[{"data":1,"prerenderedAt":122},["ShallowReactive",2],{"project-37322678":3},{"id":4,"name":5,"line":6,"line_source":7,"title":8,"url":9,"domain":10,"maker":11,"posted_at":12,"year":13,"points":14,"comments":15,"rank_in_year":16,"shown_in_year":17,"top":18,"tier":19,"category":20,"subcategory":21,"format":22,"keywords":23,"reception":29,"sentiment":30,"stance_mix":31,"scored_comments":15,"aspects":33,"strip":36,"post_text":30,"what":38,"said":65,"maker_in_thread":75,"shape":77,"grid":81,"attempts":86,"same_week":87,"maker_shows":114,"maker_hidden":115,"reader_version":116,"card":117},"37322678","Embedding","Vector Embedding Server in under 100 lines of code","title","Show HN: Vector Embedding Server in under 100 lines of code","https:\u002F\u002Fgithub.com\u002Fstruct-chat\u002Fembedding","github.com","navaneethpk",1693405772,2023,10,2,2468,3109,80,"shown","ai","embedding server","api",[24,25,26,27,28],"vector embeddings","e5 model","document chunking","docker server","sentence chunking","quiet",null,{"positive":32,"neutral":15,"mixed":32,"critical":32},0,{"idea":34,"execution":35},{"positive":32,"critical":32},{"positive":32,"critical":32},[37,37],3,{"problem":39,"audience":30,"pricing":30,"motivation":47,"time_to_build":30,"stack":51,"openness":64,"stage":64,"team_size":64},{"value":40,"source":41,"evidence":42},"Embedding documents longer than the 512-token E5 limit needs sentence-boundary chunking and mean pooling","commenter",[43],{"id":44,"by":45,"text":46},"37322804","mrjn","Author here. I was looking for a Docker-based server, which can expose a simple endpoint to generate vector embeddings for documents. The solution needs to deal with lengthy…",{"value":48,"source":41,"evidence":49},"Could not find an existing Docker server that chunked long documents at sentence boundaries",[50],{"id":44,"by":45,"text":46},[52,60],{"value":53,"source":54,"evidence":55},"Go","inferred",[56],{"id":57,"by":58,"text":59},"37348347","topicseed","I see you're skipping too long sentences — any thoughts on how you would handle them and chunk them further if they weren't skipped? Good to see non-Go code from you, ha ;)",{"value":61,"source":41,"evidence":62},"E5 models",[63],{"id":44,"by":45,"text":46},"unknown",{"praise":66,"objections":67,"requests":68,"questions":69,"alternatives":74},[],[],[],[70],{"value":71,"source":41,"evidence":72},"How long sentences are handled, and whether they could be chunked further instead of skipped",[73],{"id":57,"by":58,"text":59},[],{"comments":32,"answered":32,"key":76},[],{"commenters":15,"max_depth":78,"maker_replies":32,"first_comment_mins":79,"lifespan_hours":80},1,9,42,[82,84],[44,32,37,83,45,32],"maker\u002Fneutral\u002Fidea",[57,78,37,85,58,32],"maker\u002Fneutral\u002Fexecution",[],[88,93,98,103,107,111],{"id":89,"name":90,"points":91,"category":92},"37326870","compress",815,"dev_tools",{"id":94,"name":95,"points":96,"category":97},"37247767","obsidian-sync",416,"infrastructure",{"id":99,"name":100,"points":101,"category":102},"37252231","Shimmer",229,"consumer_social",{"id":104,"name":105,"points":106,"category":92},"37251969","Continue",187,{"id":108,"name":109,"points":110,"category":97},"37263473","Release AI",143,{"id":112,"name":113,"points":110,"category":92},"37310070","Langfuse",4,false,"v2",{"id":118,"name":5,"line":6,"ai":115,"cat":20,"year":13,"points":14,"comments":15,"rec":29,"s":30,"top":18,"kw":119,"maker":11,"domain":10,"tier":19,"attempts":32,"strip":120,"url":9,"mix":121,"praise":-1,"objection":-1,"sub":21},37322678,[24,25,26,27,28],"33",[32,15,32,32],1794036640977]