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

    LlamaIndex launches Extract v2.5 for document extraction

    LlamaIndex says the update can separate printed values from handwritten annotations on scanned forms and locate evidence for extracted values.

    JL
    1 Source, ,

    TLDR

    LlamaIndex introduced Extract v2.5, a set of document-extraction agents available on LlamaParse. The company reports improved scores on its ExtractBench tests for long lists, records spanning pages and scanned forms, with no increase in per-page pricing. It says the update adapts extraction to document layouts and adds improved citations that locate supporting evidence for extracted values.

    Combined views

    2.8K

    1 Source, first seen 4h ago

    Combined views

    2.8K

    1 Source, first seen 4h ago

    30 likes
    4h ago
    first seen 4h ago
    30 likes
    6 comments
    17 saves
    5 reposts
    6 comments
    17 saves
    5 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

    1 Source

    @jerryjliu0We got extremely good at extracting a scanned from layer by layer 📋 - from printed fields, overlaid text, handwriting, and reviewer annotations. For instance, on an annotated permit, our Extract agents can extract out both the original permit number but also any drawn/handwritten annotations on top. they're also grounded exactly in the source text. our agents reduce error rates by 2x+, at a small fraction of the price compared to using a frontier model. Our Extract v2.5 agents are SOTA in price/performance, and scanned forms are just one example. Come check it out! Extract v2.5: https://www.llamaindex.ai/blog/introducing-extract-v2-5 Available in LlamaParse: https://cloud.llamaindex.ai/4h

    1 Source

    @jerryjliu0We got extremely good at extracting a scanned from layer by layer 📋 - from printed fields, overlaid text, handwriting, and reviewer annotations. For instance, on an annotated permit, our Extract agents can extract out both the original permit number but also any drawn/handwritten annotations on top. they're also grounded exactly in the source text. our agents reduce error rates by 2x+, at a small fraction of the price compared to using a frontier model. Our Extract v2.5 agents are SOTA in price/performance, and scanned forms are just one example. Come check it out! Extract v2.5: https://www.llamaindex.ai/blog/introducing-extract-v2-5 Available in LlamaParse: https://cloud.llamaindex.ai/4h