slight-backend/env.example at main · ReaganCn/slight-backend · 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
# Database Configuration
DATABASE_URL="postgresql+asyncpg://postgres:postgres@localhost:5432/competitordb"
AWS_DATABASE_URL="postgresql+asyncpg://USERNAME:PASSWORD@RDS_ENDPOINT:5432/competitordb"

# API Keys
OPENAI_API_KEY="your-openai-api-key-here"

# Scraping Configuration
PREFERRED_SCRAPER="playwright"          # Options: 'playwright' (free), 'scrapingbee' (paid), 'auto'
PLAYWRIGHT_BROWSERS_PATH="/Users/reagan/Library/Caches/ms-playwright"
SCRAPINGBEE_API_KEY="your-scrapingbee-api-key-here"  # Only needed if using ScrapingBee
COHERE_API_KEY="your-cohere-api-key-here"  # Fallback AI for URL categorization when OpenAI quota exceeded

# URL Discovery Configuration (NEW)
LANGCHAIN_SEARCH_RESULTS_LIMIT="10"              # Number of search results to analyze
URL_DISCOVERY_CONFIDENCE_THRESHOLD="0.7"         # Minimum confidence score for URL suggestions

# Social Media API Keys (NEW)
LINKEDIN_CLIENT_ID="your_linkedin_client_id"
LINKEDIN_CLIENT_SECRET="your_linkedin_client_secret"
LINKEDIN_EMAIL="your_linkedin_email"              # For unofficial API
LINKEDIN_PASSWORD="your_linkedin_password"        # For unofficial API

TWITTER_BEARER_TOKEN="your_twitter_bearer_token"  # Twitter API v2
TWITTER_API_KEY="your_twitter_api_key"
TWITTER_API_SECRET="your_twitter_api_secret"

INSTAGRAM_ACCESS_TOKEN="your_instagram_access_token"
INSTAGRAM_USERNAME="your_instagram_username"       # For unofficial API
INSTAGRAM_PASSWORD="your_instagram_password"       # For unofficial API

TIKTOK_ACCESS_TOKEN="your_tiktok_access_token"

# AWS Configuration (for local testing)
AWS_ACCESS_KEY_ID="your-aws-access-key"
AWS_SECRET_ACCESS_KEY="your-aws-secret-key"
AWS_DEFAULT_REGION="us-east-1"

# Environment
ENVIRONMENT="dev"

# Lambda Configuration (for local testing)
LAMBDA_TIMEOUT=30
LAMBDA_MEMORY=128

# 🔍 RELIABLE SEARCH API OPTIONS (Recommended setup)

# 1. Google Custom Search API (100 free queries/day) - HIGHLY RECOMMENDED
# Get keys at: https://developers.google.com/custom-search/v1/introduction
# Create custom search engine at: https://cse.google.com/cse/create/new
GOOGLE_CSE_API_KEY="your_google_custom_search_api_key_here"
GOOGLE_CSE_ID="your_custom_search_engine_id_here"

# 2. Brave Search API (2,000 free queries/month) - EXCELLENT BACKUP
# Get key at: https://brave.com/search/api/
# Independent search index, privacy-focused
BRAVE_API_KEY="your_brave_search_api_key_here"

# Note: DuckDuckGo has been removed due to reliability issues
# (frequent timeouts, rate limiting, inconsistent results)

# Social Media API Keys
TWITTER_BEARER_TOKEN="your_twitter_bearer_token_here"
LINKEDIN_API_KEY="your_linkedin_api_key_here"
INSTAGRAM_ACCESS_TOKEN="your_instagram_access_token_here"
TIKTOK_API_KEY="your_tiktok_api_key_here"

# URL Discovery Settings
URL_DISCOVERY_MAX_RESULTS=10
URL_DISCOVERY_TIMEOUT=30
URL_DISCOVERY_DELAY=2

# Social Media Settings
SOCIAL_MEDIA_TIMEOUT=15
SOCIAL_MEDIA_MAX_POSTS=50

# 💡 COST OPTIMIZATION TIPS:
# - Start with Google CSE (most reliable, 100 free queries/day)
# - Add Brave Search as backup (2,000 free queries/month)
# - Sitemap fallback is used automatically when search APIs fail
# - Expected monthly cost: $0-5 for most use cases
# - DuckDuckGo removed due to reliability issues