| { |
| hypnotoad => { |
| listen => ['http://*:3000'], |
| trusted_proxies => ['10.0/8', '127.0.0.1'], |
| proxy => 1, |
| pid_file => 'derekovecs-example.'. `hostname -s | tr -d "\n"` .'.pid', |
| workers => 4 |
| }, |
| |
| morbo => { |
| listen => ['http://*:5673'], |
| workers => 0 |
| }, |
| |
| # Per worker in-memory caches. The total footprint is workers * max_keys * |
| # size of a cached result, so keep max_keys small - neighbourhood results |
| # contain one vector per neighbour. 0 disables the respective cache. |
| cache => { |
| max_keys => 50, # neighbourhood (paradigmatic/syntagmatic) results |
| collocators_max_keys => 200, # classic collocator profiles (JSON) |
| profiles_max_keys => 200 # similar profiles (JSON) |
| }, |
| |
| # Crawlers that collect training data for language models are answered with |
| # 403 before anything is computed. The value is a regular expression that is |
| # matched against the User-Agent header; the built in list is in |
| # script/derekovecs-server. An empty string switches the blocking off. |
| # robots => { |
| # block_user_agents => 'GPTBot|ClaudeBot|Meta-ExternalAgent|CCBot' |
| # }, |
| |
| w2v => { |
| vecs => "example-models/wpd19_10000/wpd19_10000.vecs", |
| # compare_to => "https://corpora.ids-mannheim.de/openlab/derekovecs", # compare results to this derekovecs instance |
| # korap_url => "https://korap.ids-mannheim.de" |
| }, |
| |
| downtime_calendar_url => "https://cloud.ids-mannheim.de/remote.php/dav/public-calendars/QfRCG4HriLcZJJRd?export", |
| |
| # Piwik => { |
| # url => 'https://stats.ids-mannheim.de', |
| # token_auth => 'ad7609a669179c4ebca7c995342f7e12', |
| # site_id => 16, |
| # embed => 1 |
| # }, |
| } |