[{"data":1,"prerenderedAt":361},["ShallowReactive",2],{"project-35641164":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":36,"aspects":37,"strip":43,"post_text":46,"what":47,"said":78,"maker_in_thread":181,"shape":190,"grid":193,"attempts":322,"same_week":323,"maker_shows":208,"maker_hidden":353,"reader_version":354,"card":355},"35641164","CozoDB","CozoDB, Hybrid Relational-Graph-Vector Database","title","Show HN: CozoDB, Hybrid Relational-Graph-Vector Database","https:\u002F\u002Fdocs.cozodb.org\u002Fen\u002Flatest\u002Freleases\u002Fv0.6.html","docs.cozodb.org","zh217",1682002862,2023,137,51,467,3109,16,"notable","data","embedded graph database","library",[24,25,26,27,28],"graph database","datalog","vector search","hnsw","embedded database","loved",0.257,{"positive":32,"neutral":33,"mixed":34,"critical":35},8,17,0,1,26,{"idea":38,"docs":40,"performance":41,"privacy":42},{"positive":39,"critical":34},6,{"positive":35,"critical":35},{"positive":34,"critical":34},{"positive":34,"critical":34},[34,44,34,45,34,44,45,45,34,45,45,34,45,34,45,45,44,34,34,34,45,34,45,45,45,34,44,44,44,44,45,34,45,34,35,34,34,34,45,44],5,3,"Hi HN! We're thrilled to share CozoDB v0.6, a monumental update to our FOSS database, which already unifies relational and graph features. With the addition of vector search, CozoDB becomes an even better companion for LLMs like ChatGPT.\n\nThis release introduces vector search using HNSW indices within Datalog, enabling seamless integration with powerful features such as ad-hoc joins, recursive Datalog, and classical whole-graph algorithms. This update significantly broadens CozoDB's capabilities.\n\nCheck out the linked release note for an in-depth look at the new features, comparisons to other ",{"problem":48,"audience":57,"pricing":57,"motivation":57,"time_to_build":57,"stack":58,"openness":75,"stage":76,"team_size":77},{"value":49,"source":50,"evidence":51},"Unifies relational, graph and vector search in one local-first database for LLM-related work","maker",[52,54],{"id":53},"post",{"id":55,"by":11,"text":56},"35642329","I'm not too familiar with rel, but from what I read, rel seems to be cloud only, and CozoDB always aims to be local-first. Another difference is that CozoDB has many whole-graph…",null,[59,67,71],{"value":60,"source":61,"evidence":62},"Rust","commenter",[63],{"id":64,"by":65,"text":66},"35643466","iFire","Link to the github repository. https:\u002F\u002Fgithub.com\u002Fcozodb\u002Fcozo Rust and MPL2.0 License. https:\u002F\u002Fgithub.com\u002Fcozodb\u002Fcozo\u002Fblob\u002Fmain\u002FLICENSE.txt",{"value":68,"source":50,"evidence":69},"Datalog query language",[70],{"id":53},{"value":72,"source":50,"evidence":73},"HNSW vector indices",[74],{"id":53},"open_source","unknown","solo",{"praise":79,"objections":104,"requests":116,"questions":146,"alternatives":166},[80,95],{"value":81,"source":61,"evidence":82},"Impressive work and useful for AI and graph projects",[83,87,91],{"id":84,"by":85,"text":86},"35659043","vecrvecr","I created this account to thank you for your work, this seems perfect for what I 'm working on! I'm about to finish the tutorial, it's very well done :)",{"id":88,"by":89,"text":90},"35645724","joshspankit","As a graph “fanboy” I’m impressed, humbled, and inspired by the work that’s been done already and the direction you’re heading! > Note that CozoDB does not have any meaningful…",{"id":92,"by":93,"text":94},"35642531","marginalia_nu","Neat!",{"value":96,"source":50,"evidence":97},"Good performance for concurrent writes and larger-than-RAM data",[98,101],{"id":99,"by":11,"text":100},"35642480","Yes this is correct, only the query's answer set need to be in memory. We are also working on streaming for the Rust API, in which case you don't even need to keep the whole set…",{"id":102,"by":11,"text":103},"35644637","Great questions! - As can be seen https:\u002F\u002Fdocs.cozodb.org\u002Fen\u002Flatest\u002Freleases\u002Fv0.3.html, for concurrent writes about 200K QPS can be achieved with 24 threads on a pretty old…",[105,109],{"value":106,"source":50,"evidence":107},"Lacks user, authentication and authorization features",[108],{"id":102,"by":11,"text":103},{"value":110,"source":61,"evidence":111},"Inconsistent naming between CozoDB and Cozo in README",[112],{"id":113,"by":114,"text":115},"35649177","assface","Is it called \"CozoDB\" or Cozo? Your README is inconsistent.",[117,124,128,135],{"value":118,"source":61,"evidence":119},"Full text search support",[120],{"id":121,"by":122,"text":123},"35645334","canadiantim","Amazing! Thank you, all very encouraging answers. Congrats on everything you've achieved with Cozo so far!! One last question if possible. Is there a recommended way to do Full…",{"value":125,"source":61,"evidence":126},"Access control model",[127],{"id":88,"by":89,"text":90},{"value":129,"source":61,"evidence":130},"Parquet support",[131],{"id":132,"by":133,"text":134},"35642444","luizfelberti","How well does Cozo handle larger than RAM data? Does it only need to keep the query's answer set in memory?",{"value":136,"source":61,"evidence":137},"LangChain and LlamaIndex integrations",[138,142],{"id":139,"by":140,"text":141},"35642542","ssivark","If you want folks playing with integrating CozoDB and LLMs, it might be worth adding a CozoDB wrapper to Langchain :-)",{"id":143,"by":144,"text":145},"35644084","freezed88","would love to have CozoDB be a part of llamaindex too! have a bunch of integrations with existing vector db's…",[147,154,160],{"value":148,"source":61,"evidence":149},"How it compares to other graph and vector databases",[150],{"id":151,"by":152,"text":153},"35642243","srhtftw","Wondering how it compares to rel¹. ¹- https:\u002F\u002Fdocs.relational.ai\u002Frel\u002Fprimer\u002Fbasic-syntax",{"value":155,"source":61,"evidence":156},"How to handle different LLMs with different vector spaces",[157],{"id":158,"by":89,"text":159},"35645807","How do you handle different LLMs having different vector spaces?",{"value":161,"source":61,"evidence":162},"Production readiness and security",[163],{"id":164,"by":122,"text":165},"35644454","Would using Cozo make sense for a social network? Certainly would make modelling comments easier but how well does it handle many concurrent users? Can you intermix different…",[167,171],{"value":168,"source":61,"evidence":169},"Rel (RelationalAI)",[170],{"id":151,"by":152,"text":153},{"value":172,"source":61,"evidence":173},"SQLite FTS5 and Sonic for full text search",[174,177],{"id":175,"by":122,"text":176},"35649230","Thank you, that makes sense. Plus with vector search there seems to be ways of shoehorning FTS with it. Could also potentially use sqlite storage and piggyback off SQlite FTS5…",{"id":178,"by":179,"text":180},"35650676","infogulch","Sonic [1] might be a good fit, though it is not yet factored into a separate library [2]. [1]: https:\u002F\u002Fgithub.com\u002Fvaleriansaliou\u002Fsonic [2]:…",{"comments":182,"answered":183,"key":184},14,9,[185,186,189],{"id":99,"text":100},{"id":187,"text":188},"35642553","For the parquet question: currently CozoDB is developed by a single developer (me), but I am starting to explore ways of expanding the development team. Certainly a lot more…",{"id":102,"text":103},{"commenters":36,"max_depth":44,"maker_replies":182,"first_comment_mins":191,"lifespan_hours":192},71,59,[194,196,200,204,207,210,212,214,216,219,220,222,224,227,228,229,231,234,236,239,241,243,247,249,252,255,258,261,263,266,269,270,272,275,277,279,280,283,286,289,291,293,295,297,300,303,306,309,311,314,318,320],[64,34,34,195,65,34],"other\u002Fneutral\u002Fnone",[197,35,44,198,199,34],"35644914","project\u002Fpositive\u002Fidea","samsquire",[201,35,34,202,203,34],"35668581","commenter\u002Fneutral\u002Fnone","nerdyadventurer",[205,35,45,206,199,34],"35670330","project\u002Fneutral\u002Fdocs",[132,208,45,209,133,34],2,"project\u002Fneutral\u002Fperformance",[99,208,34,211,11,35],"maker\u002Fpositive\u002Fperformance",[213,208,44,198,133,34],"35642579",[187,208,34,215,11,35],"maker\u002Fneutral\u002Fnone",[217,208,45,215,218,34],"35643677","anonzzzies",[164,45,45,209,122,34],[102,45,34,221,11,35],"project\u002Fmixed\u002Fperformance",[121,45,45,223,122,34],"project\u002Fneutral\u002Fidea",[225,45,34,226,11,35],"35645564","maker\u002Fneutral\u002Fidea",[175,45,45,223,122,34],[178,45,34,195,179,34],[88,45,45,230,89,34],"project\u002Fneutral\u002Fprivacy",[232,45,34,195,233,34],"35646652","webstrand",[235,45,34,202,89,34],"35647426",[237,45,45,226,238,34],"35652097","gremlinsinc",[240,45,45,223,179,34],"35663323",[242,45,45,223,89,34],"35645477",[244,245,44,198,246,34],"35643402",4,"pizza",[248,245,34,215,11,35],"35643448",[250,245,34,202,251,34],"35644022","esafak",[253,245,34,254,246,34],"35649185","other\u002Fneutral\u002Fidea",[256,44,34,195,257,34],"35642730","dang",[259,39,45,215,260,34],"35642248","vlmutolo",[262,39,34,215,11,35],"35642381",[264,39,45,226,265,34],"35672579","lupickup",[151,267,45,268,152,34],7,"project\u002Fneutral\u002Fnone",[55,267,34,215,11,35],[271,32,45,223,89,34],"35646330",[273,183,34,254,274,34],"35647348","blatant303",[139,276,44,198,140,34],10,[278,276,34,215,11,35],"35642694",[143,276,44,198,144,34],[84,281,44,282,85,34],11,"project\u002Fpositive\u002Fdocs",[284,281,44,285,85,34],"35661244","maker\u002Fpositive\u002Fidea",[287,281,34,288,11,35],"35662536","maker\u002Fpositive\u002Fnone",[158,290,45,223,89,34],12,[292,290,34,226,11,35],"35645975",[294,290,45,226,89,34],"35646005",[296,290,34,226,11,35],"35646036",[298,290,34,299,89,34],"35646220","commenter\u002Fneutral\u002Fidea",[113,301,35,302,114,34],13,"project\u002Fcritical\u002Fdocs",[304,301,34,305,11,35],"35651586","maker\u002Fneutral\u002Fdocs",[307,182,34,195,308,34],"35650017","avinassh",[310,182,34,305,11,35],"35651581",[312,182,34,254,313,34],"35651839","e12e",[315,316,45,223,317,34],"35648114",15,"robcomptec",[92,18,44,319,93,34],"project\u002Fpositive\u002Fnone",[321,18,34,288,11,35],"35642720",[],[324,329,334,339,344,349],{"id":325,"name":326,"points":327,"category":328},"35639810","Stretch15",550,"consumer_social",{"id":330,"name":331,"points":332,"category":333},"35665142","Lost at SQL",547,"learning_science",{"id":335,"name":336,"points":337,"category":338},"35712163","ScrapScript",503,"languages",{"id":340,"name":341,"points":342,"category":343},"35690753","Homemade rocketship treehouse",410,"hardware",{"id":345,"name":346,"points":347,"category":348},"35649245","newgrounds.com",267,"creative",{"id":350,"name":351,"points":352,"category":20},"35712238","GB Renewables Map",245,false,"v2",{"id":356,"name":5,"line":6,"ai":353,"cat":20,"year":13,"points":14,"comments":15,"rec":29,"s":357,"top":18,"kw":358,"maker":11,"domain":10,"tier":19,"attempts":34,"strip":359,"url":9,"mix":360,"praise":81,"objection":106,"sub":21},35641164,0.26,[24,25,26,27,28],"0503053303303033500030333055553030100035",[32,33,34,35],1793991064150]