91 lines
3.5 KiB
Text
91 lines
3.5 KiB
Text
# didiAI Platform - Environment Configuration
|
|
# =============================================================================
|
|
# Copy this file to .env and configure the required values
|
|
#
|
|
# Usage:
|
|
# cp .env.example .env
|
|
# nano .env # Edit and fill in your values
|
|
# ./didiAI-deploy.sh up
|
|
#
|
|
# =============================================================================
|
|
|
|
# =============================================================================
|
|
# REQUIRED - Hugging Face (for model downloads)
|
|
# =============================================================================
|
|
# Get your token from: https://huggingface.co/settings/tokens
|
|
HF_TOKEN=your_huggingface_token_here
|
|
|
|
# Model cache directory (shared across all modules)
|
|
# Default: /cai2_ds_storage/hf_cache
|
|
HF_CACHE_DIR=/cai2_ds_storage/hf_cache
|
|
|
|
# =============================================================================
|
|
# REQUIRED - SearXNG (for Web module search)
|
|
# =============================================================================
|
|
# The Web module uses SearXNG (self-hosted metasearch engine) as its primary
|
|
# search provider. SearXNG must be running and accessible.
|
|
# Deploy SearXNG via its own docker-compose or use an existing instance.
|
|
WEB_SEARXNG_BASE_URL=http://didiAI-web-searxng:8080
|
|
|
|
# =============================================================================
|
|
# OPTIONAL - External LLM APIs (fallback/litellm backend)
|
|
# =============================================================================
|
|
# Only needed if using litellm backend or external fallbacks
|
|
|
|
# OpenRouter API (multiple models via one API)
|
|
# Get key from: https://openrouter.ai/keys
|
|
OPENROUTER_API_KEY=
|
|
|
|
# OpenAI API (for GPT models)
|
|
OPENAI_API_KEY=
|
|
|
|
# Anthropic API (for Claude models)
|
|
ANTHROPIC_API_KEY=
|
|
|
|
# =============================================================================
|
|
# OPTIONAL - Module Configuration
|
|
# =============================================================================
|
|
|
|
# LLM Module (defaults are set by deploy script)
|
|
LLM_DEFAULT_BACKEND=vllm
|
|
LLM_ENABLE_VLLM=true
|
|
LLM_ENABLE_LLAMACPP=false
|
|
|
|
# Audio Module (defaults are set by deploy script)
|
|
AUDIO_MODEL=large-v3-turbo
|
|
AUDIO_DEVICE=cuda
|
|
AUDIO_COMPUTE_TYPE=int8
|
|
AUDIO_CACHE_DIR=/cai2_ds_storage/hf_cache
|
|
|
|
# Video Module (defaults are set by deploy script)
|
|
VIDEO_ANALYSIS_VLLM_BASE_URL=http://didiAI-video-vllm-buster:8000
|
|
VIDEO_ANALYSIS_VLLM_MODEL=busterx
|
|
VIDEO_ANALYSIS_RUNS_DIR=/home/vasi/ml-projects/modules/video-analysis/runs
|
|
|
|
# Web Module (defaults are set automatically)
|
|
WEB_LLM_BASE_URL=http://didiAI-llm-api:14011
|
|
WEB_VISION_MODEL=qwen-vl
|
|
WEB_TEXT_MODEL=qwen3-235b
|
|
|
|
# =============================================================================
|
|
# GPU Configuration
|
|
# =============================================================================
|
|
# GPU 0: Qwen3.5-35B-A3B (text + vision, ~57GB VRAM) + Whisper (~2GB)
|
|
#
|
|
# CUDA_VISIBLE_DEVICES is set per module in docker-compose.yml
|
|
# No need to configure here unless changing GPU allocation
|
|
|
|
# =============================================================================
|
|
# Nginx Timeouts (optional tuning)
|
|
# =============================================================================
|
|
NGINX_CONNECT_TIMEOUT=60s
|
|
NGINX_SEND_TIMEOUT=120s
|
|
NGINX_READ_TIMEOUT=600s
|
|
|
|
# =============================================================================
|
|
# Logging (optional)
|
|
# =============================================================================
|
|
# Log levels: DEBUG, INFO, WARNING, ERROR, CRITICAL
|
|
CATALOG_LOG_LEVEL=INFO
|
|
AUDIO_LOG_LEVEL=INFO
|
|
WEB_LOG_LEVEL=INFO
|