Livrare LOT 1 - Didi

ai_platform/modules/extractors/deploy/Dockerfile

@@ -0,0 +1,43 @@
+# syntax=docker/dockerfile:1
+# Multi-stage build for the extractors service. Non-root runtime, ffmpeg/ffprobe
+# available for video metadata and audio decoding.
+
+FROM python:3.11-slim AS builder
+
+WORKDIR /build
+COPY pyproject.toml ./
+COPY src ./src
+RUN pip install --no-cache-dir --upgrade pip build \
+    && pip wheel --no-cache-dir --wheel-dir /wheels ".[ml]"
+
+FROM python:3.11-slim AS runtime
+
+# ffmpeg provides ffmpeg/ffprobe; libgl1/libglib/libxcb are the OpenCV runtime
+# libs needed by ultralytics (YOLO).
+RUN apt-get update \
+    && apt-get install -y --no-install-recommends \
+        ffmpeg \
+        libgl1 \
+        libglib2.0-0 \
+        libxcb1 \
+    && rm -rf /var/lib/apt/lists/*
+
+RUN useradd --create-home --uid 10001 appuser
+WORKDIR /app
+
+COPY --from=builder /wheels /wheels
+RUN pip install --no-cache-dir /wheels/*.whl && rm -rf /wheels
+
+USER appuser
+
+ENV EXTRACTORS_HOST=0.0.0.0 \
+    EXTRACTORS_PORT=54400
+
+EXPOSE 54400
+
+HEALTHCHECK --interval=30s --timeout=5s --start-period=10s --retries=3 \
+    CMD python -c "import urllib.request,os,sys; \
+url=f'http://127.0.0.1:{os.getenv(\"EXTRACTORS_PORT\",\"54400\")}/health'; \
+sys.exit(0 if urllib.request.urlopen(url, timeout=3).status==200 else 1)"
+
+CMD ["sh", "-c", "uvicorn extractors.app:app --host $EXTRACTORS_HOST --port $EXTRACTORS_PORT"]

ai_platform/modules/extractors/deploy/deploy.sh

@@ -0,0 +1,41 @@
+#!/usr/bin/env bash
+# Deploy the extractors service. Fail-fast on missing config (no silent defaults).
+set -euo pipefail
+
+cd "$(dirname "$0")"
+[[ -f .env ]] && source .env
+
+check_required_var() {
+    if [[ -z "${!1:-}" ]]; then
+        echo "ERROR: $1 not set (see .env.example)" >&2
+        exit 1
+    fi
+}
+
+usage() {
+    cat <<EOF
+Usage: $0 {up|down|logs|build|test}
+
+Required env vars (set in .env):
+  EXTRACTORS_TAG             Image tag (e.g. 0.1.0)
+  EXTRACTORS_PORT            Host/container port (e.g. 54400 dev / 14400 prod)
+  EXTRACTORS_MAX_UPLOAD_MB   Max upload size in MB (e.g. 100)
+
+Optional:
+  EXTRACTORS_LLM_GATEWAY_URL LLM gateway base URL (sentiment/NER/OCR only)
+  EXTRACTORS_LLM_MODEL       Model alias (default: qwen3.5)
+EOF
+}
+
+check_required_var "EXTRACTORS_TAG"
+check_required_var "EXTRACTORS_PORT"
+check_required_var "EXTRACTORS_MAX_UPLOAD_MB"
+
+case "${1:-}" in
+    up)    docker compose up -d --build ;;
+    down)  docker compose down ;;
+    logs)  docker compose logs -f ;;
+    build) docker compose build ;;
+    test)  docker build -f deploy/Dockerfile --target builder -t extractors-test .. ;;
+    *)     usage; exit 1 ;;
+esac

ai_platform/modules/extractors/deploy/docker-compose.yml

@@ -0,0 +1,29 @@
+services:
+  extractors:
+    build:
+      context: ..
+      dockerfile: deploy/Dockerfile
+    image: extractors:${EXTRACTORS_TAG}
+    container_name: extractors
+    restart: unless-stopped
+    environment:
+      EXTRACTORS_HOST: "0.0.0.0"
+      EXTRACTORS_PORT: "${EXTRACTORS_PORT}"
+      EXTRACTORS_MAX_UPLOAD_MB: "${EXTRACTORS_MAX_UPLOAD_MB}"
+      # Optional, only needed by sentiment/NER/OCR (added later):
+      EXTRACTORS_LLM_GATEWAY_URL: "${EXTRACTORS_LLM_GATEWAY_URL:-}"
+      EXTRACTORS_LLM_MODEL: "${EXTRACTORS_LLM_MODEL:-qwen3.5}"
+    ports:
+      - "${EXTRACTORS_PORT}:${EXTRACTORS_PORT}"
+    healthcheck:
+      test: ["CMD", "python", "-c", "import urllib.request,os,sys; sys.exit(0 if urllib.request.urlopen(f'http://127.0.0.1:{os.getenv(\"EXTRACTORS_PORT\")}/health',timeout=3).status==200 else 1)"]
+      interval: 30s
+      timeout: 5s
+      retries: 3
+      start_period: 10s
+    networks:
+      - didi-network
+
+networks:
+  didi-network:
+    external: true