[{"data":1,"prerenderedAt":309},["ShallowReactive",2],{"project-41554791":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":28,"sentiment":29,"stance_mix":30,"scored_comments":35,"aspects":36,"strip":40,"post_text":42,"what":43,"said":71,"maker_in_thread":153,"shape":161,"grid":165,"attempts":272,"same_week":273,"maker_shows":181,"maker_hidden":301,"reader_version":302,"card":303},"41554791","Sisi","Semantic Image Search CLI tool, locally without third party APIs","title","Show HN: Sisi – Semantic Image Search CLI tool, locally without third party APIs","https:\u002F\u002Fgithub.com\u002Ffrost-beta\u002Fsisi","github.com","zcbenz",1726484353,2024,128,41,667,3515,19,"notable","ai","image search","cli",[24,25,26,27],"semantic image search","clip model","node.js","local search","curious",-0.099,{"positive":31,"neutral":32,"mixed":33,"critical":34},2,7,0,5,14,{"idea":37,"performance":39},{"positive":31,"critical":38},1,{"positive":33,"critical":31},[34,38,33,41,38,34,41,41,41,33,41,33,41,33,33,33,33,33,33,38,33,33,33,33,33,38,33,33,33,33,33,33,33,33,33,33,33,33,33,38],3,"I wrote this tool to get familiar with CLIP model, I know many people have written similar tools with CLIP before, but I'm new to machine learning and writing a classic tool helps my study.\n\nThe unusual thing with my version is, it is in pure Node.js, with the power of node-mlx, a Node.js machine learning framework.\n\nThe repo in the link is mostly about implementing indexing and CLI, the code of the model implementation lives as a Node.js module: https:\u002F\u002Fgithub.com\u002Ffrost-beta\u002Fclip .\n\nHope this helps other learners!",{"problem":44,"audience":50,"pricing":50,"motivation":51,"time_to_build":50,"stack":55,"openness":68,"stage":69,"team_size":70},{"value":45,"source":46,"evidence":47},"Searching photos by content without third-party APIs","maker",[48],{"id":49},"post",null,{"value":52,"source":46,"evidence":53},"Learning CLIP and machine learning by writing a classic tool",[54],{"id":49},[56,60,64],{"value":57,"source":46,"evidence":58},"Node.js",[59],{"id":49},{"value":61,"source":46,"evidence":62},"node-mlx",[63],{"id":49},{"value":65,"source":46,"evidence":66},"CLIP model",[67],{"id":49},"open_source","unknown","solo",{"praise":72,"objections":85,"requests":108,"questions":119,"alternatives":134},[73],{"value":74,"source":75,"evidence":76},"Useful alternative or idea for semantic photo search","commenter",[77,81],{"id":78,"by":79,"text":80},"41557194","notsylver","I was planning to do this myself lol. I was going to use SQLite as the index, and use `sqlite-vec` or something similar to query for similar files directly. I think the only…",{"id":82,"by":83,"text":84},"41558155","spullara","Very cool! Here is a similar python version. https:\u002F\u002Fgithub.com\u002Fspullara\u002Fphotoindex Oh and if you want to run something locally on your iphone you can use my app I am still…",[86,97],{"value":87,"source":75,"evidence":88},"Very slow indexing, uses only one core on Linux",[89,93],{"id":90,"by":91,"text":92},"41555976","progx","Uses only 1 core 100% under linux, can this be changed? 10 images, each ~20 kb size, took more than 10 minutes to index, is that normal without GPU-acceleration?",{"id":94,"by":95,"text":96},"41559075","sureIy","Wow that’s atrocious performance. So there’s no chance to use this on real photos",{"value":98,"source":75,"evidence":99},"Name means something offensive in Russian and other languages",[100,104],{"id":101,"by":102,"text":103},"41555939","ivanjermakov","In russian, \"sisi\" is a variation of \"tits\". Is there a job\u002Fservices that confirm that branding is appropriate across different languages? Seems like a non trivial problem to…",{"id":105,"by":106,"text":107},"41556011","phito","It's definitely not a good name in English either",[109,115],{"value":110,"source":75,"evidence":111},"Support for describing image contents, not just searching",[112],{"id":113,"by":95,"text":114},"41559061","This is cool. Is there also a way to show contents of the image as indexed? i.e. image 1 has cat and dog There are a lot of tool\u002Fapps that let you “search images” but not much…",{"value":116,"source":75,"evidence":117},"Filters such as negation, similarity threshold and file size",[118],{"id":78,"by":79,"text":80},[120,127],{"value":121,"source":75,"evidence":122},"How does CLIP compare to YOLO",[123],{"id":124,"by":125,"text":126},"41560361","y04nn","How does CLIP compare to YOLO[1]? I haven't looked into image classification\u002Fobject recognition for a while, but I remember that YOLO was quite good was working on realtime video…",{"value":128,"source":75,"evidence":129},"Whether CLIP is superseded by multimodal LLMs",[130],{"id":131,"by":132,"text":133},"41561594","Jack5500","Isn‘t clip superseeded by multimodal llms?",[135,142,146],{"value":136,"source":75,"evidence":137},"rclip",[138],{"id":139,"by":140,"text":141},"41565425","yburkov","using same app rclip: https:\u002F\u002Fgithub.com\u002Fyurijmikhalevich\u002Frclip",{"value":143,"source":75,"evidence":144},"photoindex",[145],{"id":82,"by":83,"text":84},{"value":147,"source":75,"evidence":148},"Queryable",[149],{"id":150,"by":151,"text":152},"41559520","petesergeant","I've been enjoying https:\u002F\u002Fgithub.com\u002Fmazzzystar\u002FQueryable on iPhone",{"comments":31,"answered":31,"key":154},[155,158],{"id":156,"text":157},"41556050","No it is not normal, I only tested x64\u002Farm64 macs, I will try on linux.",{"id":159,"text":160},"41556025","That is sad, the name sisi comes from the sisi empress: https:\u002F\u002Fen.m.wikipedia.org\u002Fwiki\u002FEmpress_Elisabeth_of_Austria",{"commenters":162,"max_depth":34,"maker_replies":31,"first_comment_mins":163,"lifespan_hours":164},30,158,23,[166,168,170,172,175,176,177,179,183,186,188,190,193,195,199,202,204,208,210,212,214,217,220,222,225,228,231,235,237,240,242,245,248,252,254,257,259,261,264,267,270],[78,33,34,167,79,33],"project\u002Fpositive\u002Fidea",[90,38,38,169,91,33],"project\u002Fcritical\u002Fperformance",[156,38,33,171,11,38],"maker\u002Fneutral\u002Fperformance",[173,38,41,171,174,33],"41558397","a_wild_dandan",[94,38,38,169,95,33],[82,31,34,167,83,33],[113,41,41,178,95,33],"project\u002Fneutral\u002Fidea",[180,181,41,178,182,33],"41560973",4,"kjeldsendk",[184,181,41,178,185,33],"41562387","Eisenstein",[150,34,33,187,151,33],"other\u002Fneutral\u002Fnone",[124,189,41,178,125,33],6,[191,189,33,192,185,33],"41560526","other\u002Fneutral\u002Fidea",[139,32,41,194,140,33],"project\u002Fneutral\u002Fnone",[196,197,33,187,198,33],"41556172",8,"netdur",[200,197,33,187,201,33],"41556810","KetoManx64",[203,197,33,187,198,33],"41557213",[205,197,33,206,207,33],"41561342","other\u002Fcritical\u002Fnone","nickphx",[209,197,33,187,198,33],"41563807",[101,211,33,187,102,33],9,[105,211,38,213,106,33],"project\u002Fcritical\u002Fnone",[215,211,33,187,216,33],"41556524","Zambyte",[218,211,33,187,219,33],"41557297","Narhem",[159,211,33,221,11,38],"maker\u002Fneutral\u002Fnone",[223,211,33,187,224,33],"41556123","rlpb",[226,211,33,187,227,33],"41556324","bjord",[229,211,38,213,230,33],"41557685","jollyllama",[232,211,33,233,234,33],"41559631","commenter\u002Fneutral\u002Fnone","fkyoureadthedoc",[236,211,33,187,230,33],"41560732",[238,211,33,187,239,33],"41556432","philsnow",[241,211,33,187,219,33],"41557370",[243,211,33,187,244,33],"41556852","kristopolous",[246,211,33,187,247,33],"41556935","visarga",[249,211,33,250,251,33],"41557042","commenter\u002Fcritical\u002Fnone","pdimitar",[253,211,33,233,247,33],"41557199",[255,211,33,233,256,33],"41557456","fedeb95",[258,211,33,233,102,33],"41557856",[260,211,33,233,95,33],"41559148",[262,211,33,233,263,33],"41566169","Lockal",[265,211,33,187,266,33],"41558338","kgeist",[131,268,38,269,132,33],10,"project\u002Fcritical\u002Fidea",[271,268,41,178,185,33],"41563154",[],[274,279,284,289,293,297],{"id":275,"name":276,"points":277,"category":278},"41521919","FixHub",928,"hardware",{"id":280,"name":281,"points":282,"category":283},"41539125","Meet.hn",768,"consumer_social",{"id":285,"name":286,"points":287,"category":288},"41517312","Konty",392,"dev_tools",{"id":290,"name":291,"points":292,"category":20},"41544969","Wordllama",370,{"id":294,"name":295,"points":296,"category":288},"41563958","Void",347,{"id":298,"name":299,"points":300,"category":288},"41530190","FlowTracker",280,false,"v2",{"id":304,"name":5,"line":6,"ai":301,"cat":20,"year":13,"points":14,"comments":15,"rec":28,"s":305,"top":18,"kw":306,"maker":11,"domain":10,"tier":19,"attempts":33,"strip":307,"url":9,"mix":308,"praise":74,"objection":87,"sub":21},41554791,-0.1,[24,25,26,27],"5103153330303000000100000100000000000001",[31,32,33,34],1793991100363]