eval-llm-in-production/.env.example at main · DataScientest/eval-llm-in-production · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
# =============================================================================
# LLMOps Secure API - Environment Configuration
# =============================================================================
# Copy this file to .env and fill in your values
# NEVER commit .env to version control!
# =============================================================================

# -----------------------------------------------------------------------------
# REQUIRED - Security Configuration
# -----------------------------------------------------------------------------
# JWT secret for token signing - MUST be at least 32 characters
# Generate with: openssl rand -hex 32
JWT_SECRET_KEY=your-secure-random-key-at-least-32-characters-long

# -----------------------------------------------------------------------------
# LLM Provider API Keys (at least one required)
# -----------------------------------------------------------------------------
# OpenAI API Key (for gpt-4o-secondary model)
OPENAI_API_KEY=sk-your-openai-api-key

# Groq API Key (for groq-kimi-primary model - recommended)
GROQ_API_KEY=gsk-your-groq-api-key

# Google Gemini API Key (for gemini-third model)
GEMINI_API_KEY=your-gemini-api-key

# OpenRouter API Key (for openrouter-fallback model)
OPENROUTER_API_KEY=sk-or-your-openrouter-api-key

# HuggingFace Token (for TEI embeddings)
HF_TOKEN=hf_your-huggingface-token

# -----------------------------------------------------------------------------
# Service URLs (defaults work with Docker Compose)
# -----------------------------------------------------------------------------
# LiteLLM Proxy URL
LITELLM_URL=http://litellm:8000

# MLflow Tracking URI
MLFLOW_TRACKING_URI=http://mlflow:5000

# Qdrant Vector Database URL
QDRANT_URL=http://qdrant:6333

# TEI Embeddings Service URL
TEI_URL=http://tei-embeddings:80

# -----------------------------------------------------------------------------
# Cache Configuration
# -----------------------------------------------------------------------------
# Cache TTL in seconds (default: 1800 = 30 minutes)
CACHE_TTL=1800

# Semantic cache similarity threshold (0.0 to 1.0)
QDRANT_SIMILARITY_THRESHOLD=0.70

# -----------------------------------------------------------------------------
# CORS Configuration (comma-separated origins)
# -----------------------------------------------------------------------------
# For development:
CORS_ORIGINS=http://localhost:3000,http://localhost:8000

# For production, specify your actual domains:
# CORS_ORIGINS=https://app.yourdomain.com,https://admin.yourdomain.com

# -----------------------------------------------------------------------------
# Logging Configuration
# -----------------------------------------------------------------------------
# Log level: DEBUG, INFO, WARNING, ERROR, CRITICAL
LOG_LEVEL=INFO

# LiteLLM log level
LITELLM_LOG=INFO