Converted from pip to uv

.gitignore

@@ -8,4 +8,5 @@ __pycache__/
 notebooks/
 .python-version
 ml/data
-.ruff_cache
+.ruff_cache
+.venv

Dockerfile

@@ -2,13 +2,19 @@ FROM python:3.12-slim
 
 WORKDIR /app
 ENV PYTHONPATH=/app
+ENV UV_NO_DEV=1
+
+COPY --from=ghcr.io/astral-sh/uv:0.9.26 /uv /uvx /bin/
+
 RUN apt-get update && apt-get install -y \
     build-essential \
     libstdc++6 \
     && rm -rf /var/lib/apt/lists/*
 
-COPY requirements.txt .
-RUN pip install --no-cache-dir --upgrade -r requirements.txt
+COPY pyproject.toml uv.lock* ./
+RUN uv sync --locked
+ENV PATH="/app/.venv/bin:$PATH"
+
 COPY .env .
 COPY pytest.ini .
 COPY alembic.ini .
@@ -19,4 +25,6 @@ COPY ml ./ml
 COPY tests ./tests
 COPY streamlit ./streamlit
 
-CMD ["python", "discogs_rec_api/main.py"]
+
+CMD ["uv", "run", "python", "discogs_rec_api/main.py"]
+

pyproject.toml

@@ -0,0 +1,27 @@
+[project]
+name = "discogs-rec-api"
+version = "0.1.0"
+requires-python = ">=3.10"
+dependencies = [
+    "alembic==1.16.4",
+    "annoy==1.17.3",
+    "asyncpg==0.30.0",
+    "bcrypt==4.0.1",
+    "cachetools==6.2.2",
+    "email-validator==2.2.0",
+    "fastapi==0.116.1",
+    "httpx==0.28.1",
+    "huggingface-hub==0.34.4",
+    "jwt==1.4.0",
+    "passlib==1.7.4",
+    "psycopg2-binary==2.9.10",
+    "pydantic-settings==2.10.1",
+    "pytest==8.4.1",
+    "pytest-asyncio==1.1.0",
+    "python-dotenv==1.1.1",
+    "python-jose==3.5.0",
+    "python-multipart==0.0.20",
+    "sqlalchemy==2.0.41",
+    "streamlit==1.51.0",
+    "uvicorn==0.35.0",
+]

setup_scripts/main.py

@@ -22,30 +22,24 @@ async def main():
     data_path = ml_path / "data"
     Path(data_path).mkdir(exist_ok=True, parents=True)
 
-    # download and unzip data
     download_files(path=data_path, minimal=args.minimal, ci=args.ci)
     if not args.minimal:
         unzip_data(path=ml_path, ci=args.ci)
 
-    # delete cache from hf
     hf_cache_path = ml_path / "data" / ".cache"
     shutil.rmtree(hf_cache_path)
 
-    # for ci pipeline exit out
     if args.ci:
         return
 
-    # reset alembic and grab latest updates
     reset_alembic()
-    # load releases table
+
     csv_path = ml_path / "data" / "releases.csv"
 
     load_release_from_csv(csv_path=csv_path)
 
-    # delete csv (not needed as its loaded to db)
     csv_path.unlink()
 
-    # create a super user
     test_superuser = UserCreate(
         username="superuser",
         email="super@super.com",

setup_scripts/utils.py

@@ -64,7 +64,6 @@ def unzip_data(path: Path, ci: bool = False) -> None:
     zip_path = path / "data" / f"{file_type}.zip"
     with ZipFile(zip_path, "r") as zip_object:
         for item in zip_object.namelist():
-            print(item)
             if item in files_to_extract:
                 zip_object.extract(item, path)