Package sk.iway.iwcm.rag.vectorstore

Interface VectorStore

All Known Implementing Classes:

MariaDbVectorStore, PgVectorStore, VectorStoreRouter

public interface VectorStore

Abstraction for vector storage and similarity search. Handles ONLY native vector storage and search operations. Entity CRUD operations are handled by EmbeddingChunkRepository (JPA).

Method Summary

Modifier and Type	Method	Description
Map<String,float[]>	getExistingEmbeddingsByHash(String entityType, long entityId, String embeddingProvider, String embeddingModel, int domainId)	Get existing embeddings for an entity and domain, keyed by content hash.
boolean	initializeSchema()	Initialize the database-specific vector schema if needed.
boolean	isAvailable()	Check if the vector store can be used in the current runtime configuration.
boolean	isAvailableAndInitialized()	Check if the vector store is available and schema is initialized.
default boolean	recreateIndex()	Recreate the database-specific vector index using the configured metric.
boolean	resetDimensions(int dimensions)	Delete all stored embeddings and resize the vector column.
List<VectorSearchResult>	search(float[] queryEmbedding, String embeddingProvider, String embeddingModel, RagEntityType entityType, Integer domainId, String language, int limit, Map<String,Object> bonusParams)	Find the most similar chunks to the query embedding.
List<VectorSearchResult>	searchFulltext(String query, String embeddingProvider, String embeddingModel, RagEntityType entityType, Integer domainId, String language, int limit, Map<String,Object> bonusParams)	Find relevant chunks by fulltext search in chunk text.
void	updateEmbedding(Long id, float[] embedding)	Update the embedding vector for an existing chunk entity.
void	updateEmbeddingBatch(List<Long> ids, List<float[]> embeddings)	Update embedding vectors for multiple existing chunk entities in a batch.

Method Details

updateEmbedding

void updateEmbedding(Long id,
 float[] embedding)

Update the embedding vector for an existing chunk entity. The entity must already be saved via EmbeddingChunkRepository.

Parameters:

id - the chunk entity ID

embedding - the embedding vector

updateEmbeddingBatch

void updateEmbeddingBatch(List<Long> ids,
 List<float[]> embeddings)

Update embedding vectors for multiple existing chunk entities in a batch. All entities must already be saved via EmbeddingChunkRepository.

Parameters:

ids - the chunk entity IDs

embeddings - the embedding vectors (must match ids in size and order)

search

List<VectorSearchResult> search(float[] queryEmbedding,
 String embeddingProvider,
 String embeddingModel,
 RagEntityType entityType,
 Integer domainId,
 String language,
 int limit,
 Map<String,Object> bonusParams)

Find the most similar chunks to the query embedding.

Parameters:

queryEmbedding - the query vector

embeddingProvider - provider used to generate/query embeddings

embeddingModel - model used to generate/query embeddings

entityType - entity type to filter by (null for all)

domainId - domain ID to filter by (null for all)

language - language to filter by (null for all)

limit - max number of results

bonusParams - optional store-specific filters, such as document root groups

Returns:

list of search results ordered by similarity (descending)

searchFulltext

List<VectorSearchResult> searchFulltext(String query,
 String embeddingProvider,
 String embeddingModel,
 RagEntityType entityType,
 Integer domainId,
 String language,
 int limit,
 Map<String,Object> bonusParams)

Find relevant chunks by fulltext search in chunk text.

Parameters:

query - textual query

embeddingProvider - provider used to filter rows

embeddingModel - model used to filter rows

entityType - entity type to filter by (null for all)

domainId - domain ID to filter by (null for all)

language - language to filter by (null for all)

limit - max number of results

bonusParams - optional store-specific filters, such as document root groups and fallback flags

Returns:

list of search results ordered by fulltext rank (descending)

isAvailable

boolean isAvailable()

Check if the vector store can be used in the current runtime configuration. This does not guarantee that required schema objects already exist.

isAvailableAndInitialized

boolean isAvailableAndInitialized()

Check if the vector store is available and schema is initialized. Implementations should return true only when operations can be executed safely.

initializeSchema

boolean initializeSchema()

Initialize the database-specific vector schema if needed.

recreateIndex

default boolean recreateIndex()

Recreate the database-specific vector index using the configured metric. Implementations without a native index-management capability may keep the default.

Returns:

true when the index was recreated successfully

resetDimensions

boolean resetDimensions(int dimensions)

Delete all stored embeddings and resize the vector column.

Parameters:

dimensions - new vector dimensions

getExistingEmbeddingsByHash

Map<String,float[]> getExistingEmbeddingsByHash(String entityType,
 long entityId,
 String embeddingProvider,
 String embeddingModel,
 int domainId)

Get existing embeddings for an entity and domain, keyed by content hash. Used to skip re-embedding unchanged chunks.

Parameters:

entityType - entity type of the indexed object

entityId - ID of the indexed object

embeddingProvider - provider that generated the embeddings

embeddingModel - model that generated the embeddings

domainId - domain that owns the indexed object

Returns:

existing embeddings keyed by content hash