Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
- Integrate AI models with Azure SQL Database using external models, the vector data type, and built-in AI functions. Design embedding strategies, generate embeddings from text, and implement maintenance patterns.
By the end of this module, you'll be able to:
- Evaluate AI models for SQL database workloads based on capabilities and performance requirements.
- Create and manage external models to reference AI endpoints from Transact-SQL.
- Design embeddings with appropriate chunking strategies.
- Generate and store embeddings using built-in SQL AI functions.
- Choose maintenance approaches to keep embeddings aligned with source data.
- Implement intelligent search capabilities in SQL Server and Azure SQL by combining traditional full-text search with semantic vector search. Learn to choose search approaches, prepare SQL for vector search, and implement vector, hybrid, and ranking-based search patterns.
By the end of this module, you'll be able to:
- Choose between full-text, semantic vector, and hybrid search approaches.
- Implement full-text search for keyword-based queries.
- Design for vector data including vector data type, indexes, and size.
- Evaluate vector index types and metrics, and choose between ANN and ENN.
- Implement vector search using vector-related functions.
- Implement hybrid search and Reciprocal Rank Fusion (RRF).
- Evaluate performance of vector and hybrid search.
- Learn how to implement Retrieval Augmented Generation (RAG) patterns using Azure SQL Database. Identify RAG use cases, prepare database context for Large Language Model (LLM) processing, construct augmented prompts, and process model responses.
By the end of this module, you're able to:
- Identify use cases for RAG in SQL-based applications
- Convert structured database data to JSON for LLM processing
- Create prompts that combine instructions with retrieved database context
- Send retrieval results to an LLM and extract responses
