Vector Databases are a special type of  database that plays a very essential role in AI applications. A Vector Database its queries and storage mechanisms are different from traditional relational and NoSQL Databases. Traditional Databases search for an exact match, but Vector Databases perform similarity searches ie all the results that are similar to the query based on certain parameters. Spring Ai Vector Database utilizes the AI Model intelligence and provides similar results.

Vector Databases perform similarity searches and return relevant data

Spring Ai provides a VectorStore interface, which provides all the required functions to communicate with Vector Databases. When a user query is sent to the AI Model, it retrieves a set of Similar Documents from Vector Databases, these Documents serve as a context for user questions. this technique is also called Retrieval Augmented Generation or RAG.

Spring Ai provides a SimpleVectorStore,  inmemory simple implementation of vector storage

Below is the list of Vector Databases available today.

• Apache Cassandra.
• Chroma Vector Store.
• Elasticsearch Vector Store.
• GemFire Vector Store.
• MariaDB Vector Store.
• Milvus Vector Store.
• MongoDB Atlas Vector Store.
• Neo4j Vector Store.
• OpenSearch Vector Store.
• Oracle Vector Store.
• PgVector Store.
• Pinecone Vector Store.
• Qdrant Vector Store.
• Redis Vector Store.
• SAP Hana Vector Store.
• Typesense Vector Store.
• Weaviate Vector Store.