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 +1,40 @@
# Audio Transcription Service - Dockerfile
# Uses faster-whisper for optimized speech-to-text transcription
FROM nvidia/cuda:12.1.0-runtime-ubuntu22.04
# Prevent interactive prompts during build
ENV DEBIAN_FRONTEND=noninteractive
ENV TZ=Europe/Bucharest
# Install Python 3.10 (default in Ubuntu 22.04) and system dependencies
RUN apt-get update && apt-get install -y \
python3 \
python3-pip \
python3-dev \
curl \
ffmpeg \
&& rm -rf /var/lib/apt/lists/* \
&& ln -sf /usr/bin/python3 /usr/bin/python
# Set working directory
WORKDIR /app
# Copy project files
COPY pyproject.toml /app/
COPY src/ /app/src/
# Install Python dependencies
RUN pip install --no-cache-dir -e .
# Create cache directory
RUN mkdir -p /root/.cache/huggingface
# Default port
ENV AUDIO_PORT=54300
# Expose port
EXPOSE 54300
# Run FastAPI with uvicorn
CMD python -m uvicorn audio.app:app --host 0.0.0.0 --port ${AUDIO_PORT}

View file

@ -0,0 +1,116 @@
#!/usr/bin/env bash
#
# Docker Compose Startup Script for Audio Transcription
#
# Usage: ./deploy/deploy.sh [OPTIONS]
#
# Options:
# --profile <api|api-nginx> 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" && "$ACTION" == "up" ]]; then
echo "ERROR: --profile is required"
echo "Options: api, api-nginx"
exit 1
fi
# Fail-fast required vars
check_required_var "AUDIO_MODEL"
check_required_var "AUDIO_DEVICE"
check_required_var "AUDIO_CACHE_DIR"
cd "$SCRIPT_DIR"
case $ACTION in
up)
echo "Starting Audio Transcription API with profile: $PROFILE"
echo " Model: $AUDIO_MODEL"
echo " Device: $AUDIO_DEVICE"
echo " Compute type: ${AUDIO_COMPUTE_TYPE:-int8}"
echo " Cache dir: $AUDIO_CACHE_DIR"
echo ""
# shellcheck disable=SC2086
exec docker compose --profile "$PROFILE" up $DETACH
;;
down)
if [[ -z "$PROFILE" ]]; then
echo "ERROR: --profile is required with --down"
exit 1
fi
echo "Stopping Audio Transcription 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 +1,95 @@
# Audio Module - Docker Compose Configuration
#
# Port Allocation (Dev AI Audio: 54300):
# 54300 - Audio API (Whisper STT service)
#
# Profiles:
# api - API server only
#
# Required environment variables (set in deploy/.env file):
# AUDIO_MODEL - Whisper model name (e.g., large-v3-turbo)
# AUDIO_DEVICE - Device: cuda or cpu
# AUDIO_COMPUTE_TYPE - Compute type: int8, float16, int8_float16
# AUDIO_CACHE_DIR - Model cache directory
#
# GPU Configuration:
# - Runs on GPU 0 (shared with Qwen3.5-35B-A3B)
# - Requires ~6GB VRAM for large-v3-turbo with int8
#
# Naming Convention: didiAI-{module}-{service}
#
# Network:
# Uses deploy_default network (shared with other modules)
networks:
deploy_default:
external: true
services:
# ==========================================================================
# Audio Transcription API Server
# ==========================================================================
audio-api:
container_name: didiAI-audio-api
image: didiai-audio-api
build:
context: ..
dockerfile: deploy/Dockerfile
ports:
- "54300:54300"
networks:
- deploy_default
environment:
# GPU configuration
- CUDA_VISIBLE_DEVICES=0
# External URL for OpenAPI spec (REQUIRED)
- AUDIO_EXTERNAL_URL=${AUDIO_EXTERNAL_URL}
# Whisper model configuration
- AUDIO_MODEL=${AUDIO_MODEL:-large-v3-turbo}
- AUDIO_DEVICE=${AUDIO_DEVICE:-cuda}
- AUDIO_COMPUTE_TYPE=${AUDIO_COMPUTE_TYPE:-int8}
- AUDIO_CACHE_DIR=${AUDIO_CACHE_DIR:-/root/.cache/huggingface}
# Transcription settings
- AUDIO_BEAM_SIZE=${AUDIO_BEAM_SIZE:-5}
- AUDIO_BEST_OF=${AUDIO_BEST_OF:-5}
- AUDIO_TEMPERATURE=${AUDIO_TEMPERATURE:-0.0}
# Server settings
- AUDIO_HOST=0.0.0.0
- AUDIO_PORT=54300
- AUDIO_LOG_LEVEL=${AUDIO_LOG_LEVEL:-INFO}
# Runtime config polling
- AUDIO_DASHBOARD_URL=${AUDIO_DASHBOARD_URL:-http://didiAI-dashboard:51300}
# Upload limits
- AUDIO_MAX_FILE_SIZE_MB=${AUDIO_MAX_FILE_SIZE_MB:-500}
volumes:
# Model cache (shared with other modules)
- ${AUDIO_CACHE_DIR:-/root/.cache/huggingface}:/root/.cache/huggingface
deploy:
resources:
reservations:
devices:
- driver: nvidia
device_ids: ['0']
capabilities: [gpu]
healthcheck:
test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:54300/health')"]
interval: 30s
timeout: 10s
retries: 3
start_period: 60s
restart: unless-stopped
profiles:
- api