[{"data":1,"prerenderedAt":274},["ShallowReactive",2],{"project-29551947":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":41,"post_text":43,"what":44,"said":87,"maker_in_thread":154,"shape":163,"grid":166,"attempts":237,"same_week":238,"maker_shows":33,"maker_hidden":266,"reader_version":267,"card":268},"29551947","NLP for Semantic Search","A free course, 'NLP for Semantic Search'","title","Show HN: I made a free course, 'NLP for Semantic Search'","https:\u002F\u002Fwww.pinecone.io\u002Flearn\u002Fnlp\u002F","pinecone.io","jamesbriggs",1639492614,2021,239,29,166,2533,7,"notable","learning_science","online course","other",[24,25,26,27],"semantic search","nlp","sentence transformers","dense vectors","loved",0.278,{"positive":31,"neutral":32,"mixed":33,"critical":34},5,13,1,0,19,{"idea":37,"docs":38,"performance":39,"design":40},{"positive":34,"critical":34},{"positive":33,"critical":34},{"positive":34,"critical":34},{"positive":33,"critical":34},[34,42,34,34,34,31,42,34,34,42,42,42,42,31,34,42,42,34,42,31,34,42,34,42,42,31,31,42,42],3,null,{"problem":45,"audience":52,"pricing":59,"motivation":63,"time_to_build":43,"stack":67,"openness":84,"stage":85,"team_size":86},{"value":46,"source":47,"evidence":48},"Teaching how NLP turns text into dense vectors for semantic search","maker",[49],{"id":50,"by":11,"text":51},"29551948","Hi all, I'm James, past data scientist, ML engineer, and now dev advocate at Pinecone. I've been dedicating much of the past few months to building a course on what I've found to…",{"value":53,"source":47,"evidence":54},"People learning NLP and semantic search, ideally with Python knowledge",[55,56],{"id":50,"by":11,"text":51},{"id":57,"by":11,"text":58},"29554308","Ideally I think it's useful to be familiar with Python and some NLP. Parts of the course can get reasonably in-depth, but we have tried to simplify every as much as possible and…",{"value":60,"source":47,"evidence":61},"Free",[62],{"id":50,"by":11,"text":51},{"value":64,"source":47,"evidence":65},"Maker wanted to teach semantic search, which he finds fascinating",[66],{"id":50,"by":11,"text":51},[68,72,80],{"value":69,"source":47,"evidence":70},"Python",[71],{"id":57,"by":11,"text":58},{"value":73,"source":74,"evidence":75},"Hugo","commenter",[76],{"id":77,"by":78,"text":79},"29561728","gk1","It's built with Hugo and deployed through Netlify.",{"value":81,"source":74,"evidence":82},"Netlify",[83],{"id":77,"by":78,"text":79},"free","launched","company",{"praise":88,"objections":104,"requests":119,"questions":127,"alternatives":142},[89],{"value":90,"source":74,"evidence":91},"Informative, polished and useful for learning NLP",[92,96,100],{"id":93,"by":94,"text":95},"29552377","SleekEagle","Looks really informative and polished!",{"id":97,"by":98,"text":99},"29553978","nbeleski","I am browsing the web in search for NLP resources as I consider a pivot into this new area (I already have a few years in data science and image processing) and finding this post…",{"id":101,"by":102,"text":103},"29556564","NetOpWibby","Bless you for sharing this knowledge.",[105],{"value":106,"source":74,"evidence":107},"Semantic search is less useful than literal keyword search for known terms",[108,112,116],{"id":109,"by":110,"text":111},"29556734","danuker","I very much appreciate the course you shared. But I want to mention for everyone taking it: please also keep in mind \"dumb\" logical operators like OR, AND, NOT, and quotes that…",{"id":113,"by":114,"text":115},"29557983","smt88","This was my thought exactly. I absolutely loathe semantic search and have never found it more useful than literal search.",{"id":117,"by":114,"text":118},"29560926","It most often results in being unable to find something I know exact keywords for. I have used search long enough to remember having only literal search, and I never had an issue…",[120],{"value":121,"source":74,"evidence":122},"Support for longer documents beyond transformer token limits",[123],{"id":124,"by":125,"text":126},"29557344","rolisz","Does this semantic search work for longer documents? I know BERT&Co models are limited to around 500-1000 tokens.",[128,135],{"value":129,"source":74,"evidence":130},"How does the course relate to vector search approaches",[131],{"id":132,"by":133,"text":134},"29560554","rmbyrro","Looks very good, thanks for sharing! How does your course relate to the vector search approach discussed here?…",{"value":136,"source":74,"evidence":137},"What prerequisites are needed",[138],{"id":139,"by":140,"text":141},"29552643","notjulianjaynes","What skills would you say are nessecary prerequisites for understanding this material? I'm a writer, and in the past I have had success making poems and shit via messing around…",[143,150],{"value":144,"source":47,"evidence":145},"HuggingFace NLP course",[146,147],{"id":57,"by":11,"text":58},{"id":148,"by":11,"text":149},"29563215","The HuggingFace course is very good for NLP: https:\u002F\u002Fhuggingface.co\u002Fcourse\u002Fchapter1\u002F1",{"value":151,"source":74,"evidence":152},"Google Vector Search",[153],{"id":132,"by":133,"text":134},{"comments":155,"answered":156,"key":157},6,2,[158,159,160],{"id":50,"text":51},{"id":57,"text":58},{"id":161,"text":162},"29554117","That's awesome, glad to hear it!",{"commenters":164,"max_depth":165,"maker_replies":155,"first_comment_mins":34,"lifespan_hours":35},18,4,[167,169,171,173,175,176,180,182,184,188,190,192,195,197,198,200,202,205,207,209,212,214,219,221,225,227,229,233,236],[50,34,34,168,11,33],"project\u002Fpositive\u002Fdocs",[109,33,42,170,110,34],"project\u002Fmixed\u002Fidea",[113,33,34,172,114,34],"commenter\u002Fcritical\u002Fidea",[174,33,34,172,133,34],"29560534",[117,33,34,172,114,34],[177,156,31,178,179,34],"29555537","project\u002Fpositive\u002Fnone","maestrae",[139,42,42,181,140,34],"maker\u002Fneutral\u002Fnone",[57,42,34,183,11,33],"maker\u002Fneutral\u002Fdocs",[185,42,34,186,187,34],"29555717","other\u002Fneutral\u002Fnone","amrrs",[132,165,42,189,133,34],"project\u002Fneutral\u002Fidea",[191,165,42,189,78,34],"29560687",[193,31,42,181,194,34],"29556793","Pandabob",[196,31,42,181,78,34],"29557643",[97,155,31,168,98,34],[161,155,34,199,11,33],"maker\u002Fpositive\u002Fnone",[124,18,42,201,125,34],"project\u002Fneutral\u002Fperformance",[203,18,42,189,204,34],"29562712","crucialfelix",[206,18,34,189,11,33],"29563204",[208,18,42,189,204,34],"29563724",[93,210,31,211,94,34],8,"project\u002Fpositive\u002Fdesign",[213,210,34,199,11,33],"29552595",[215,216,42,217,218,34],"29562640",9,"project\u002Fneutral\u002Fnone","ewuhic",[148,216,34,220,11,33],"other\u002Fneutral\u002Fdocs",[222,223,42,189,224,34],"29556390",10,"thewarrior",[226,223,42,189,78,34],"29559823",[101,228,31,199,102,34],11,[230,231,31,199,232,34],"29555109",12,"__vim__",[234,32,42,217,235,34],"29552762","MR4D",[77,32,42,217,78,34],[],[239,244,248,253,258,262],{"id":240,"name":241,"points":242,"category":243},"29513547","federalist",433,"infrastructure",{"id":245,"name":246,"points":247,"category":20},"29540808","Deployment from Scratch",326,{"id":249,"name":250,"points":251,"category":252},"29540416","LZMA decoder x86 CMOV patch",205,"languages",{"id":254,"name":255,"points":256,"category":257},"29551465","DoodleCSS",188,"dev_tools",{"id":259,"name":260,"points":261,"category":257},"29538264","glibc-abi-tool",171,{"id":263,"name":264,"points":265,"category":257},"29535432","setup-new-computer-script",169,false,"v2",{"id":269,"name":5,"line":6,"ai":266,"cat":20,"year":13,"points":14,"comments":15,"rec":28,"s":270,"top":18,"kw":271,"maker":11,"domain":10,"tier":19,"attempts":34,"strip":272,"url":9,"mix":273,"praise":90,"objection":106,"sub":21},29551947,0.28,[24,25,26,27],"03000530033335033035030335533",[31,32,33,34],1794036614241]