Convert to full uv/pyproject dependency management

.github/workflows/test_app.yml

@@ -37,11 +37,10 @@ jobs:
         with:
           python-version: ${{ matrix.python-version }}
 
-      - name: Install dependencies
-        run: |
-          uv pip install --system -r requirements.txt
+      - name: Install the project
+        run: uv sync --locked --all-extras --dev
 
       - name: Run tests
         run: |
-          pytest tests/test_automated
-          pytest tests/test_alembic
+          uv run pytest tests/test_automated
+          uv run pytest tests/test_alembic

Dockerfile

@@ -6,12 +6,14 @@ COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /bin/
 # Set working directory
 WORKDIR /app
 
-COPY requirements.txt ./requirements.txt
+COPY pyproject.toml uv.lock ./
 
 # Install dependencies
-RUN uv pip install --system -r requirements.txt
-RUN playwright install chromium
-RUN playwright install-deps chromium
+RUN uv sync
+# Must call from the root directory because uv does not add playwright to path
+RUN /app/.venv/bin/playwright install-deps chromium
+RUN /app/.venv/bin/playwright install chromium
+
 
 # Copy project files
 COPY api ./api

README.md

@@ -18,6 +18,12 @@ core | A module which integrates other components, such as collector_manager and
 api | API for interacting with collector_manager, core, and collector_db
 local_database | Resources for setting up a test database for local development
 
+## Installation
+
+```
+uv sync
+```
+
 ## How to use
 
 1. Create an .env file in this directory with these contents, or set the environment variable another way: `VUE_APP_PDAP_API_KEY=KeyGoesHere`

pyproject.toml

@@ -1,3 +1,52 @@
 [project]
-name="source-collector"
-version="0.1.0"
+name = "data-source-identification"
+version = "0.1.0"
+requires-python = ">=3.11"
+dependencies = [
+    "aiohttp~=3.11.11",
+    "alembic~=1.14.0",
+    "apscheduler~=3.11.0",
+    "asyncpg~=0.30.0",
+    "beautifulsoup4>=4.12.3",
+    "bs4~=0.0.2",
+    "ckanapi~=4.8",
+    "datasets~=2.19.1",
+    "docker~=7.1.0",
+    "fastapi[standard]~=0.115.6",
+    "from-root~=1.3.0",
+    "google-api-python-client>=2.156.0",
+    "httpx~=0.28.1",
+    "huggingface-hub~=0.28.1",
+    "keras~=2.15.0",
+    "lxml~=5.1.0",
+    "marshmallow~=3.23.2",
+    "numpy~=1.26.4",
+    "openai~=1.60.1",
+    "pandas~=2.2.3",
+    "playwright~=1.49.1",
+    "psycopg2-binary~=2.9.6",
+    "psycopg[binary]~=3.1.20",
+    "pydantic~=2.10.6",
+    "pyjwt~=2.10.1",
+    "python-dotenv~=1.0.1",
+    "requests~=2.32.3",
+    "sqlalchemy~=2.0.36",
+    "starlette~=0.45.3",
+    "tensorflow-cpu~=2.15.1",
+    "tensorflow-io-gcs-filesystem==0.31.0",
+    "tqdm>=4.64.1",
+    "transformers~=4.40.2",
+    "urllib3~=1.26.18",
+    "uvicorn~=0.34.0",
+]
+
+[dependency-groups]
+dev = [
+    "docker>=7.1.0",
+    "pytest>=7.2.2",
+    "pytest-asyncio~=0.25.2",
+    "pytest-mock==3.12.0",
+    "pytest-timeout~=2.3.1",
+]
+
+

start_mirrored_local_app.py

@@ -1,10 +1,6 @@
 """
 Starts a local instance of the application utilizing a database
 mirrored from production.
-
-Because this is used for testing only, the docker module is not included in
-requirements.txt, and must be installed separately via
-`pip install docker`
 """
 import uvicorn