Package dev.langchain4j.store.embedding.astradb

Class AstraDbEmbeddingStore

java.lang.Object

dev.langchain4j.store.embedding.astradb.AstraDbEmbeddingStore

All Implemented Interfaces:

EmbeddingStore<TextSegment>

public class AstraDbEmbeddingStore
extends Object
implements EmbeddingStore<TextSegment>

Implementation of EmbeddingStore using AstraDB.

See Also:

• EmbeddingStore

Field Summary

Fields

Modifier and Type	Field	Description
static final String	KEY_ATTRIBUTES_BLOB	Saving the text chunk as an attribut.
static final String	KEY_SIMILARITY	Metadata used for similarity.

Constructor Summary

Constructors

Constructor	Description
AstraDbEmbeddingStore(@NonNull com.dtsx.astra.sdk.AstraDBCollection client)	Initialization of the store with an EXISTING collection.
AstraDbEmbeddingStore(@NonNull com.dtsx.astra.sdk.AstraDBCollection client, int itemsPerChunk, int concurrentThreads)	Initialization of the store with an EXISTING collection.

Method Summary

Modifier and Type	Method	Description
String	add(Embedding embedding)	Adds a given embedding to the store.
String	add(Embedding embedding, TextSegment textSegment)	Adds a given embedding and the corresponding content that has been embedded to the store.
void	add(String id, Embedding embedding)	Adds a given embedding to the store.
List<String>	addAll(List<Embedding> embeddings)	Adds multiple embeddings to the store.
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.
void	clear()	Delete all records from the table.
List<EmbeddingMatch<TextSegment>>	findRelevant(Embedding referenceEmbedding, int maxResults, double minScore)	Finds the most relevant (closest in space) embeddings to the provided reference embedding.
List<EmbeddingMatch<TextSegment>>	findRelevant(Embedding referenceEmbedding, io.stargate.sdk.data.domain.query.Filter metaDatafilter, int maxResults, double minScore)	Semantic search with metadata filtering.

Methods inherited from class java.lang.Object

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

Methods inherited from interface dev.langchain4j.store.embedding.EmbeddingStore

addAll, findRelevant, findRelevant, findRelevant, generateIds, remove, removeAll, removeAll, removeAll, search

Field Details

KEY_ATTRIBUTES_BLOB

public static final String KEY_ATTRIBUTES_BLOB

Saving the text chunk as an attribut.

See Also:

• Constant Field Values

KEY_SIMILARITY

public static final String KEY_SIMILARITY

Metadata used for similarity.

See Also:

• Constant Field Values

Constructor Details

AstraDbEmbeddingStore

public AstraDbEmbeddingStore(@NonNull
 @NonNull com.dtsx.astra.sdk.AstraDBCollection client)

Initialization of the store with an EXISTING collection.

Parameters:

client - astra db collection client

AstraDbEmbeddingStore

public AstraDbEmbeddingStore(@NonNull
 @NonNull com.dtsx.astra.sdk.AstraDBCollection client,
 int itemsPerChunk,
 int concurrentThreads)

Initialization of the store with an EXISTING collection.

Parameters:

client - astra db collection client

itemsPerChunk - size of 1 chunk in between 1 and 20

Method Details

clear

public void clear()

Delete all records from the table.

add

public String add(Embedding embedding)

Adds a given embedding to the store.

Specified by:

add in interface EmbeddingStore<TextSegment>

Parameters:

embedding - The embedding to be added to the store.

Returns:

The auto-generated ID associated with the added embedding.

add

public String add(Embedding embedding,
 TextSegment textSegment)

Adds a given embedding and the corresponding content that has been embedded to the store.

Specified by:

add in interface EmbeddingStore<TextSegment>

Parameters:

embedding - The embedding to be added to the store.

textSegment - Original content that was embedded.

Returns:

The auto-generated ID associated with the added embedding.

add

public void add(String id,
 Embedding embedding)

Adds a given embedding to the store.

Specified by:

add in interface EmbeddingStore<TextSegment>

Parameters:

id - The unique identifier for the embedding to be added.

embedding - The embedding to be added to the store.

addAll

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

Adds multiple embeddings to the store.

Specified by:

addAll in interface EmbeddingStore<TextSegment>

Parameters:

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

Returns:

A list of auto-generated IDs associated with the added embeddings.

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.

findRelevant

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

Finds the most relevant (closest in space) embeddings to the provided reference embedding.

Specified by:

findRelevant in interface EmbeddingStore<TextSegment>

Parameters:

referenceEmbedding - The embedding used as a reference. Returned embeddings should be relevant (closest) to this one.

maxResults - The maximum number of embeddings to be returned.

minScore - The minimum relevance score, ranging from 0 to 1 (inclusive). Only embeddings with a score of this value or higher will be returned.

Returns:

A list of embedding matches. Each embedding match includes a relevance score (derivative of cosine distance), ranging from 0 (not relevant) to 1 (highly relevant).

findRelevant

public List<EmbeddingMatch<TextSegment>> findRelevant(Embedding referenceEmbedding,
 io.stargate.sdk.data.domain.query.Filter metaDatafilter,
 int maxResults,
 double minScore)

Semantic search with metadata filtering.

Parameters:

referenceEmbedding - vector

metaDatafilter - fileter for metadata

maxResults - limit

minScore - threshold

Returns:

records