[{"data":1,"prerenderedAt":415},["ShallowReactive",2],{"project-42295792":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":45,"post_text":47,"what":48,"said":71,"maker_in_thread":217,"shape":230,"grid":234,"attempts":371,"same_week":376,"maker_shows":38,"maker_hidden":407,"reader_version":408,"card":409},"42295792","SeekStorm","open-source sub-millisecond search in Rust","title","Show HN: SeekStorm – open-source sub-millisecond search in Rust","https:\u002F\u002Fgithub.com\u002FSeekStorm\u002FSeekStorm","github.com","wolfgarbe",1733144793,2024,245,61,301,3515,9,"notable","data","full-text search engine","library",[24,25,26,27],"full-text search","rust search engine","bm25","open source search","mixed",0.035,{"positive":31,"neutral":32,"mixed":33,"critical":34},8,13,0,6,27,{"execution":37,"performance":39,"design":41,"docs":43,"idea":44},{"positive":33,"critical":38},2,{"positive":40,"critical":38},3,{"positive":42,"critical":33},1,{"positive":33,"critical":42},{"positive":33,"critical":42},[46,42,42,33,46,42,33,40,40,40,33,33,40,33,40,33,33,46,42,33,33,40,33,46,40,33,46,46,46,42,33,40,42,33,40,33,33,40,33,33],5,null,{"problem":49,"audience":47,"pricing":47,"motivation":59,"time_to_build":47,"stack":63,"openness":69,"stage":70,"team_size":70},{"value":50,"source":51,"evidence":52},"Fast full-text search with low latency and efficient hardware use","maker",[53,56],{"id":54,"by":11,"text":55},"42296607","It depends on the application. When using SeekStorm as a server, keeping the latency per query low increases the throughput and the number of parallel queries a server can handle…",{"id":57,"by":11,"text":58},"42301622","Its not just about speed. Speed reflects efficiency. Efficiency is needed to serve more queries in parallel, to search within exponentially growing data, with less expensive…",{"value":60,"source":51,"evidence":61},"Efficiency: serve more queries on less hardware and energy",[62],{"id":57,"by":11,"text":58},[64],{"value":65,"source":51,"evidence":66},"Rust",[67],{"id":68},"post","open_source","unknown",{"praise":72,"objections":96,"requests":127,"questions":155,"alternatives":188},[73,89],{"value":74,"source":75,"evidence":76},"Impressive speed and benchmarks","commenter",[77,81,85],{"id":78,"by":79,"text":80},"42300139","throwaway888abc","Impressive, bookmarked, upvoted. Appreciate the demo: https:\u002F\u002Fdeephn.org\u002F?q=apple+silicon",{"id":82,"by":83,"text":84},"42302220","faizshah","This is really impressive, I would suggest benchmarking it against Vespa as well I have gotten better perf results from Vespa than Lucerne\u002FSolr\u002FES. I’ll take a try this weekend…",{"id":86,"by":87,"text":88},"42303292","littlestymaar","I don't know how fair the benchmark is, but beating Tantivy by that margin is impressive to say the least. Any plan to make it run on WASM? I wanted to add this feature to…",{"value":90,"source":75,"evidence":91},"Tantivy developer finds benchmark credible",[92],{"id":93,"by":94,"text":95},"42304001","fulmicoton","Developer of tantivy chiming in! (I hope that's ok) Database performance is a space where there are a lot of lies and bullshit, so you are 100% right to be suspicious. I don't…",[97,108,115,120],{"value":98,"source":75,"evidence":99},"Boolean operators and plural\u002Fsearch accuracy issues in demo",[100,104],{"id":101,"by":102,"text":103},"42308376","0bit","Counter-example: https:\u002F\u002Fdeephn.org\u002F?q=embeddings Contrast with https:\u002F\u002Fhn.algolia.com\u002F?dateRange=all&page=0&prefix=true&query=embeddings&sort=byPopularity&type=story It is fast…",{"id":105,"by":106,"text":107},"42318899","d3Xt3r","Seems to buggy. According to the SeekStorm github, it's supposed to support boolean operators right? But they don't seem to work. Eg: https:\u002F\u002Fdeephn.org\u002F?q=Linux+OR+KDE",{"value":109,"source":75,"evidence":110},"Sparse documentation",[111],{"id":112,"by":113,"text":114},"42304909","emmanueloga_","The documentation seems a bit sparse. Also, I couldn't find binaries so I'm guessing building from source is required at the moment? I'm curious about the binary size of it all.…",{"value":116,"source":75,"evidence":117},"No WASM or Python bindings yet",[118,119],{"id":86,"by":87,"text":88},{"id":112,"by":113,"text":114},{"value":121,"source":75,"evidence":122},"Unclear what differentiates it from existing search engines",[123],{"id":124,"by":125,"text":126},"42301243","Thaxll","It feels like everyone re-implement the same application, searching text in language x.y.z has been done a million times, search speed in not a problem so what differenciate this…",[128,133,140,147],{"value":129,"source":75,"evidence":130},"WASM support",[131,132],{"id":86,"by":87,"text":88},{"id":112,"by":113,"text":114},{"value":134,"source":75,"evidence":135},"S3 \u002F object storage support",[136],{"id":137,"by":138,"text":139},"42318264","jszymborski","S3 support would be absolutely killer.",{"value":141,"source":75,"evidence":142},"HTTP interface",[143],{"id":144,"by":145,"text":146},"42329134","bosky101","Why isn't there a http interface? That would increase adoption by far",{"value":148,"source":75,"evidence":149},"Benchmark against Vespa and Typesense",[150,151],{"id":82,"by":83,"text":84},{"id":152,"by":153,"text":154},"42302349","dantodor","Interesting approach, would love to see a comparison with Typesense",[156,163,170,181],{"value":157,"source":75,"evidence":158},"Distributed server support and whether PoC code is available",[159],{"id":160,"by":161,"text":162},"42301099","treefarmer","Is there distributed server support? I see it on the list of new features with (currently PoC) next to it, but is the code for the PoC available anywhere? Also, would there be…",{"value":164,"source":75,"evidence":165},"Multi-language tokenization and stemming",[166],{"id":167,"by":168,"text":169},"42299309","remram","What is the story for multi-language corpus? Do I have to do my own stop word pruning, tokenizing, lemming, etc? This is usually the case with full-text search solutions and it…",{"value":171,"source":75,"evidence":172},"How it compares to Meilisearch and PostgreSQL",[173,177],{"id":174,"by":175,"text":176},"42302700","llIIllIIllIIl","How is it different from Meilisearch[1]? I’m running search for my small multi tenant SaaS and self hosted Meilisearch gives me grief like any relatively new tech, so I’m…",{"id":178,"by":179,"text":180},"42300428","distracted_boy","How does this compare to PostgreSQL?",{"value":182,"source":75,"evidence":183},"Whether network latency overshadows sub-millisecond gains",[184],{"id":185,"by":186,"text":187},"42296424","Leoko","Sub-millisecond latency sounds impressive, but isn't network latency going to overshadow these gains in most real-world scenarios?",[189,197,201,209,213],{"value":190,"source":75,"evidence":191},"Tantivy",[192,196],{"id":193,"by":194,"text":195},"42298520","pornel","When search is cheap and quick, it's possible to improve search by postprocessing search results and running more queries when necessary. I use Tantivy, and add refinements like:…",{"id":86,"by":87,"text":88},{"value":198,"source":75,"evidence":199},"Meilisearch",[200],{"id":174,"by":175,"text":176},{"value":202,"source":75,"evidence":203},"PostgreSQL full-text search and ParadeDB",[204,205],{"id":178,"by":179,"text":180},{"id":206,"by":207,"text":208},"42307939","philippemnoel","ParadeDB (paradedb.com) is similar to this HN, but baked into Postgres to solve this very problem you are describing",{"value":210,"source":75,"evidence":211},"Vespa, Lucene\u002FSolr, Elasticsearch",[212],{"id":82,"by":83,"text":84},{"value":214,"source":75,"evidence":215},"Typesense",[216],{"id":152,"by":153,"text":154},{"comments":218,"answered":219,"key":220},14,12,[221,224,227],{"id":222,"text":223},"42303602","The code for the distributed search cluster is not yet stable enough to be published, but it will be released as open-source as well. As for shared storage, do you mean something…",{"id":225,"text":226},"42303739","In SeekStorm you can choose per index whether to use Mmap or let SeekStorm fully control Ram access. There is a slight performance advantage to the latter, at the cost of higher…",{"id":228,"text":229},"42417258","SeekStorm does currently not use io_uring, but it is on our roadmap. Challenges are the cross-platform compatibility. Linux (io_uring) and Windows (IoRing) use different…",{"commenters":231,"max_depth":46,"maker_replies":218,"first_comment_mins":232,"lifespan_hours":233},39,70,289,[235,237,239,240,242,244,245,249,253,255,259,260,262,264,268,271,275,278,281,283,286,288,291,294,298,300,302,303,304,307,308,311,313,317,318,322,324,326,328,330,331,335,337,338,342,345,347,350,352,353,355,359,361,363,367,370],[78,33,46,236,79,33],"project\u002Fpositive\u002Fnone",[101,33,42,238,102,33],"project\u002Fcritical\u002Fexecution",[105,33,42,238,106,33],[160,42,40,241,161,33],"project\u002Fneutral\u002Fnone",[222,42,33,243,11,42],"maker\u002Fneutral\u002Fnone",[137,42,46,236,138,33],[246,38,46,247,248,33],"42300414","maker\u002Fpositive\u002Fnone","justmarc",[250,40,42,251,252,33],"42301772","project\u002Fcritical\u002Fperformance","infamouscow",[225,40,33,254,11,42],"maker\u002Fneutral\u002Fperformance",[256,40,40,257,258,33],"42345939","project\u002Fneutral\u002Fperformance","nextaccountic",[228,40,33,254,11,42],[167,261,40,241,168,33],4,[263,261,33,243,11,42],"42299421",[265,261,40,266,267,33],"42303535","project\u002Fneutral\u002Fdesign","ronjakoi",[269,261,33,270,11,42],"42303632","maker\u002Fneutral\u002Fdesign",[272,261,33,273,274,33],"42299820","other\u002Fneutral\u002Fnone","jazzyjackson",[276,261,33,273,277,33],"42303966","kreyenborgi",[279,46,40,241,280,33],"42298943","tlofreso",[282,46,33,243,11,42],"42299154",[284,46,40,241,285,33],"42299264","fiedzia",[287,46,33,273,274,33],"42299851",[289,46,33,273,290,33],"42301809","CharlieDigital",[292,46,33,293,274,33],"42302638","commenter\u002Fneutral\u002Fnone",[295,46,40,296,297,33],"42302035","project\u002Fneutral\u002Fdocs","m348e912",[82,34,46,299,83,33],"project\u002Fpositive\u002Fperformance",[185,301,42,251,186,33],7,[54,301,33,254,11,42],[193,301,33,273,194,33],[305,301,33,293,306,33],"42300045","intelVISA",[174,31,40,241,175,33],[309,31,33,293,310,33],"42302760","wiradikusuma",[312,31,33,273,175,33],"42302932",[314,31,46,315,316,33],"42310731","project\u002Fpositive\u002Fdesign","J_Shelby_J",[152,18,40,257,153,33],[319,320,40,241,321,33],"42308631",10,"ghita_",[323,320,33,254,11,42],"42309510",[325,320,46,247,321,33],"42383446",[86,327,46,299,87,33],11,[329,327,33,254,11,42],"42303704",[93,327,46,299,94,33],[332,327,33,333,334,33],"42304069","other\u002Fneutral\u002Fperformance","PSeitz",[124,219,42,336,125,33],"project\u002Fcritical\u002Fidea",[57,219,33,254,11,42],[339,219,40,340,341,33],"42301959","project\u002Fneutral\u002Fidea","sdesol",[343,219,33,273,344,33],"42303651","jamil7",[112,32,42,346,113,33],"project\u002Fcritical\u002Fdocs",[348,32,33,349,11,42],"42305269","maker\u002Fneutral\u002Fdocs",[351,32,33,349,11,42],"42369154",[144,218,40,266,145,33],[354,218,33,270,11,42],"42369243",[356,357,33,273,358,33],"42299529",15,"athompsondog",[178,360,40,241,179,33],16,[362,360,33,243,11,42],"42300947",[364,360,33,365,366,33],"42302762","commenter\u002Fneutral\u002Fperformance","yellow_lead",[368,360,33,365,369,33],"42303928","anonzzzies",[206,360,33,273,207,33],[372,373],{"id":4,"t":12,"points":14,"comments":15},{"id":374,"t":375,"points":38,"comments":38},"50179771",1792585666,[377,382,387,392,397,402],{"id":378,"name":379,"points":380,"category":381},"42289690","Markwhen",912,"productivity",{"id":383,"name":384,"points":385,"category":386},"42284412","Privastead",551,"security_privacy",{"id":388,"name":389,"points":390,"category":391},"42320032","Outerbase Studio",356,"dev_tools",{"id":393,"name":394,"points":395,"category":396},"42270389","Vince",283,"infrastructure",{"id":398,"name":399,"points":400,"category":401},"42311031","30cc",275,"languages",{"id":403,"name":404,"points":405,"category":406},"42261909","Voice-Pro",271,"creative",false,"v2",{"id":410,"name":5,"line":6,"ai":407,"cat":20,"year":13,"points":14,"comments":15,"rec":28,"s":411,"top":18,"kw":412,"maker":11,"domain":10,"tier":19,"attempts":38,"strip":413,"url":9,"mix":414,"praise":74,"objection":98,"sub":21},42295792,0.04,[24,25,26,27],"5110510333003030051003053055510310300300",[31,32,33,34],1794036665212]