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.

017286889e25c87cb44b20ceca2d1d79?s=128

Daron Yondem

June 15, 2021
Tweet

Transcript

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

  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
  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)
  4. Putting the pieces together

  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
  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
  7. AI Enrichment Flow

  8. Knowledge Store

  9. AI Enrichment DEMO

  10. Semantic Search • Language Understanding • Semantic Captions and Highlights

    • Semantic Answers • Semantic ranking instead of similarity scoring algorithm. • Spell Check
  11. Semantic Search DEMO

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