feature: adding vector db example using vertex ai

[pabloxtiyo]

This project serves as an example of how to leverage the Spring AI framework to build applications that utilize generative AI capabilities, specifically focusing on vector embeddings and similarity search.

Key Features & Technologies:

• Spring AI: Utilizes the Spring AI library to simplify the integration of AI functionalities into a Spring Boot application.
• Google Cloud Vertex AI Embeddings: Demonstrates how to generate text embeddings using Google Cloud's Vertex AI PaLM 2 embedding models. These embeddings convert textual data into numerical vectors, capturing semantic meaning.
• MariaDB as a Vector Database: Shows how MariaDB, with its vector storage and search capabilities (e.g., using its VECTOR data type and functions like VECTOR_COSINE_DISTANCE), can be used to store and perform similarity searches on the generated Vertex AI embeddings.
• Vector Search/Similarity Search: The core functionality likely involves ingesting data, generating embeddings for it, storing these embeddings in MariaDB, and then performing queries to find items semantically similar to a given input query.

Purpose:

The primary goal of this example is to provide developers with a practical, hands-on demonstration of:

1. Generating high-quality text embeddings with Vertex AI.
2. Storing these vector embeddings efficiently in MariaDB.
3. Performing semantic similarity searches against the stored vectors using Spring AI abstractions.
4. Integrating these components within a standard Spring Boot application.