-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy path.env.example
More file actions
117 lines (102 loc) · 5.67 KB
/
Copy path.env.example
File metadata and controls
117 lines (102 loc) · 5.67 KB
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
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
# =============================================================================
# Athena - Strategic Knowledge Copilot — Environment Configuration Template
#
# Copy this file to .env and fill in all required values.
# .env is in .gitignore and must NEVER be committed to version control.
# In production, inject these values via Azure Key Vault CSI driver or
# Kubernetes Secrets — do not use .env files in production containers.
# =============================================================================
# =============================================================================
# Application
# =============================================================================
ENVIRONMENT=production # production | development
DEBUG=false
LOG_LEVEL=INFO
# =============================================================================
# Database — Azure Database for PostgreSQL Flexible Server (production)
# In development, point to a local or Docker PostgreSQL instance
# =============================================================================
POSTGRES_USER=athena_user
POSTGRES_PASSWORD=CHANGE_ME_strong_password_here
POSTGRES_DB=athena_knowledge
POSTGRES_HOST=localhost # AKS: private endpoint FQDN
POSTGRES_PORT=5432
DATABASE_URL=postgresql+asyncpg://athena_user:CHANGE_ME_strong_password_here@localhost:5432/athena_knowledge
# =============================================================================
# Redis — Azure Cache for Redis (production)
# In development, point to a local or Docker Redis instance
# =============================================================================
REDIS_URL=redis://localhost:6379/0 # AKS: private endpoint host + TLS
# =============================================================================
# Qdrant Vector Store (in-cluster StatefulSet)
# =============================================================================
QDRANT_URL=http://localhost:6333
QDRANT_COLLECTION=documents
# =============================================================================
# Internal Service URLs (used for inter-service HTTP calls)
# =============================================================================
CONTEXT_ENGINE_SERVICE_URL=http://localhost:8001 # AKS: http://context-engine-service:8000
INFERENCE_SERVICE_URL=http://localhost:8002 # AKS: http://inference-service:8000
# =============================================================================
# Authentication & Security
# REQUIRED — no default. Generate with: openssl rand -hex 32
# =============================================================================
JWT_SECRET_KEY=CHANGE_ME_generate_with_openssl_rand_hex_32
JWT_ALGORITHM=HS256
ACCESS_TOKEN_EXPIRE_MINUTES=30
REFRESH_TOKEN_EXPIRE_DAYS=7
# =============================================================================
# CORS — space-separated or JSON list of allowed origins
# Empty = deny all cross-origin requests (correct for pure API backends)
# Example: CORS_ORIGINS=["https://app.example.com","https://admin.example.com"]
# =============================================================================
CORS_ORIGINS=[]
# =============================================================================
# Security Alerting
# Slack incoming webhook: https://hooks.slack.com/services/T.../B.../...
# Teams connector webhook: https://<tenant>.webhook.office.com/...
# Leave empty to disable webhook alerts (events still logged to audit_logs)
# =============================================================================
ALERT_WEBHOOK_URL=
# =============================================================================
# ML Models & vLLM
# =============================================================================
USE_VLLM=false # true = use vLLM server; false = CPU fallback
VLLM_URL=http://localhost:8080 # AKS: http://vllm-service:8080
VLLM_MODEL=abi-commits/qwen-query-optimizer
VLLM_GPU_MEMORY_UTILIZATION=0.90
VLLM_MAX_MODEL_LEN=4096
EMBEDDING_MODEL=BAAI/bge-small-en-v1.5
RERANKER_MODEL=cross-encoder/ms-marco-MiniLM-L-6-v2
LLM_MODEL=abi-commits/qwen-query-optimizer
HUGGING_FACE_HUB_TOKEN= # Required for gated models
# =============================================================================
# Query Optimization
# =============================================================================
CONFIDENCE_THRESHOLD=0.6
# =============================================================================
# Rate Limiting
# =============================================================================
RATE_LIMIT_REQUESTS=100
RATE_LIMIT_WINDOW=60
# =============================================================================
# Document Ingestion
# =============================================================================
CHUNK_SIZE=512
CHUNK_OVERLAP=50
MAX_FILE_SIZE_MB=50
# =============================================================================
# Context Engineering (for Context Engine Service)
# =============================================================================
MAX_CONTEXT_TOKENS=4096
# =============================================================================
# Observability — OpenTelemetry (Tempo in-cluster endpoint for AKS)
# Leave empty to disable trace export (traces collected in-process only)
# =============================================================================
OTEL_EXPORTER_OTLP_ENDPOINT= # AKS: http://tempo:4317
OTEL_SERVICE_NAME=athena-knowledge-copilot
# =============================================================================
# Uvicorn Workers (per container)
# =============================================================================
UVICORN_WORKERS=4 # API service
# UVICORN_WORKERS=2 # Context Engine / Inference services