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

    Weaviate Shares Late-Interaction Multi-Vector Retrieval Update

    Weaviate posted about late-interaction multi-vector retrieval for embedding PDF pages as images.

    OK
    CS
    WA
    5 Sources, 30d ago, first seen 30d ago

    TLDR

    Connor Shorten retweeted a post from Weaviate stating the company stopped asking PDFs to become text before searching them. The post describes late-interaction multi-vector retrieval that embeds PDF pages as images. A generated headline in the packet reads Weaviate Launches Multi-Vector Retrieval For Direct PDF Image Search. A generated source summary adds that the approach enables search over charts and tables.

    Combined views

    4.4K

    5 Sources, first seen 30d ago

    Combined views

    4.4K

    5 Sources, first seen 30d ago

    30 likes
    30 likes
    1 comments
    17 saves
    18 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    1 comments
    17 saves
    18 reposts

    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

    5 Sources

    @weaviate_ioWe stopped asking PDFs to become text before we searched them. With late-interaction multi-vector retrieval, you can embed each PDF page as an image and search the charts, tables, and layouts that text extraction misses. We tested it on 92 pages of NVIDIA investor decks. A query about automotive revenue retrieved the exact five-quarter bar chart, even though the words "change" and "over time" never appeared on the page. No OCR. No chunking. Just drag your PDFs into Weaviate Cloud and start asking questions. See how it works: https://weaviate.io/blog/charts-tables-pdfs?utm_source=linkedin&utm_medium=w_social&utm_campaign=query_agent&utm_content=blog_annoucement_808982937
    @CShorten30RT @weaviate_io: We stopped asking PDFs to become text before we searched them. With late-interaction multi-vector retrieval, you can embe…
    @prempvThis is very cool. Late interaction techniques over multimodal docs can truly help tackle the long tail of retrieval. cc @lateinteraction
    @lateinteractionRT @weaviate_io: We stopped asking PDFs to become text before we searched them. With late-interaction multi-vector retrieval, you can embe…

    5 Sources

    @weaviate_ioWe stopped asking PDFs to become text before we searched them. With late-interaction multi-vector retrieval, you can embed each PDF page as an image and search the charts, tables, and layouts that text extraction misses. We tested it on 92 pages of NVIDIA investor decks. A query about automotive revenue retrieved the exact five-quarter bar chart, even though the words "change" and "over time" never appeared on the page. No OCR. No chunking. Just drag your PDFs into Weaviate Cloud and start asking questions. See how it works: https://weaviate.io/blog/charts-tables-pdfs?utm_source=linkedin&utm_medium=w_social&utm_campaign=query_agent&utm_content=blog_annoucement_808982937
    @CShorten30RT @weaviate_io: We stopped asking PDFs to become text before we searched them. With late-interaction multi-vector retrieval, you can embe…
    @prempvThis is very cool. Late interaction techniques over multimodal docs can truly help tackle the long tail of retrieval. cc @lateinteraction
    @lateinteractionRT @weaviate_io: We stopped asking PDFs to become text before we searched them. With late-interaction multi-vector retrieval, you can embe…