[{"data":1,"prerenderedAt":119},["ShallowReactive",2],{"project-39837654":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":35,"post_text":37,"what":38,"said":60,"maker_in_thread":74,"shape":76,"grid":78,"attempts":81,"same_week":82,"maker_shows":111,"maker_hidden":112,"reader_version":113,"card":114},"39837654","Unstract(AGPL)","Launch LLM-powered APIs to structure unstructured docs","title","Show HN: Unstract(AGPL) – Launch LLM-powered APIs to structure unstructured docs","https:\u002F\u002Fgithub.com\u002FZipstack\u002Funstract","github.com","shuss",1711538330,2024,25,1,1724,3515,50,"shown","ai","document extraction","api",[24,25,26,27,28],"llm document extraction","pdf parsing","unstructured data","etl pipeline","prompt engineering","quiet",null,{"positive":15,"neutral":32,"mixed":32,"critical":32},0,{"idea":34},{"positive":15,"critical":32},[36],5,"Hello HN!\n\nOne of the most common uses of LLMs is to go beyond what traditional RPA or IDP can do when it comes to structuring unstructured documents. However, there are a lot of challenges in getting this done right from extraction of text data from PDFs, scanned images or other formats, prompt engineering, evaluation and integration with existing systems. This very specific use case is where Unstract can help teams move really fast, leveraging LLMs. By doing the heavy-lifting in this fast-changing ecosystem it lets engineers concentrate on implementing core business workflow automations.\n\nHe",{"problem":39,"audience":45,"pricing":49,"motivation":53,"time_to_build":30,"stack":57,"openness":58,"stage":59,"team_size":59},{"value":40,"source":41,"evidence":42},"Structuring unstructured documents like PDFs and scans using LLMs","maker",[43],{"id":44},"post",{"value":46,"source":41,"evidence":47},"Engineers and teams automating business workflows",[48],{"id":44},{"value":50,"source":41,"evidence":51},"Core is AGPL open source; some features enterprise-only; LLMWhisperer free up to 100 pages a day",[52],{"id":44},{"value":54,"source":41,"evidence":55},"Move fast with LLMs on document structuring without rebuilding the heavy lifting",[56],{"id":44},[],"open_source","unknown",{"praise":61,"objections":70,"requests":71,"questions":72,"alternatives":73},[62],{"value":63,"source":64,"evidence":65},"Looks promising for document workflows","commenter",[66],{"id":67,"by":68,"text":69},"39837816","navinsylvester","This looks promising. I'm looking forward to exploring this further and seeing its practical applications in streamlining document-related workflows. It's always refreshing to…",[],[],[],[],{"comments":32,"answered":32,"key":75},[],{"commenters":15,"max_depth":15,"maker_replies":32,"first_comment_mins":77,"lifespan_hours":32},28,[79],[67,32,36,80,68,32],"project\u002Fpositive\u002Fidea",[],[83,88,93,98,103,107],{"id":84,"name":85,"points":86,"category":87},"39783223","Memories",797,"productivity",{"id":89,"name":90,"points":91,"category":92},"39778570","Dropflow",404,"dev_tools",{"id":94,"name":95,"points":96,"category":97},"39836630","Explanations",391,"learning_science",{"id":99,"name":100,"points":101,"category":102},"39807912","Glossarie",363,"languages",{"id":104,"name":105,"points":106,"category":92},"39816836","Jampack",328,{"id":108,"name":109,"points":110,"category":92},"39793513","magick.css",305,4,false,"v2",{"id":115,"name":5,"line":6,"ai":112,"cat":20,"year":13,"points":14,"comments":15,"rec":29,"s":30,"top":18,"kw":116,"maker":11,"domain":10,"tier":19,"attempts":32,"strip":117,"url":9,"mix":118,"praise":63,"objection":-1,"sub":21},39837654,[24,25,26,27,28],"5",[15,32,32,32],1793991087628]