Livrare LOT 1 - Didi

This commit is contained in:
Dezvoltari Evotech 2026-06-25 14:13:25 -07:00
commit 5380c3fc63
990 changed files with 133308 additions and 0 deletions

View file

@ -0,0 +1,41 @@
# Video Analysis API Server
# Multi-stage build for smaller final image
FROM python:3.11.12-slim AS builder
# Install uv
COPY --from=ghcr.io/astral-sh/uv:0.10 /uv /usr/local/bin/uv
WORKDIR /app
# Copy project files
COPY pyproject.toml uv.lock README.md ./
COPY src/ ./src/
# Install dependencies (allow resolving to pick up new deps)
RUN uv sync --no-dev
# Production image
FROM python:3.11.12-slim
WORKDIR /app
# Copy virtual environment from builder
COPY --from=builder /app/.venv /app/.venv
# Copy source code
COPY src/ ./src/
ENV PATH="/app/.venv/bin:$PATH"
ENV PYTHONUNBUFFERED=1
ENV VIDEO_ANALYSIS_PORT=54600
# Health check (python urllib; no curl in slim)
HEALTHCHECK --interval=30s --timeout=10s --retries=3 \
CMD python -c "import urllib.request; import os; urllib.request.urlopen(f'http://localhost:{os.environ.get(\"VIDEO_ANALYSIS_PORT\", 54600)}/health')" || exit 1
EXPOSE 54600
CMD uvicorn video_analysis.app:app --host 0.0.0.0 --port ${VIDEO_ANALYSIS_PORT}

View file

@ -0,0 +1,116 @@
#!/usr/bin/env bash
#
# Docker Compose Startup Script for Video Analysis
#
# Usage: ./deploy/deploy.sh [OPTIONS]
#
# Options:
# --profile <api|api-vllm> Docker compose profile
# --detach Run in detached mode
# --down Stop and remove containers
# --logs Show logs
# --help Show this help message
#
# Required: Set environment variables in deploy/.env file or export them before running.
# See ../.env.example (module root) for the full list of variables.
#
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
# Load .env file ONLY from deploy/ directory
if [[ -f "$SCRIPT_DIR/.env" ]]; then
echo "Loading environment from: $SCRIPT_DIR/.env"
set -a
source "$SCRIPT_DIR/.env"
set +a
fi
PROFILE=""
DETACH=""
ACTION="up"
show_help() {
sed -n '2,18p' "$0" | sed 's/^# //' | sed 's/^#//'
exit 0
}
check_required_var() {
local var_name="$1"
if [[ -z "${!var_name:-}" ]]; then
echo "ERROR: Required environment variable $var_name is not set"
echo "Set it in deploy/.env file or export it before running this script"
exit 1
fi
}
while [[ $# -gt 0 ]]; do
case $1 in
--profile)
PROFILE="$2"
shift 2
;;
--detach|-d)
DETACH="-d"
shift
;;
--down)
ACTION="down"
shift
;;
--logs)
ACTION="logs"
shift
;;
--help|-h)
show_help
;;
*)
echo "Unknown option: $1"
echo "Use --help for usage information"
exit 1
;;
esac
done
# Require profile when bringing up
if [[ -z "$PROFILE" && "$ACTION" == "up" ]]; then
echo "ERROR: --profile is required"
echo "Options: api, api-vllm"
exit 1
fi
# Fail-fast required vars for wrapper <-> vLLM wiring
check_required_var "VIDEO_ANALYSIS_VLLM_BASE_URL"
check_required_var "VIDEO_ANALYSIS_VLLM_MODEL"
check_required_var "VIDEO_ANALYSIS_RUNS_DIR"
check_required_var "VIDEO_ANALYSIS_EXTERNAL_URL"
cd "$SCRIPT_DIR"
case $ACTION in
up)
echo "Starting Video Analysis with profile: $PROFILE"
echo " vLLM base URL: $VIDEO_ANALYSIS_VLLM_BASE_URL"
echo " vLLM model: $VIDEO_ANALYSIS_VLLM_MODEL"
echo " runs dir: $VIDEO_ANALYSIS_RUNS_DIR"
echo ""
# shellcheck disable=SC2086
exec docker compose --profile "$PROFILE" up $DETACH
;;
down)
if [[ -z "$PROFILE" ]]; then
echo "ERROR: --profile is required with --down"
exit 1
fi
echo "Stopping Video Analysis containers..."
exec docker compose --profile "$PROFILE" down
;;
logs)
if [[ -z "$PROFILE" ]]; then
echo "ERROR: --profile is required with --logs"
exit 1
fi
exec docker compose --profile "$PROFILE" logs -f
;;
esac

View file

@ -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

View file

@ -0,0 +1,52 @@
upstream video_analysis_api {
# With host networking, the API binds host:8007
server 127.0.0.1:8007;
keepalive 32;
}
server {
listen 80;
server_name _;
# Timeouts (video processing + vLLM may take time)
proxy_connect_timeout 60s;
proxy_send_timeout 300s;
proxy_read_timeout 600s;
# Allow large video uploads
client_max_body_size 500M;
# Disable buffering for large uploads / streaming
proxy_buffering off;
proxy_request_buffering off;
location /health {
access_log off;
proxy_pass http://video_analysis_api/health;
proxy_http_version 1.1;
proxy_set_header Host $host;
proxy_set_header Connection "";
}
location / {
proxy_pass http://video_analysis_api;
proxy_http_version 1.1;
# Forward client info
proxy_set_header Host $host;
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_set_header X-Forwarded-Proto $scheme;
# Streaming friendliness (even if not currently used)
proxy_set_header Connection "";
proxy_set_header X-Accel-Buffering no;
proxy_cache off;
chunked_transfer_encoding off;
# Request correlation
proxy_set_header X-Request-ID $request_id;
}
}

View file

@ -0,0 +1,41 @@
upstream video_analysis_api {
server didiAI-video-api:8011;
keepalive 32;
}
server {
listen 80;
server_name _;
proxy_connect_timeout ${NGINX_CONNECT_TIMEOUT};
proxy_send_timeout ${NGINX_SEND_TIMEOUT};
proxy_read_timeout ${NGINX_READ_TIMEOUT};
# Larger uploads (videos)
client_max_body_size 500M;
location /health {
access_log off;
proxy_pass http://video_analysis_api/health;
proxy_http_version 1.1;
proxy_set_header Host $host;
}
location / {
proxy_pass http://video_analysis_api;
proxy_http_version 1.1;
proxy_set_header Host $host;
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
# SSE-friendly (safe even if you don't stream yet)
proxy_set_header Connection '';
proxy_set_header X-Accel-Buffering no;
proxy_buffering off;
proxy_cache off;
chunked_transfer_encoding off;
proxy_set_header X-Request-ID $request_id;
}
}