Package org.springframework.ai.vectorstore.hanadb

Class HanaCloudVectorStore

java.lang.Object
org.springframework.ai.vectorstore.observation.AbstractObservationVectorStore
org.springframework.ai.vectorstore.hanadb.HanaCloudVectorStore
All Implemented Interfaces:
Consumer<List<Document>>, DocumentWriter, VectorStore, VectorStoreRetriever
public class HanaCloudVectorStore extends AbstractObservationVectorStore
The SAP HANA Cloud vector engine offers multiple use cases in AI scenarios. Recent advances in Generative AI (GenAI) and Large Language Models (LLM) have led to increased awareness of and popularity for vector databases. Similarity search, a key functionality of vector databases, complements traditional relational databases as well as full-text search systems. Using natural language text as an example, embedding functions map data to high dimensional vectors to preserve their semantic similarity. Developers can then use vector-based semantic search to find similarity between different passages of text. Because the data within an LLM is current only up to a specific point in time, vector databases can offer additional relevant text to make searches more accurate – known as Retrieval Augmented Generation (RAG). Therefore, the addition of RAG to an LLM using a vector database like SAP HANA Cloud provides an effective approach to increase the quality of responses from an LLM. The SAP HANA Cloud vector engine supports the create, read, update, and delete (CRUD) operations involving vectors using SQL. HanaCloudVectorStore is an implementation of org.springframework.ai.vectorstore.VectorStore interface that provides implementation of COSINE_SIMILARITY function introduced in HanaDB in Mar, 2024 Hana DB introduced a new datatype REAL_VECTOR that can store embeddings generated by org.springframework.ai.embedding.EmbeddingModel
Since:
1.0.0
Author:
Rahul Mittal, Christian Tzolov, Sebastien Deleuze, Soby Chacko
See Also: