-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy path.env.example
More file actions
120 lines (87 loc) · 3.84 KB
/
Copy path.env.example
File metadata and controls
120 lines (87 loc) · 3.84 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
# CHARM Market Intelligence Engine - Environment Configuration
# Copy this file to .env and fill in the values.
# Lines starting with # are comments.
# =============================================================================
# CORE FLAGS (safe defaults - no external calls)
# =============================================================================
# Store processed data in SQLite database (data/charm.db)
USE_SQLITE=true
# Sync data to Google Sheets (requires credentials below)
USE_SHEETS=false
# Generate LLM-powered insights (requires API key or Ollama)
USE_LLM=false
# Enable experimental clustering analysis
USE_CLUSTERING=false
# =============================================================================
# REPRODUCIBILITY
# =============================================================================
# Random seed for deterministic outputs (word clouds, clustering)
CHARM_SEED=42
# =============================================================================
# STREAMLIT APP SAFETY
# =============================================================================
# Allow running the pipeline from the Streamlit app.
# Keep this false for shared or hosted environments.
ALLOW_PIPELINE_RUN=false
# =============================================================================
# PIPELINE STEP TOGGLES
# =============================================================================
# These let you skip parts of the pipeline when running from the Streamlit wizard.
# They default to true to match the normal end-to-end behavior.
PIPELINE_SCRAPE=true
PIPELINE_REPORTS=true
PIPELINE_NLP=true
PIPELINE_SENTIMENT=true
PIPELINE_GEOCODE=true
# =============================================================================
# SCRAPING CONFIGURATION
# =============================================================================
# User-Agent header for web requests (include contact info per robots.txt guidelines)
USER_AGENT="CHARM/1.0 (mailto:your-email@example.com)"
# Rate limiting: number of concurrent fetches
SCRAPER_MAX_WORKERS=4
# Rate limiting: minimum seconds between requests
SCRAPER_REQUEST_INTERVAL=0.8
# =============================================================================
# GEOCODING (Nominatim / OpenStreetMap)
# =============================================================================
# Contact email required by Nominatim usage policy
GEOCODE_CONTACT_EMAIL=your-email@example.com
# Optional: custom user agent for geocoding
GEOCODE_USER_AGENT=""
# =============================================================================
# GOOGLE SHEETS (optional - only if USE_SHEETS=true)
# =============================================================================
# Path to service account JSON key file
GOOGLE_SERVICE_ACCOUNT_FILE=secrets/service_account.json
# Google Sheet ID (from the URL: docs.google.com/spreadsheets/d/THIS_PART/edit)
GOOGLE_SHEET_ID=
# Worksheet names
GOOGLE_SHEET_WORKSHEET=jobs
GOOGLE_SHEET_WORKSHEET_REPORTS=reports
# =============================================================================
# LLM CONFIGURATION (optional - only if USE_LLM=true)
# =============================================================================
# Provider: "openai", "ollama", or "openai_compat"
LLM_PROVIDER=openai
# Model name
LLM_MODEL=gpt-4o-mini
# Maximum tokens in LLM response
LLM_MAX_TOKENS=1200
# For OpenAI
OPENAI_API_KEY=
# For Ollama (local)
OLLAMA_BASE_URL=http://localhost:11434
# For OpenAI-compatible servers (vLLM, etc.)
LLM_BASE_URL=
# For Hugging Face hosted inference (optional)
HF_TOKEN=
HF_MODEL=
HF_INFERENCE_URL=
# =============================================================================
# NOTIFICATIONS (optional)
# =============================================================================
# Mattermost incoming webhook URL
MATTERMOST_WEBHOOK_URL=
# URL to your dashboard (for notification links)
DASHBOARD_URL=