Package dev.langchain4j.store.embedding.vespa

Class VespaEmbeddingStore

java.lang.Object

dev.langchain4j.store.embedding.vespa.VespaEmbeddingStore

All Implemented Interfaces:

EmbeddingStore<TextSegment>

public class VespaEmbeddingStore
extends Object
implements EmbeddingStore<TextSegment>

Represents the Vespa - search engine and vector database. Does not support storing Metadata yet. Example server configuration contains cosine similarity search rank profile, of course other Vespa neighbor search methods are supported too. Read more here.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	VespaEmbeddingStore.Builder

Constructor Summary

Constructors

Constructor	Description
VespaEmbeddingStore(String url, String keyPath, String certPath, Duration timeout, String namespace, String documentType, String clusterName, String rankProfile, Integer targetHits, Boolean avoidDups, Boolean logRequests, Boolean logResponses)	Creates a new VespaEmbeddingStore instance.

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 new embedding with provided ID 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 VespaEmbeddingStore.Builder	builder()
void	removeAll()	Removes all embeddings from the store.
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, findRelevant, findRelevant, findRelevant, findRelevant, generateIds, remove, removeAll, removeAll

Constructor Details

VespaEmbeddingStore

public VespaEmbeddingStore(String url,
 String keyPath,
 String certPath,
 Duration timeout,
 String namespace,
 String documentType,
 String clusterName,
 String rankProfile,
 Integer targetHits,
 Boolean avoidDups,
 Boolean logRequests,
 Boolean logResponses)

Creates a new VespaEmbeddingStore instance.

Parameters:

url - server url, local or cloud one. The latter you can find under Endpoint of your Vespa application, e.g. https://alexey-heezer.langchain4j.mytenant346.aws-us-east-1c.dev.z.vespa-app.cloud/

keyPath - local path to the SSL private key file in PEM format. Read docs for details. Null if there is no SSL private key file e.g. for local Vespa server.

certPath - local path to the SSL certificate file in PEM format. Read docs for details. Null if there is no SSL certificate file e.g. for local Vespa server.

timeout - for Vespa Java client in java.time.Duration format.

namespace - required for document ID generation, find more details here.

documentType - document type, used for document ID generation, find more details here and data querying

clusterName - cluster name, used for deleting all documents, find more details here

rankProfile - rank profile from your .sd schema. Provided example schema configures cosine similarity match

targetHits - sets the number of hits (10 is default) exposed to the real Vespa's first-phase ranking function per content node, find more details here.

avoidDups - if true (default), then VespaEmbeddingStore will generate a hashed ID based on provided text segment, which avoids duplicated entries in DB. If false, then random ID will be generated.

logRequests - If true, requests to the Vespa service are logged.

logResponses - If true, responses from the Vespa service are logged.

Method Details

builder

public static VespaEmbeddingStore.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)

Adds a new embedding with provided ID to the store.

Specified by:

add in interface EmbeddingStore<TextSegment>

Parameters:

id - "user-specified" part of document ID, find more details here

embedding - the embedding to add

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.

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.

search

public EmbeddingSearchResult<TextSegment> search(EmbeddingSearchRequest request)

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. The score inside EmbeddingMatch is Vespa relevance according to provided rank profile.

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.

removeAll

public void removeAll()

Description copied from interface: EmbeddingStore

Removes all embeddings from the store.

Specified by:

removeAll in interface EmbeddingStore<TextSegment>