Рет қаралды 6,595
Learn how to build generative AI applications in Java using the Spring AI EmbeddingClient and the PostgreSQL pgvector extension.
First, you’ll be introduced to the Spring AI ChatClient that uses the OpenAI GPT-4 model to generate recommendations based on user prompts. Next, explore how to deploy PostgreSQL with the pgvector extension and perform vector similarity searches using the Spring AI EmbeddingClient and Spring JdbcClient. In the end, discover how to optimize and scale the application using specialized indexes such as HNSW and distributed PostgreSQL (YugabyteDB).
Here you can find a complete version of the application:
github.com/YugabyteDB-Samples...
0:00 Learning plan
0:45 Sample application
1:29 Spring AI chatclient
3:30 Limitations of the current implementation
4:49 Deploying PostgreSQL pgvector in Docker
5:42 Preloading an Airbnb dataset
7:12 Exploring the dataset
8:59 Using spring AI embeddingclient with pgvector
14:10 Pptimizing the search with HNSW index
17:42 Scaling with distributed PostgreSQL (YugabyteDB)
21:12 Homework
Curious to learn more about databases? Follow me here:
* Medium: / magda7817
* Twitter: / denismagda