Introduction to AI-Native Vector Databases

Introduction

• Learning AI-native vector databases
• What you should know
• The superpower of vector databases

1. Data: What Data Do Vector Databases Store and How Is It Stored?

• Structured versus unstructured data
• Human-understandable versus machine-understandable data
• Drawing out and visualizing vector representations of data
• Introduce the concept of distance between two vectors
• Challenge: Working with vectors
• Solution: Working with vectors

2. Natural Querying: How Do You Search for Data in a Vector Database?

• Frame the query as a question or search
• Generate the question in machine-understandable language
• Adding data to a vector database
• Performing semantic searches using Weaviate
• Challenge: Vector search with Weaviate
• Solution: Vector Search with Weaviate

3. Machine Learning Vectors: How Does a Vector Database Understand Your Data?

• Machine learning models and object classification
• Translating data from human to machine-understandable
• ML models and vector embeddings
• Challenge: Search with images and text
• Solution: Search with images and text

4. Scalability: What Does a Vector Database Need to Do?

• Scalability: When to use a vector DB
• Ways to measure performance of a vector DB
• CRUD operations in vector DBs
• Challenge: CRUD and performance
• Solution: CRUD and performance

5. Demonstrate Vector DBs and Use Cases

• Vector DB1: E-commerce RecSys
• Vector DB2: Hybrid search
• Vector DB3: Retrieval augmented generation
• Challenge: Vector DBs
• Solution: Vector DBs

Conclusion

• Continue your AI-native vector databases learning journey