feat: setup dataset enrichment app codebase and scripts

Dockerfile

@@ -0,0 +1,35 @@
+FROM python:3.12-slim
+
+ENV PYTHONUNBUFFERED=1 \
+    UV_SYSTEM_PYTHON=1 \
+    APP_DATA_DIR=/data \
+    VIDEO_ARCHIVE=/videos
+
+# ffmpeg does the trimming and frame extraction; libgl1/libglib2.0-0 are what
+# OpenCV needs once ultralytics pulls in the non-headless build.
+RUN apt-get update && apt-get install -y --no-install-recommends \
+        ffmpeg libgl1 libglib2.0-0 \
+    && rm -rf /var/lib/apt/lists/*
+
+# uv comes from PyPI rather than `COPY --from=ghcr.io/astral-sh/uv`: pulling it
+# from a second registry made every build fail whenever ghcr.io was unreachable,
+# even with all the dependency layers already cached. This is the only pip call
+# in the project — bootstrapping the tool that installs everything else.
+RUN pip install --no-cache-dir uv
+
+WORKDIR /app
+
+# Dependencies first so code edits don't re-download ~3 GB of CUDA wheels.
+COPY requirements.txt ./
+RUN uv pip install -r requirements.txt
+
+# The vendored SAM3 declares timm/ftfy/regex/tqdm itself, so this install keeps
+# its dependencies (unlike einops + pycocotools, which it needs but never
+# declares — those are pinned in requirements.txt).
+COPY sam3/ ./sam3/
+RUN uv pip install -e ./sam3
+
+COPY backend/ ./backend/
+
+EXPOSE 8000
+CMD ["uvicorn", "backend.main:app", "--host", "0.0.0.0", "--port", "8000"]