commit-config.yaml
+mkdocs.yaml
+README.md
+Makefile
+
+# Various
+**/__pychache__
+**/*.egg-info
+**.pyc
+**.pytest_cache
+**.ipynb
+**.bat
+**.egg-info
+**/build

.gitignore

@@ -160,3 +160,8 @@ cython_debug/
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 #.idea/
+
+# Databases and Models
+*.db
+models/*
+!models/.gitkeep

db/.gitkeep

@@ -0,0 +1,22 @@
+services:
+
+  backend:
+    build:
+      context: .
+      dockerfile: docker/backend.dockerfile
+    ports:
+      - "8081:8081"
+    volumes:
+      - ./db:/app/db
+      - ./models:/app/models     # Mount machine learning model folder
+
+  frontend:
+    build:
+      context: .
+      dockerfile: docker/frontend.dockerfile
+    ports:
+      - "8501:8501"
+    depends_on:
+      - backend
+    environment:
+      - ENV=docker-compose

docker-compose.yml

@@ -0,0 +1,37 @@
+# Use a Python image with uv pre-installed
+FROM ghcr.io/astral-sh/uv:python3.12-bookworm-slim
+
+# Install the project into `/app`
+WORKDIR /app
+
+# Enable bytecode compilation
+ENV UV_COMPILE_BYTECODE=1
+
+# Copy from the cache instead of linking since it's a mounted volume
+ENV UV_LINK_MODE=copy
+
+# Install the project's dependencies using the lockfile and settings
+RUN --mount=type=cache,target=/root/.cache/uv \
+    --mount=type=bind,source=uv.lock,target=uv.lock \
+    --mount=type=bind,source=pyproject.toml,target=pyproject.toml \
+    uv sync --frozen --no-install-project --extra backend
+
+# Then, add the rest of the project source code and install it
+# Installing separately from its dependencies allows optimal layer caching
+ADD . /app
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync --frozen --extra backend
+
+# Place executables in the environment at the front of the path
+ENV PATH="/app/.venv/bin:$PATH"
+
+# Reset the entrypoint, don't invoke `uv`
+ENTRYPOINT []
+
+EXPOSE 8081
+
+# Run the FastAPI application by default
+# Uses `fastapi dev` to enable hot-reloading when the `watch` sync occurs
+# Uses `--host 0.0.0.0` to allow access from outside the container
+ENTRYPOINT ["fastapi", "run", "src/moin_moin/backend/api.py" , "--port", "8081"]
+

docker/backend.dockerfile

@@ -0,0 +1,36 @@
+# Use a Python image with uv pre-installed
+FROM ghcr.io/astral-sh/uv:python3.12-bookworm-slim
+
+# Install the project into `/app`
+WORKDIR /app
+
+# Enable bytecode compilation
+ENV UV_COMPILE_BYTECODE=1
+
+# Copy from the cache instead of linking since it's a mounted volume
+ENV UV_LINK_MODE=copy
+
+# Install the project's dependencies using the lockfile and settings
+RUN --mount=type=cache,target=/root/.cache/uv \
+    --mount=type=bind,source=uv.lock,target=uv.lock \
+    --mount=type=bind,source=pyproject.toml,target=pyproject.toml \
+    uv sync --frozen --no-install-project --extra frontend
+
+# Then, add the rest of the project source code and install it
+# Installing separately from its dependencies allows optimal layer caching
+ADD . /app
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync --frozen --extra frontend
+
+# Place executables in the environment at the front of the path
+ENV PATH="/app/.venv/bin:$PATH"
+
+# Reset the entrypoint, don't invoke `uv`
+ENTRYPOINT []
+
+EXPOSE 8501
+
+# Run the FastAPI application by default
+# Uses `fastapi dev` to enable hot-reloading when the `watch` sync occurs
+# Uses `--host 0.0.0.0` to allow access from outside the container
+ENTRYPOINT ["streamlit", "run", "src/moin_moin/frontend/app.py", "--server.port=8501", "--server.address=0.0.0.0"]

docker/frontend.dockerfile

@@ -35,8 +35,10 @@ torch = [{ index = "pytorch-cpu"}]
 moin-moin = "moin_moin:main"
 
 [build-system]
-requires = ["hatchling"]
-build-backend = "hatchling.build"
+requires = [
+  "setuptools >= 40.9.0",
+]
+build-backend = "setuptools.build_meta"
 
 
 [tool.ruff]

models/.gitkeep

@@ -17,7 +17,7 @@ class ClipModel:
     """
 
     def __init__(self: Self, text_options: dict[str, str]) -> None:
-        self.model = SentenceTransformer("clip-ViT-B-32")
+        self.model = SentenceTransformer("clip-ViT-B-32", cache_folder="models")
         self.model.eval()
         self.labels = list(text_options.keys())
         self.text_embedding = self.model.encode(list(text_options.values()))

pyproject.toml

@@ -33,7 +33,7 @@
 
 ML_MODEL: dict[str, ClipModel] = {}
 
-DB_NAME: Final[str] = "sqlite:///moin-moin.db"
+DB_NAME: Final[str] = "sqlite:///db/moin-moin.db"
 ENGINE: Final[Engine] = create_engine(DB_NAME)
 
 INSTITUTIONS = {