Vector Databases in Practice: Deep Dive
1h 50mIntermediate2024-03-20
Authors
Joon-Pil Hwang
Course details
Vector databases and their uses are transforming how we work. They are fundamentally changing how data is stored, managed, and retrieved through their deep integration with AI models. In this course, learn practical, end-to-end skills on how to build and use vector databases. Instructor Joon-Pil Hwang guides you through building an application that is primarily powered by a vector database, taking you all the way from database creation to usage and even app integration. Learn key considerations in using a vector database in practice, as well as be aware of some common techniques and baseline choices as starting points. Discover keyword, vector, and hybrid searches to find the right data faster, as well as how to apply retrieval-augmented generation - which makes generative AI tools more accurate by grounding them with your data.
Skills covered
Machine LearningDatabase DevelopmentDatabase ManagementArtificial Intelligence (AI)Software DevelopmentDeep Dive (X:Y)
Concepts
0. Introduction
- 01 - The power of AI-powered vector databases
1. Search Functions in a Vector Database
- 02 - A high-level view of vector databases
- 03 - What you can do with vector databases
- 04 - Get set up for the course
- 05 - Keyword filtering and keyword searches
- 06 - Vector searches
- 07 - Searching with filters
- 08 - Hybrid searches
- 09 - Retrieval augmented generation
- 10 - Challenge - Vector database queries
- 11 - Solution - Vector database queries
2. Building a Vector Database
- 12 - Create your own database
- 13 - Work with Weaviate
- 14 - Create an object collection
- 15 - Basic data import in Weaviate
- 16 - Establishing relationships with references
- 17 - Recap - Building a vector database
- 18 - Challenge - Add another object collection
- 19 - Solution - Add another object collection
3. Building a Vector Database-Powered App
- 20 - Web apps and vector databases
- 21 - Create a basic app
- 22 - Connect the app to Weaviate
- 23 - Parsing query responses
- 24 - Recommendations with RAG
- 25 - Challenge - App enhancements
- 26 - Solution - App enhancements
4. Making a Vector Database Work for Your Data
- 27 - Messiness of real data
- 28 - Pre-processing text for vector databases
- 29 - Chunking longer texts
- 30 - Chunk Wikipedia articles
- 31 - Challenge - Import Wikipedia data chunks
- 32 - Solution - Import Wikipedia data chunks
Conclusion
- 33 - Continue learning about vector databases
Related courses
- LLMOps in Practice: A Deep Dive
- Advanced RAG Applications with Vector Databases
- Creating a Chat Tool Using OpenAI Models and Pinecone
- Introduction to Spring AI
- Securing Generative AI: Strategies, Methodologies, Tools, and Best Practices
- Fundamentals of AI Engineering: Principles and Practical Applications
- Introduction to AI-Native Vector Databases
- LLM Foundations: Vector Databases for Caching and Retrieval Augmented Generation (RAG)
Related learn paths
- Vector Databases Professional Certificate
- Explore AI for Data Engineering
- Master Retrieval-Augmented Generation (RAG)
- Manage Your LLMs with LLMOps
- Build AI Products Using Azure AI Services in Your Development Lifecycle
- Working with Data: Collecting, Processing, and Storing Data for AI
- Getting Started with C++
- Advance Your Angular Skills