hackanova5.0/.env.example at main · Shreekant-code/hackanova5.0 · 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
# ===============================
# MERN + AI Crawler Shared Config
# ===============================

# MongoDB server used by both Node backend and crawler
MONGODB_URI=mongodb://localhost:27017

# Existing backend DB name (must match Database/db_connect.js usage)
APP_DB_NAME=Hacknova5

# AGNO + Gemini credentials for crawler extraction
GEMINI_API_KEY=your_gemini_api_key_here
AGNO_MODEL_ID=gemini-2.5-flash

# Optional MyScheme public API key used for JS-page fallback crawling
MYSCHEME_API_KEY=tYTy5eEhlu9rFjyxuCr7ra7ACp4dv1RH8gWuHTDc

# Cloudinary configuration (for upload service / frontend integration)
CLOUDINARY_CLOUD_NAME=your_cloud_name
CLOUDINARY_API_KEY=your_cloudinary_api_key
CLOUDINARY_API_SECRET=your_cloudinary_api_secret
CLOUDINARY_UPLOAD_PRESET=
CLOUDINARY_FOLDER=

# Optional crawler tuning
CRAWLER_TIMEOUT_SECONDS=20
CRAWLER_RETRIES=2
MAX_TEXT_CHARS=20000
MAX_SCHEME_LINKS=200

# Optional document extraction limits
MAX_DOCUMENT_BYTES=8388608
OCR_TIMEOUT_MS=30000
GEMINI_DOC_TIMEOUT_MS=15000

# Document validation toggles
ENFORCE_CLOUDINARY_URL=false
REJECT_EMPTY_EXTRACTION=true

# ===============================
# Automation Layer Config
# ===============================

# Safety policy: allowed official domain suffixes for portal automation
OFFICIAL_PORTAL_SUFFIXES=.gov.in,.nic.in,.gov,.ac.in
# Additional official hosts if a valid portal does not use gov/nic suffix
# Example: maandhan.in,www.maandhan.in
OFFICIAL_PORTAL_HOSTS=

# Crawl controls
AUTOMATION_CRAWL_TIMEOUT_MS=15000
AUTOMATION_USE_PLAYWRIGHT_CRAWLER=false
AUTOMATION_FORM_CACHE_TTL_MINUTES=60

# AI field understanding
AUTOMATION_ENABLE_GEMINI_FIELD_MAPPING=true
AUTOMATION_GEMINI_TIMEOUT_MS=12000

# Execution controls
# "simulation" (safe default) or "playwright" (real browser automation)
AUTOMATION_EXECUTION_MODE=simulation
AUTOMATION_EXECUTION_TIMEOUT_MS=60000

# Fallback guide generation
AUTOMATION_AUTO_FALLBACK_GUIDE=true
AUTOMATION_ENABLE_FALLBACK_GUIDE=true
AUTOMATION_ENABLE_BROWSER_PDF_CAPTURE=true
AUTOMATION_FALLBACK_TIMEOUT_MS=20000

# Autofill strategy
# true: fill required + optional mapped fields
# false: fill required mapped fields only
AUTOMATION_FILL_OPTIONAL_FIELDS=true

# Execution behavior
# true from request body will fill/select/upload actions but skip submit action
# request key: dry_run_fill_only