Optional
createfalse
Number of dimensions in the embedding vectors.
Optional
distanceDistance metric for vector similarity.
'cosine'
Embedding function to generate embeddings from text. Can be a LangChain Embeddings instance or a function.
Optional
fieldsFields to extract text from for embedding generation. Uses JSON path syntax. Defaults to ["$"] (entire document).
Optional
hnswHNSW-specific configuration parameters. Only used when indexType is 'hnsw'.
Optional
indexVector index type to use.
'hnsw'
Optional
ivfflatIVFFlat-specific configuration parameters. Only used when indexType is 'ivfflat'.
Whether to create indexes for all distance metrics. If false, only creates index for the specified distanceMetric.