SearchFlow/.env.example at main · PohTeyToe/SearchFlow · 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
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
# SearchFlow Environment Configuration
# Copy this file to .env and customize values for your environment.
#
# Usage:
#   cp .env.example .env
#   # Edit .env with your values
#   docker-compose up -d

# ============================================
# DATABASE
# ============================================

# DuckDB warehouse file path (inside containers)
DUCKDB_PATH=/data/searchflow.duckdb

# PostgreSQL -- used for Airflow metadata and CRM simulation
POSTGRES_HOST=postgres
POSTGRES_PORT=5432
POSTGRES_DB=searchflow
POSTGRES_USER=searchflow
POSTGRES_PASSWORD=searchflow123

# ============================================
# REDIS
# ============================================

REDIS_HOST=redis
REDIS_PORT=6379

# ============================================
# AIRFLOW
# ============================================

AIRFLOW__CORE__SQL_ALCHEMY_CONN=postgresql+psycopg2://airflow:airflow@postgres:5432/airflow
AIRFLOW__CORE__EXECUTOR=LocalExecutor
AIRFLOW__CORE__LOAD_EXAMPLES=false
AIRFLOW_UID=50000

# ============================================
# EVENT GENERATOR
# ============================================

# Events emitted per second in continuous mode
EVENTS_PER_SECOND=10

# Funnel conversion rates (industry benchmarks for travel)
CLICK_THROUGH_RATE=0.30
CONVERSION_RATE=0.10

# Number of simulated user accounts
USER_POOL_SIZE=10000

# Fraction of traffic from anonymous (non-logged-in) visitors
ANONYMOUS_RATE=0.40

# ============================================
# ML ENGINE
# ============================================

# Directory where trained model artifacts are stored
MODEL_PATH=/app/models

# Redis cache TTL for inference results (seconds)
CACHE_TTL=3600

# Dashboard URL for CORS (Vercel deployment)
DASHBOARD_URL=https://dashboard-nine-lilac-71.vercel.app

# API key for ML Engine authentication (leave empty to disable auth in dev)
ML_API_KEY=

# ============================================
# KAFKA
# ============================================

# Kafka broker address (internal Docker network)
KAFKA_BOOTSTRAP_SERVERS=kafka:9092

# ============================================
# MLFLOW
# ============================================

# MLflow tracking server URL (used by training scripts)
MLFLOW_TRACKING_URI=http://mlflow:5000

# ============================================
# DBT
# ============================================

DBT_PROFILES_DIR=/dbt

# ============================================
# SPARK
# ============================================

SPARK_MODE=master
SPARK_MASTER_URL=spark://spark:7077

# ============================================
# SEARCH ASSISTANT
# ============================================

# LLM backend: "anthropic" (default) or "claude-cli"
LLM_BACKEND=anthropic

# Anthropic API key for ChatAnthropic (required when LLM_BACKEND=anthropic)
# ANTHROPIC_API_KEY=sk-ant-...

# ML Engine URL (internal Docker network)
ML_ENGINE_URL=http://ml-engine:8000

# ============================================
# SNOWFLAKE (Production -- Optional)
# ============================================
# Uncomment and fill in for production deployment.
# SNOWFLAKE_ACCOUNT=
# SNOWFLAKE_USER=
# SNOWFLAKE_PASSWORD=
# SNOWFLAKE_WAREHOUSE=TRANSFORM_WH
# SNOWFLAKE_DATABASE=SEARCHFLOW
# SNOWFLAKE_SCHEMA=PUBLIC