Const
Optional
bm25b?: numberThe BM25 b parameter.
Optional
bm25k1?: numberThe BM25 k1 parameter.
Optional
cleanupThe interval in seconds at which the inverted index is cleaned up.
Optional
stopwordsAdditional stopwords to add.
Optional
stopwordsThe stopwords preset to use.
Optional
stopwordsStopwords to remove.
Create a ReplicationConfigUpdate
object to be used when defining the replication configuration of Weaviate.
See the docs for more details.
Optional
asyncWhether asynchronous replication is enabled.
Optional
factor?: numberThe replication factor.
Create a ModuleConfig<'flat', VectorIndexConfigFlatUpdate>
object to update the configuration of the FLAT vector index.
Use this method when defining the options.vectorIndexConfig
argument of the reconfigure.vectorizer
method.
The configuration object.
Optional
quantizer?: BQConfigUpdateThe quantizer configuration to use. Default is bq
.
Optional
vectorThe maximum number of objects to cache in the vector cache. Default is 1000000000000.
Create a ModuleConfig<'hnsw', VectorIndexConfigHNSWCreate>
object to update the configuration of the HNSW vector index.
Use this method when defining the options.vectorIndexConfig
argument of the reconfigure.vectorizer
method.
The configuration object.
Optional
dynamicThe dynamic ef factor. Default is 8.
Optional
dynamicThe dynamic ef max. Default is 500.
Optional
dynamicThe dynamic ef min. Default is 100.
Optional
ef?: numberThe ef parameter. Default is -1.
Optional
flatThe flat search cutoff. Default is 40000.
Optional
quantizer?: PQConfigUpdate | BQConfigUpdate | SQConfigUpdateThe quantizer configuration to use. Use vectorIndex.quantizer.bq
or vectorIndex.quantizer.pq
to make one.
Optional
vectorThe maximum number of objects to cache in the vector cache. Default is 1000000000000.
Define the quantizer configuration to use when creating a vector index.
Create an object of type BQConfigUpdate
to be used when updating the quantizer configuration of a vector index.
NOTE: If the vector index already has a quantizer configured, you cannot change its quantizer type; only its values. So if you want to change the quantizer type, you must recreate the collection.
The configuration object.
Optional
options: { Optional
cache?: booleanWhether to cache the quantizer.
Optional
rescoreThe new rescore limit.
Create an object of type PQConfigUpdate
to be used when updating the quantizer configuration of a vector index.
NOTE: If the vector index already has a quantizer configured, you cannot change its quantizer type; only its values. So if you want to change the quantizer type, you must recreate the collection.
The configuration object.
Optional
options: { Optional
centroids?: numberThe new number of centroids.
Optional
pqThe new encoder distribution.
Optional
pqThe new encoder type.
Optional
segments?: numberThe new number of segments.
Optional
trainingThe new training limit.
Create an object of type SQConfigUpdate
to be used when updating the quantizer configuration of a vector index.
NOTE: If the vector index already has a quantizer configured, you cannot change its quantizer type; only its values. So if you want to change the quantizer type, you must recreate the collection.
The configuration object.
Optional
options: { Optional
rescoreThe rescore limit.
Optional
trainingThe training limit.
Create a VectorConfigUpdate
object to be used when updating the named vector configuration of Weaviate.
The options for the named vector.
Create an
InvertedIndexConfigUpdate
object to be used when updating the configuration of the keyword searching algorithm of your collection.See the docs for details!