-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy path.env.example
More file actions
168 lines (120 loc) · 5.45 KB
/
.env.example
File metadata and controls
168 lines (120 loc) · 5.45 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
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
# LLM-Latency-Lens Environment Configuration
# Copy this file to .env and fill in your values
# =============================================================================
# LLM Provider API Keys
# =============================================================================
# OpenAI API Key
# Get from: https://platform.openai.com/api-keys
OPENAI_API_KEY=sk-...
# Anthropic API Key
# Get from: https://console.anthropic.com/settings/keys
ANTHROPIC_API_KEY=sk-ant-...
# Google (Vertex AI) API Key
# Get from: https://console.cloud.google.com/apis/credentials
GOOGLE_API_KEY=...
# =============================================================================
# Application Configuration
# =============================================================================
# Rust logging level (error, warn, info, debug, trace)
RUST_LOG=info
# Enable Rust backtraces (0=off, 1=on, full=full traces)
RUST_BACKTRACE=1
# =============================================================================
# Prometheus Configuration
# =============================================================================
# Prometheus bind host
PROMETHEUS_HOST=0.0.0.0
# Prometheus bind port
PROMETHEUS_PORT=9090
# =============================================================================
# Grafana Configuration
# =============================================================================
# Grafana admin username
GF_ADMIN_USER=admin
# Grafana admin password (CHANGE IN PRODUCTION!)
GF_ADMIN_PASSWORD=change_me_in_production
# Grafana root URL (for production with reverse proxy)
GF_ROOT_URL=http://localhost:3000
# =============================================================================
# TLS/SSL Configuration (Production)
# =============================================================================
# Let's Encrypt email for certificate generation
ACME_EMAIL=your-email@example.com
# =============================================================================
# Alert Configuration
# =============================================================================
# Slack webhook URL for alerts
SLACK_WEBHOOK_URL=https://hooks.slack.com/services/YOUR/SLACK/WEBHOOK
# =============================================================================
# Database Configuration (Optional)
# =============================================================================
# PostgreSQL connection string (if using database backend)
# DATABASE_URL=postgresql://user:password@localhost:5432/llm_metrics
# =============================================================================
# Observability Configuration (Optional)
# =============================================================================
# OpenTelemetry endpoint
# OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4317
# OpenTelemetry service name
# OTEL_SERVICE_NAME=llm-latency-lens
# =============================================================================
# Rate Limiting Configuration (Optional)
# =============================================================================
# Maximum requests per second
# MAX_RPS=100
# Burst size for rate limiter
# BURST_SIZE=10
# =============================================================================
# Retry Configuration (Optional)
# =============================================================================
# Maximum retry attempts
# MAX_RETRIES=3
# Retry delay in milliseconds
# RETRY_DELAY_MS=1000
# =============================================================================
# Timeout Configuration (Optional)
# =============================================================================
# Request timeout in seconds
# REQUEST_TIMEOUT_SECONDS=30
# Connection timeout in seconds
# CONNECT_TIMEOUT_SECONDS=10
# =============================================================================
# Phase 2 - Operational Intelligence (Layer 1) Configuration
# =============================================================================
# REQUIRED: RuVector Service URL (HARD STARTUP FAILURE if unavailable)
# Get from: Google Secret Manager or deployment config
RUVECTOR_SERVICE_URL=https://ruvector-service.example.com
# REQUIRED: RuVector API Key (from Google Secret Manager)
RUVECTOR_API_KEY=your-ruvector-api-key
# REQUIRED: Agent identification
AGENT_NAME=llm-latency-lens
AGENT_DOMAIN=latency-lens
AGENT_PHASE=phase2
AGENT_LAYER=layer1
# =============================================================================
# Performance Budget Configuration
# =============================================================================
# Maximum tokens per request (default: 1000)
MAX_TOKENS=1000
# Maximum latency in milliseconds (default: 2000)
MAX_LATENCY_MS=2000
# Maximum API calls per run (default: 3)
MAX_CALLS_PER_RUN=3
# =============================================================================
# Caching Configuration
# =============================================================================
# Minimum cache TTL in seconds (default: 60)
CACHE_MIN_TTL_SECS=60
# Maximum cache TTL in seconds (default: 120)
CACHE_MAX_TTL_SECS=120
# Maximum cache entries (default: 1000)
CACHE_MAX_ENTRIES=1000
# Enable cache statistics (default: true)
CACHE_ENABLE_STATS=true
# =============================================================================
# Signal Emission Configuration
# =============================================================================
# Enable telemetry emission (default: true)
EMIT_TELEMETRY=true
# Enable signal emission for anomaly/drift/lineage/latency (default: true)
EMIT_SIGNALS=true