Mixpeek mentions (16)

• Rip apart my landing page

  I want you to rip apart my landing page: https://mixpeek.com. Source: about 1 year ago

• Free javascript content search for your website

  It uses scrapy to build the spider (https://github.com/scrapy) then indexes them all into the mixpeek API (https://mixpeek.com), which is powered by Lucene's KNN (https://issues.apache.org/jira/browse/LUCENE-9004). Source: over 1 year ago

• Show HN: Collie.ai – One click full application search

  Hey HN! We just released the beta version of collie.ai (https://collie.ai). Collie.ai recursively scrapes your website's entire contents and files, then gives you a search bar that seamlessly integrates into your website's design. It uses scrapy to build the spider (https://github.com/scrapy), which is powered by Lucene's KNN (https://issues.apache.org/jira/browse/LUCENE-9004) I've been in the search engineering... - Source: Hacker News / over 1 year ago

• Semantic Search + LLM grounded answer for your PDFs, youtube and webpages

  Nice! I made something similar: https://mixpeek.com/. Source: over 1 year ago

• S3 File Tag

  i've run into this very problem at mixpeek, where the solution was to mark the file if it's determined it needs re-processing then append it to a queue that has re-processing jobs executed by a separate lambda. Chances are there's a reason it fails which needs investigating. I typically flag this to the user. Source: over 1 year ago

Blerp mentions (0)