Oracle Database 23ai: Oracle AI Vector Search Fundamentals
Leverage the key capability of Oracle Database 23ai to design and manage Artificial Intelligence (AI) workloads using the new Oracle AI Vector Search feature. Learn how to create tables with vector data type, load data, and the query them based on semantics, rather than keywords. You will learn to perform semantic search on unstructured data by combining it with your relational data in one single system. With hands-on practices, you’ll be be able to reinforce the learning of the new AI Vector Search feature and its capabilities.
STUDENTS WILL LEARN TO
- Describe AI Vector Search features, benefits, and capabilities
- Determine the AI Vector Search Workflow
- Run basic queries on vectors
- Create vector indexes to run similarity search
- Determine vector memory considerations
- Perform DML and DDL operations on vectors
- Create and find nearest vectors
- Narrow search results using attribute filtering
- Determine the closes vectors by using additional vector distance functions
- Perform additional vector operations, such as creating, converting, and describing vectors
About the course
COURSE OUTLINE
MODULE 01: Course Overview
- Course Overview
- Benefits
- Practice 1-1: Configuring the Landing Pad VM
- Practice 1-2: Updating the ora File
- Practice 1-3: Creating a User
MODULE 02: Overview of Oracle AI Vector Search
- VECTOR Data Type
- Vector Embeddings
- Similarity Search
- Vector Embedding Models
- Import Embedding Models
MODULE 03: Oracle AI Vector Search Workflow
- Generate Vector Embeddings
- Store Vector Embeddings
- Vector Indexes
- Query Data with Similarity Searches
MODULE 04: Running Basic Queries on Vectors
- Basic Queries
- Practice 4-1: Selecting the Values from a Vector
- Demo: Running Basic Queries on Vectors
MODULE 05: Vector Indexes and Memory Management
- Vector Indexes and Memory
- Memory Considerations
MODULE 06: DML Operations on Vectors
- Create a Table with a Vector Column
- Vector DML
- Summary
- Practice 6-1: Performing DML Operations on Vectors
- Demo: DML Operations on Vectors
MODULE 07: DDL Operations on Vectors
- Tables with Different Vector Formats
- DDL Operations on Vectors
- Summary
- Demo: Vector DDL
- Prohibited Operations
- Practice 7-1: Performing DDL Operations on Vector Columns
MODULE 08: Finding Nearest Vectors
- Vector Constructor
- Vector Distance
- Demo: Create and Find Nearest Vectors
- Practice 8-1: Vector Distance
MODULE 09: Closest Vector Search Techniques
- Exact Similarity Search
- Approximate Similarity Search
- Multi-Vector Similarity Search
- Summary
- Demo: Find Closest Vectors
- Practice 9-1: Finding the Closest Vectors to a Given Vector
- Practice 9-2: Finding Vectors Based on Vectors Clustered in Groups
MODULE 10: Narrowing Search Results
- Attribute Filtering
- Summary
- Demo: Narrow Search
- Practice 10-1: Setting Up a Table with Sample Vectors
- Practice 10-2: Attribute Filtering
MODULE 11: Advanced Distance Functions
- Other Distance Functions
- Summary
- Demo: Test Other Distance Functions
- Practice 11-1: Setting Up a Table with Sample Vectors
- Practice 11-2: Using Alternative Distance Functions
- Practice 11-3: Using Alternative Vector Distance
- Practice 11-4: Using Shorthand Syntax to Look for the Closest Vectors
MODULE 12: Additional Vector Functions
- Other Vector Functions
- Summary
- Demo: Test Other Vector Functions
- Practice 12-1: Other Vector Functions
MODULE 13: Course Conclusion
- Course Conclusion
Register for Training
Schedule
| Start Date | End Date | Duration (days) | Price | Code |
|---|
