Livrare LOT 1 - Didi

ai_platform/modules/video-analysis/deploy/docker-compose.yml

@@ -0,0 +1,130 @@
+# Video Analysis Module - Docker Compose Configuration
+#
+# Port Allocation (Dev AI Vision/Video: 54500-54600):
+#   54500 - vLLM BusterX (deepfake detection model)
+#   54600 - Video Analysis API
+#
+# Profiles:
+#   api       - API server only (requires external vLLM)
+#   api-vllm  - API + vLLM BusterX (GPU required)
+#
+# Required environment variables (set in deploy/.env file):
+#   HF_TOKEN                      - Hugging Face token for model downloads
+#   HF_CACHE_DIR                  - Cache directory for models
+#   VIDEO_ANALYSIS_RUNS_DIR       - Directory for analysis artifacts
+#
+# Naming Convention: didiAI-{module}-{service}
+#
+# Network:
+#   Uses deploy_default network (shared with other modules)
+
+networks:
+  deploy_default:
+    external: true
+
+services:
+  # ==========================================================================
+  # vLLM Server - BusterX (Deepfake Detection Model)
+  # ==========================================================================
+  # Vision-language model for video deepfake detection
+  # Runs on GPU 1 (Qwen3.5-35B-A3B uses GPU 0 via llm-inference module)
+  # BusterX is based on Qwen2.5-VL-7B (~17GB VRAM with optimizations)
+  vllm-buster:
+    container_name: didiAI-video-vllm-buster
+    image: vllm/vllm-openai:v0.8.5
+    ports:
+      - "54500:54500"
+    networks:
+      - deploy_default
+    volumes:
+      - ${HF_CACHE_DIR:-/cai2_ds_storage/hf_cache}:/root/.cache/huggingface
+    environment:
+      - HF_HOME=/root/.cache/huggingface
+      - HUGGING_FACE_HUB_TOKEN=${HF_TOKEN}
+      - CUDA_VISIBLE_DEVICES=1
+    command: >
+      --model l8cv/BusterX_plusplus
+      --host 0.0.0.0
+      --port 54500
+      --served-model-name busterx
+      --tensor-parallel-size 1
+      --max-model-len 32768
+      --gpu-memory-utilization 0.25
+      --trust-remote-code
+      --enable-prefix-caching
+      --disable-log-requests
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              device_ids: ['1']
+              capabilities: [gpu]
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:54500/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 10
+      start_period: 600s
+    restart: unless-stopped
+    profiles:
+      - api-vllm
+
+  # ==========================================================================
+  # Video Analysis API Server
+  # ==========================================================================
+  video-analysis-api:
+    container_name: didiAI-video-api
+    image: didiai-video-api
+    build:
+      context: ..
+      dockerfile: deploy/Dockerfile
+
+    ports:
+      - "54600:54600"
+    networks:
+      - deploy_default
+
+    environment:
+      # Server settings
+      - VIDEO_ANALYSIS_HOST=0.0.0.0
+      - VIDEO_ANALYSIS_PORT=54600
+      # External URL for OpenAPI spec (REQUIRED)
+      - VIDEO_ANALYSIS_EXTERNAL_URL=${VIDEO_ANALYSIS_EXTERNAL_URL}
+      # vLLM connection (points to vllm-buster container)
+      - VIDEO_ANALYSIS_VLLM_BASE_URL=${VIDEO_ANALYSIS_VLLM_BASE_URL:-http://didiAI-video-vllm-buster:54500}
+      - VIDEO_ANALYSIS_VLLM_MODEL=${VIDEO_ANALYSIS_VLLM_MODEL:-busterx}
+      - VIDEO_ANALYSIS_RUNS_DIR=${VIDEO_ANALYSIS_RUNS_DIR:-/app/runs}
+
+      # Optional tuning
+      - VIDEO_ANALYSIS_FRAMES=${VIDEO_ANALYSIS_FRAMES:-16}
+      - VIDEO_ANALYSIS_MAX_SIDE=${VIDEO_ANALYSIS_MAX_SIDE:-960}
+      - VIDEO_ANALYSIS_JPEG_QUALITY=${VIDEO_ANALYSIS_JPEG_QUALITY:-85}
+      - VIDEO_ANALYSIS_MAX_TOKENS=${VIDEO_ANALYSIS_MAX_TOKENS:-750}
+      - VIDEO_ANALYSIS_TEMPERATURE=${VIDEO_ANALYSIS_TEMPERATURE:-0.000001}
+      - VIDEO_ANALYSIS_REPETITION_PENALTY=${VIDEO_ANALYSIS_REPETITION_PENALTY:-1.05}
+
+      # Runtime config polling
+      - VIDEO_ANALYSIS_DASHBOARD_URL=${VIDEO_ANALYSIS_DASHBOARD_URL:-http://didiAI-dashboard:51300}
+
+      # Semantic analysis settings
+      - VIDEO_ANALYSIS_SEMANTIC_LLM_BASE_URL=${VIDEO_ANALYSIS_SEMANTIC_LLM_BASE_URL}
+      - VIDEO_ANALYSIS_SEMANTIC_AGGREGATION_MODEL=${VIDEO_ANALYSIS_SEMANTIC_AGGREGATION_MODEL}
+      - VIDEO_ANALYSIS_SEMANTIC_LLM_API_KEY=${VIDEO_ANALYSIS_SEMANTIC_LLM_API_KEY}
+
+    volumes:
+      # Persist artifacts on the host (module-root runs/ folder)
+      - ../runs:/app/runs
+
+    healthcheck:
+      test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:54600/health')"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 20s
+
+    restart: unless-stopped
+    profiles:
+      - api
+      - api-vllm
+