Class CassandraEmbeddingStore

java.lang.Object

dev.langchain4j.store.embedding.cassandra.CassandraEmbeddingStore

All Implemented Interfaces:

EmbeddingStore<TextSegment>

public class CassandraEmbeddingStore
extends Object
implements EmbeddingStore<TextSegment>

Implementation of EmbeddingStore using Cassandra.

See Also:

• EmbeddingStore
• MetadataVectorTable

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	CassandraEmbeddingStore.Builder
static class	CassandraEmbeddingStore.BuilderAstra

Field Summary

Fields

Modifier and Type	Field	Description
protected com.datastax.oss.driver.api.core.CqlSession	cassandraSession	Cassandra question.
protected com.dtsx.astra.sdk.cassio.MetadataVectorTable	embeddingTable	Represents an embedding table in Cassandra, it is a table with a vector column.

Constructor Summary

Constructors

Constructor	Description
CassandraEmbeddingStore(com.datastax.oss.driver.api.core.CqlSession session, String tableName, int dimension)	Embedding Store.
CassandraEmbeddingStore(com.datastax.oss.driver.api.core.CqlSession session, String tableName, int dimension, com.dtsx.astra.sdk.cassio.CassandraSimilarityMetric metric)	Embedding Store.

Method Summary

Modifier and Type	Method	Description
String	add(@NonNull Embedding embedding)	Add a new embedding to the store.
String	add(@NonNull Embedding embedding, TextSegment textSegment)	Add a new embedding to the store.
void	add(@NonNull String rowId, @NonNull Embedding embedding)	Add a new embedding to the store.
List<String>	addAll(List<Embedding> embeddingList)	Add multiple embeddings as a single action.
void	addAll(List<String> ids, List<Embedding> embeddingList, List<TextSegment> textSegmentList)	Adds multiple embeddings and their corresponding contents that have been embedded to the store.
static CassandraEmbeddingStore.Builder	builder()
static CassandraEmbeddingStore.BuilderAstra	builderAstra()
void	clear()	Delete all rows.
void	delete()	Delete the table.
List<EmbeddingMatch<TextSegment>>	findRelevant(Embedding embedding, int maxResults, double minScore)
List<EmbeddingMatch<TextSegment>>	findRelevant(Embedding embedding, int maxResults, double minScore, Metadata metadata)	Similarity Search ANN based on the embedding.
com.datastax.oss.driver.api.core.CqlSession	getCassandraSession()
EmbeddingSearchResult<TextSegment>	search(EmbeddingSearchRequest request)	Searches for the most similar (closest in the embedding space) Embeddings.

Methods inherited from class Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface EmbeddingStore

addAll, generateIds, remove, removeAll, removeAll, removeAll

Field Details

embeddingTable

protected com.dtsx.astra.sdk.cassio.MetadataVectorTable embeddingTable

Represents an embedding table in Cassandra, it is a table with a vector column.

cassandraSession

protected com.datastax.oss.driver.api.core.CqlSession cassandraSession

Cassandra question.

Constructor Details

CassandraEmbeddingStore

public CassandraEmbeddingStore(com.datastax.oss.driver.api.core.CqlSession session,
 String tableName,
 int dimension)

Embedding Store.

Parameters:

session - cassandra Session

tableName - table name

dimension - dimension

CassandraEmbeddingStore

public CassandraEmbeddingStore(com.datastax.oss.driver.api.core.CqlSession session,
 String tableName,
 int dimension,
 com.dtsx.astra.sdk.cassio.CassandraSimilarityMetric metric)

Embedding Store.

Parameters:

session - cassandra Session

tableName - table name

dimension - dimension

metric - metric

Method Details

delete

public void delete()

Delete the table.

clear

public void clear()

Delete all rows.

getCassandraSession

public com.datastax.oss.driver.api.core.CqlSession getCassandraSession()

builder

public static CassandraEmbeddingStore.Builder builder()

builderAstra

public static CassandraEmbeddingStore.BuilderAstra builderAstra()

add

public String add(@NonNull Embedding embedding)

Add a new embedding to the store. - the row id is generated - text and metadata are not stored

Specified by:

add in interface EmbeddingStore<TextSegment>

Parameters:

embedding - representation of the list of floats

Returns:

newly created row id

add

public String add(@NonNull Embedding embedding,
 TextSegment textSegment)

Add a new embedding to the store. - the row id is generated - text and metadata coming from the text Segment

Specified by:

add in interface EmbeddingStore<TextSegment>

Parameters:

embedding - representation of the list of floats

textSegment - text content and metadata

Returns:

newly created row id

add

public void add(@NonNull String rowId,
 @NonNull Embedding embedding)

Add a new embedding to the store.

Specified by:

add in interface EmbeddingStore<TextSegment>

Parameters:

rowId - the row id

embedding - representation of the list of floats

addAll

public List<String> addAll(List<Embedding> embeddingList)

Add multiple embeddings as a single action.

Specified by:

addAll in interface EmbeddingStore<TextSegment>

Parameters:

embeddingList - embeddings list

Returns:

list of new row if (same order as the input)

addAll

public void addAll(List<String> ids,
 List<Embedding> embeddingList,
 List<TextSegment> textSegmentList)

Description copied from interface: EmbeddingStore

Adds multiple embeddings and their corresponding contents that have been embedded to the store.

Specified by:

addAll in interface EmbeddingStore<TextSegment>

Parameters:

ids - A list of IDs associated with the added embeddings.

embeddingList - A list of embeddings to be added to the store.

textSegmentList - A list of original contents that were embedded.

search

public EmbeddingSearchResult<TextSegment> search(EmbeddingSearchRequest request)

Description copied from interface: EmbeddingStore

Searches for the most similar (closest in the embedding space) Embeddings.
All search criteria are defined inside the EmbeddingSearchRequest.
EmbeddingSearchRequest.filter() can be used to filter by various metadata entries (e.g., user/memory ID). Please note that not all EmbeddingStore implementations support Filtering.

Specified by:

search in interface EmbeddingStore<TextSegment>

Parameters:

request - A request to search in an EmbeddingStore. Contains all search criteria.

Returns:

An EmbeddingSearchResult containing all found Embeddings.

findRelevant

public List<EmbeddingMatch<TextSegment>> findRelevant(Embedding embedding,
 int maxResults,
 double minScore)

findRelevant

public List<EmbeddingMatch<TextSegment>> findRelevant(Embedding embedding,
 int maxResults,
 double minScore,
 Metadata metadata)

Similarity Search ANN based on the embedding.

Parameters:

embedding - vector

maxResults - max number of results

minScore - score minScore

metadata - map key-value to build a metadata filter

Returns:

list of matching results