Package dev.langchain4j.store.embedding.azure.cosmos.mongo.vcore

Class AzureCosmosDbMongoVCoreEmbeddingStore

java.lang.Object

dev.langchain4j.store.embedding.azure.cosmos.mongo.vcore.AzureCosmosDbMongoVCoreEmbeddingStore

All Implemented Interfaces:

EmbeddingStore<TextSegment>

public class AzureCosmosDbMongoVCoreEmbeddingStore
extends Object
implements EmbeddingStore<TextSegment>

Represents an Azure CosmosDB Mongo vCore as an embedding store.

More info to set up MongoDb as vectorDatabase.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	AzureCosmosDbMongoVCoreEmbeddingStore.Builder
static enum	AzureCosmosDbMongoVCoreEmbeddingStore.SimilarityMetric
static enum	AzureCosmosDbMongoVCoreEmbeddingStore.VectorIndexType

Constructor Summary

Constructors

Constructor	Description
AzureCosmosDbMongoVCoreEmbeddingStore(com.mongodb.client.MongoClient mongoClient, String connectionString, String databaseName, String collectionName, String indexName, String applicationName, com.mongodb.client.model.CreateCollectionOptions createCollectionOptions, Boolean createIndex, String kind, Integer numLists, Integer dimensions, Integer m, Integer efConstruction, Integer efSearch)

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> embeddings, List<TextSegment> embedded)	Adds multiple embeddings and their corresponding contents that have been embedded to the store.
static AzureCosmosDbMongoVCoreEmbeddingStore.Builder	builder()
List<EmbeddingMatch<TextSegment>>	findRelevant(Embedding referenceEmbedding, int maxResults, double minScore)
EmbeddingSearchResult<TextSegment>	search(EmbeddingSearchRequest request)	Searches for the most similar (closest in the embedding space) Embeddings.

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, generateIds, remove, removeAll, removeAll, removeAll

Constructor Details

AzureCosmosDbMongoVCoreEmbeddingStore

public AzureCosmosDbMongoVCoreEmbeddingStore(com.mongodb.client.MongoClient mongoClient,
 String connectionString,
 String databaseName,
 String collectionName,
 String indexName,
 String applicationName,
 com.mongodb.client.model.CreateCollectionOptions createCollectionOptions,
 Boolean createIndex,
 String kind,
 Integer numLists,
 Integer dimensions,
 Integer m,
 Integer efConstruction,
 Integer efSearch)

Parameters:

mongoClient - - mongoClient for the Azure CosmosDB Mongo vCore

connectionString - - connection string required to connect to Azure Cosmos Mongo vCore

databaseName - - databaseName for the mongoDb vCore

collectionName - - collection name for the mongoDB vCore

indexName - - index name for the mongoDB vCore collection

applicationName - - application name for the client for tracking and logging

createCollectionOptions - - options for creating a collection

createIndex - - set to true if you want the application to create an index, or false if you want to create it manually.

kind - - Type of vector index to create. Possible options are: - vector-ivf - vector-hnsw: available as a preview feature only, to enable visit https://learn.microsoft.com/en-us/azure/azure-resource-manager/management/preview-features

numLists - - This integer is the number of clusters that the inverted file (IVF) index uses to group the vector data. We recommend that numLists is set to documentCount/1000 for up to 1 million documents and to sqrt(documentCount) for more than 1 million documents. Using a numLists value of 1 is akin to performing brute-force search, which has limited performance.

dimensions - - Number of dimensions for vector similarity. The maximum number of supported dimensions is 2000.

m - - used only for vector -hnsw. The max number of connections per layer (16 by default, minimum value is 2, maximum value is 100). Higher m is suitable for datasets with high dimensionality and/or high accuracy requirements.

efConstruction - - used only for vector -hnsw. The size of the dynamic candidate list for constructing the graph (64 by default, minimum value is 4, maximum value is 1000). Higher ef_construction will result in better index quality and higher accuracy, but it will also increase the time required to build the index. ef_construction has to be at least 2 * m.

efSearch - - used only for vector -hnsw. The size of the dynamic candidate list for search (40 by default). A higher value provides better recall at the cost of speed.

Method Details

builder

public static AzureCosmosDbMongoVCoreEmbeddingStore.Builder builder()

add

public String add(Embedding embedding)

Description copied from interface: EmbeddingStore

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 void add(String id,
 Embedding embedding)

Description copied from interface: EmbeddingStore

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.

add

public String add(Embedding embedding,
 TextSegment textSegment)

Description copied from interface: EmbeddingStore

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.

addAll

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

Description copied from interface: EmbeddingStore

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.

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 referenceEmbedding,
 int maxResults,
 double minScore)

addAll

public void addAll(List<String> ids,
 List<Embedding> embeddings,
 List<TextSegment> embedded)

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.

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

embedded - A list of original contents that were embedded.