AI Infused Search - Speaker Deck

Slide 1

Slide 1 text

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

Slide 2

Slide 2 text

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

Slide 3

Slide 3 text

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)

Slide 4

Slide 4 text

Putting the pieces together

Slide 5

Slide 5 text

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

Slide 6

Slide 6 text

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

Slide 7

Slide 7 text

AI Enrichment Flow

Slide 8

Slide 8 text

Knowledge Store

Slide 9

Slide 9 text

AI Enrichment DEMO

Slide 10

Slide 10 text

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

Slide 11

Slide 11 text

Semantic Search DEMO

Slide 12

Slide 12 text

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

Slide 13

Slide 13 text

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

Slide 14

Slide 14 text

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

Slide 15

Slide 15 text

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