• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI
    Announcement

    WonderSearch 1.1 launches with query-time retrieval

    The launch announcement says users can search their data without pre-embedding it or using a vector database.

    Robert ScobleRS
    daleDA
    2 Sources, ,

    TLDR

    WonderSearch announced version 1.1, saying it moves retrieval intelligence to query time. It claims to rank first on seven of seven sparse retrieval benchmarks, ahead of BM25, SPLADE and ELSER v2. The announcement also advertises a free quota.

    Combined views

    10.9K

    2 Sources, first seen 5h ago

    Combined views

    10.9K

    2 Sources, first seen 5h ago

    133 likes
    5h ago
    first seen 5h ago
    133 likes
    19 comments
    79 saves
    26 reposts
    19 comments
    79 saves
    26 reposts
    Featured Source

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    2 Sources

    dale@daleverettToday, we’re launching 1.1 of WonderSearch (YCF26), the world’s #1 sparse retrieval system. All of your data, instantly searchable by AI. #1 on 7/7 sparse retrieval benchmarks. Ahead of BM25, SPLADE, and ELSER v2. And #1 on SciFact, Touché-2020, and DBPedia* But the biggest shift? Architectural. WonderSearch moves retrieval intelligence to query time. > No vector database, just your own. > No pre-embedding your data, just search. > New model? Just switch it up. WonderSearch 1.1 is live. Free quota below ↓5h
    Robert Scoble@ScobleizerRT @daleverett: Today, we’re launching 1.1 of WonderSearch (YCF26), the world’s #1 sparse retrieval system. All of your data, instantly sea…3h

    2 Sources

    dale@daleverettToday, we’re launching 1.1 of WonderSearch (YCF26), the world’s #1 sparse retrieval system. All of your data, instantly searchable by AI. #1 on 7/7 sparse retrieval benchmarks. Ahead of BM25, SPLADE, and ELSER v2. And #1 on SciFact, Touché-2020, and DBPedia* But the biggest shift? Architectural. WonderSearch moves retrieval intelligence to query time. > No vector database, just your own. > No pre-embedding your data, just search. > New model? Just switch it up. WonderSearch 1.1 is live. Free quota below ↓5h
    Robert Scoble@ScobleizerRT @daleverett: Today, we’re launching 1.1 of WonderSearch (YCF26), the world’s #1 sparse retrieval system. All of your data, instantly sea…3h