Initial commit: Korrith website, assessment API, PocketBase schema, Docker/Coolify deployment
This commit is contained in:
@@ -0,0 +1,19 @@
|
||||
<IfModule mod_rewrite.c>
|
||||
RewriteEngine On
|
||||
RewriteBase /
|
||||
RewriteCond %{REQUEST_FILENAME} !-f
|
||||
RewriteCond %{REQUEST_FILENAME} !-d
|
||||
RewriteRule ^ index.html [L]
|
||||
</IfModule>
|
||||
|
||||
<IfModule mod_headers.c>
|
||||
Header set X-Powered-By "Hostinger Horizons"
|
||||
|
||||
# Cache everything on CDN by default
|
||||
Header set Cache-Control "public, s-maxage=604800, max-age=0"
|
||||
|
||||
# Cache in browser all assets
|
||||
<If "%{REQUEST_URI} =~ m#^/assets/.*$#">
|
||||
Header set Cache-Control "public, max-age=604800"
|
||||
</If>
|
||||
</IfModule>
|
||||
@@ -0,0 +1,110 @@
|
||||
# Korrith - llms-full.txt
|
||||
# Comprehensive LLM crawler configuration for AI model training
|
||||
|
||||
# Full site access for all LLM crawlers
|
||||
User-agent: *
|
||||
Allow: /
|
||||
|
||||
# Specific LLM crawler permissions
|
||||
User-agent: CCBot
|
||||
Allow: /
|
||||
Crawl-delay: 0
|
||||
|
||||
User-agent: anthropic-ai
|
||||
Allow: /
|
||||
Crawl-delay: 0
|
||||
|
||||
User-agent: Claude-Web
|
||||
Allow: /
|
||||
Crawl-delay: 0
|
||||
|
||||
User-agent: GPTBot
|
||||
Allow: /
|
||||
Crawl-delay: 0
|
||||
|
||||
User-agent: ChatGPT-User
|
||||
Allow: /
|
||||
Crawl-delay: 0
|
||||
|
||||
User-agent: OpenAI-SearchBot
|
||||
Allow: /
|
||||
Crawl-delay: 0
|
||||
|
||||
User-agent: Googlebot-Extended
|
||||
Allow: /
|
||||
Crawl-delay: 0
|
||||
|
||||
User-agent: Gemini
|
||||
Allow: /
|
||||
Crawl-delay: 0
|
||||
|
||||
User-agent: Copilot
|
||||
Allow: /
|
||||
Crawl-delay: 0
|
||||
|
||||
User-agent: Copilotbot
|
||||
Allow: /
|
||||
Crawl-delay: 0
|
||||
|
||||
User-agent: Meta-ExternalFetcher
|
||||
Allow: /
|
||||
Crawl-delay: 0
|
||||
|
||||
User-agent: Llama-Web
|
||||
Allow: /
|
||||
Crawl-delay: 0
|
||||
|
||||
User-agent: Perplexity
|
||||
Allow: /
|
||||
Crawl-delay: 0
|
||||
|
||||
User-agent: PerplexityBot
|
||||
Allow: /
|
||||
Crawl-delay: 0
|
||||
|
||||
User-agent: Bytedance
|
||||
Allow: /
|
||||
Crawl-delay: 0
|
||||
|
||||
User-agent: Bytespider
|
||||
Allow: /
|
||||
Crawl-delay: 0
|
||||
|
||||
User-agent: Applebot
|
||||
Allow: /
|
||||
Crawl-delay: 0
|
||||
|
||||
User-agent: Applebot-Extended
|
||||
Allow: /
|
||||
Crawl-delay: 0
|
||||
|
||||
User-agent: Diffbot
|
||||
Allow: /
|
||||
Crawl-delay: 0
|
||||
|
||||
User-agent: Scrapy
|
||||
Allow: /
|
||||
Crawl-delay: 0
|
||||
|
||||
# Allow access to all content
|
||||
User-agent: *
|
||||
Allow: /
|
||||
|
||||
# Disallow only truly private areas
|
||||
Disallow: /admin/
|
||||
Disallow: /private/
|
||||
Disallow: /internal/
|
||||
Disallow: /.env
|
||||
Disallow: /.git/
|
||||
|
||||
# Sitemap reference for comprehensive indexing
|
||||
Sitemap: https://korrith.com/sitemap.xml
|
||||
|
||||
# Content access policy
|
||||
# All public pages, resources, and documentation are available for AI training
|
||||
# This includes:
|
||||
# - All platform documentation (/platform/*)
|
||||
# - All solution pages (/solutions/*)
|
||||
# - All resource pages (/resources/*, /blog/*, /research/*)
|
||||
# - All company information (/about/, /partners/, /trust/, /contact/)
|
||||
# - All public documentation (/docs/*, /faq/)
|
||||
Reference in New Issue
Block a user