_______               __                   _______
       |   |   |.---.-..----.|  |--..-----..----. |    |  |.-----..--.--.--..-----.
       |       ||  _  ||  __||    < |  -__||   _| |       ||  -__||  |  |  ||__ --|
       |___|___||___._||____||__|__||_____||__|   |__|____||_____||________||_____|
                                                             on Gopher (inofficial)
   URI Visit Hacker News on the Web
       
       
       COMMENT PAGE FOR:
   URI   Show HN: GitHub-assistant – Natural language questions from your GitHub data
       
       
        eddywebs wrote 53 min ago:
        Can this help in explaining how the code works, its schematics or HLD
        of a given github repo ?
       
        diggan wrote 1 hour 32 min ago:
        Is there any information you can get out of this that isn't already
        available in the GitHub.com UI? I tried asking things like "What could
        the most interesting information you can tell me about this
        repository?" but it seems like most of the data is already available in
        the UI in pretty much the same format, except you click a link to see
        it instead of writing a question and waiting for a reply.
       
          eddywebs wrote 53 min ago:
          Same thoughts
       
        bberenberg wrote 2 hours 58 min ago:
        Pretty nifty, is Relta going to be OSS as well?
       
        croemer wrote 11 hours 5 min ago:
        Tried adding a repo I work on, import worked after failing first, but
        then the query result was that there was no data on top contributors.
        
        Put the video in the Readme!
       
          aazo11 wrote 7 hours 3 min ago:
          Was able to reproduce and pushed an update. Thanks for calling this
          out.
       
          aazo11 wrote 10 hours 25 min ago:
          Hi -- strange that didn't work. Overall, the semantic layer is
          designed to provide very tight guardrails and not hallucinate. You
          can see the agent suggest changes to the semantic layer if you give
          the produced answer a thumbs down.
          
          The idea is for the system to provide answers that have close to 100%
          accuracy, but make it a single click for developers to to improve the
          semantic layer.
       
          sfarshid wrote 10 hours 38 min ago:
          Just updated the README, thanks for the suggestion!
       
       
   DIR <- back to front page