Upgrade to Pro — share decks privately, control downloads, hide ads and more …

AI Infused Search

AI Infused Search

This is the presentation I used for the Global AI Tour 2021.

Daron Yondem

June 15, 2021
Tweet

More Decks by Daron Yondem

Other Decks in Technology

Transcript

  1. AI Infused Search
    Daron Yöndem
    http://daron.me
    @daronyondem

    View full-size slide

  2. Levels of Artificial Intelligence
    Easy Medium Hard
    Use an
    existing model
    Customize a
    pre-trained model
    Train a new model
    from scratch
    A pre existing
    Service like a box
    around someone's face
    It can recognize face
    But we need specific
    faces
    Lot’s of time and
    effort needed

    View full-size slide

  3. What is Azure Cognitive Search?
    • A search engine for full text search
    • Rich indexing, with text analysis and optional AI enrichment for
    content extraction and transformation
    • Simple syntax, full Lucene syntax, and typeahead search
    • REST APIs and client libraries in Azure SDKs for .NET, Python, Java,
    and JavaScript
    • State-of-art ranking algorithms through semantic search (preview)

    View full-size slide

  4. Putting the pieces together

    View full-size slide

  5. Indexers
    • Crawler that extracts searchable text and metadata from an
    external Azure data source
    • Azure SQL, Azure Cosmos DB, Azure Table Storage and Blob Storage
    • In Preview: Amazon Redshift, Salesforce Objects, Snowflake

    View full-size slide

  6. AI Enrichment
    • An extension of indexers
    • Built-in skills from Microsoft or custom skills
    • Natural language processing
    • Entity recognition, language detection, key phrase extraction, text
    manipulation, sentiment detection, and PII detection.
    • Image processing skills
    • Optical Character Recognition (OCR) and identification of visual
    features, such as facial detection, image interpretation, image
    recognition

    View full-size slide

  7. AI Enrichment Flow

    View full-size slide

  8. Knowledge Store

    View full-size slide

  9. AI Enrichment
    DEMO

    View full-size slide

  10. Semantic Search
    • Language Understanding
    • Semantic Captions and Highlights
    • Semantic Answers
    • Semantic ranking instead of similarity scoring algorithm.
    • Spell Check

    View full-size slide

  11. Semantic Search
    DEMO

    View full-size slide

  12. Why not a database search?
    • Linguistic-aware text processing (stemming, lemmatization,
    word forms) in 56 languages
    • Autocorrection of misspelled words, synonyms, suggestions,
    scoring controls, facets, and custom tokenization.
    • Offload search

    View full-size slide

  13. Why a database search?
    • Paging in Azure Search relies on the $skip parameter, which is
    currently capped at a maximum of 100000. (use of partitions to
    read all data)
    • No backup / restore
    • Static schema
    • No joins if needed.
    • Optimized heavily for query performance, slower write
    performance

    View full-size slide

  14. Resources
    Semantic Search Sign Up
    https://aka.ms/SemanticSearchPreviewSignup
    Azure Search Documentation
    https://drn.fyi/35mz2e7
    Quickstart: Use cognitive skillset in the Azure portal
    https://drn.fyi/3iFnBpB

    View full-size slide

  15. Thanks
    http://daron.me | @daronyondem
    Grab slides on http://decks.daron.me/

    View full-size slide