Class WeaviateEmbeddingStore
java.lang.Object
dev.langchain4j.store.embedding.weaviate.WeaviateEmbeddingStore
- All Implemented Interfaces:
EmbeddingStore<TextSegment>
Represents the Weaviate vector database.
Current implementation assumes the cosine distance metric is used.
-
Constructor Summary
ConstructorDescriptionWeaviateEmbeddingStore
(String apiKey, String scheme, String host, Integer port, Boolean useGrpcForInserts, Boolean securedGrpc, Integer grpcPort, String objectClass, Boolean avoidDups, String consistencyLevel, Collection<String> metadataKeys, String textFieldName, String metadataFieldName) Creates a new WeaviateEmbeddingStore instance. -
Method Summary
Modifier and TypeMethodDescriptionAdds a given embedding to the store.add
(Embedding embedding, TextSegment textSegment) Adds a given embedding and the corresponding content that has been embedded to the store.void
Adds a new embedding with provided ID to the store.Adds multiple embeddings to the store.addAll
(List<Embedding> embeddings, List<TextSegment> embedded) Adds multiple embeddings and their corresponding contents that have been embedded to the store.void
Removes all embeddings from the store.void
removeAll
(Collection<String> ids) Removes all embeddings that match the specified IDs from the store.search
(EmbeddingSearchRequest request) Searches for the most similar (closest in the embedding space)Embedding
s.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
findRelevant, findRelevant, findRelevant, findRelevant, remove, removeAll
-
Constructor Details
-
WeaviateEmbeddingStore
public WeaviateEmbeddingStore(String apiKey, String scheme, String host, Integer port, Boolean useGrpcForInserts, Boolean securedGrpc, Integer grpcPort, String objectClass, Boolean avoidDups, String consistencyLevel, Collection<String> metadataKeys, String textFieldName, String metadataFieldName) Creates a new WeaviateEmbeddingStore instance.- Parameters:
apiKey
- Your Weaviate API key. Not required for local deployment.scheme
- The scheme, e.g. "https" of cluster URL. Find in under Details of your Weaviate cluster.host
- The host, e.g. "langchain4j-4jw7ufd9.weaviate.network" of cluster URL. Find in under Details of your Weaviate cluster.port
- The port, e.g. 8080. This parameter is optional.useGrpcForInserts
- Use GRPC instead of HTTP for batch inserts only. You still need HTTP configured for searchsecuredGrpc
- The GRPC connection is securedgrpcPort
- The port, e.g. 50051. This parameter is optional.objectClass
- The object class you want to store, e.g. "MyGreatClass". Must start from an uppercase letter.avoidDups
- If true (default), thenWeaviateEmbeddingStore
will generate a hashed ID based on provided text segment, which avoids duplicated entries in DB. If false, then random ID will be generated.consistencyLevel
- Consistency level: ONE, QUORUM (default) or ALL. Find more details here.metadataKeys
- Metadata keys that should be persisted (optional)textFieldName
- The name of the field that contains the text of aTextSegment
. Default is "text".metadataFieldName
- metadataFieldName The name of the field whereMetadata
entries are stored. Default is "_metadata". If set to empty string,Metadata
entries will be stored in the root of the Weaviate object.
-
-
Method Details
-
add
Description copied from interface:EmbeddingStore
Adds a given embedding to the store.- Specified by:
add
in interfaceEmbeddingStore<TextSegment>
- Parameters:
embedding
- The embedding to be added to the store.- Returns:
- The auto-generated ID associated with the added embedding.
-
add
Adds a new embedding with provided ID to the store.- Specified by:
add
in interfaceEmbeddingStore<TextSegment>
- Parameters:
id
- the ID of the embedding to add in UUID format, since it's Weaviate requirement. See Weaviate docs and UUID on Wikipediaembedding
- the embedding to add
-
add
Description copied from interface:EmbeddingStore
Adds a given embedding and the corresponding content that has been embedded to the store.- Specified by:
add
in interfaceEmbeddingStore<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
Description copied from interface:EmbeddingStore
Adds multiple embeddings to the store.- Specified by:
addAll
in interfaceEmbeddingStore<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
Description copied from interface:EmbeddingStore
Adds multiple embeddings and their corresponding contents that have been embedded to the store.- Specified by:
addAll
in interfaceEmbeddingStore<TextSegment>
- Parameters:
embeddings
- A list of embeddings to be added to the store.embedded
- A list of original contents that were embedded.- Returns:
- A list of auto-generated IDs associated with the added embeddings.
-
removeAll
Description copied from interface:EmbeddingStore
Removes all embeddings that match the specified IDs from the store.- Specified by:
removeAll
in interfaceEmbeddingStore<TextSegment>
- Parameters:
ids
- A collection of unique IDs of the embeddings to be removed.
-
removeAll
public void removeAll()Description copied from interface:EmbeddingStore
Removes all embeddings from the store.- Specified by:
removeAll
in interfaceEmbeddingStore<TextSegment>
-
search
Searches for the most similar (closest in the embedding space)Embedding
s.
All search criteria are defined inside theEmbeddingSearchRequest
.
EmbeddingSearchRequest.filter()
can be used to filter by various metadata entries (e.g., user/memory ID). Please note that not allEmbeddingStore
implementations supportFilter
ing. The score insideEmbeddingMatch
is Weaviate's certainty.- Specified by:
search
in interfaceEmbeddingStore<TextSegment>
- Parameters:
request
- A request to search in anEmbeddingStore
. Contains all search criteria.- Returns:
- An
EmbeddingSearchResult
containing all foundEmbedding
s.
-