Optional
filterMethod to add documents to the vector store. It ensures the existence of the table in the database, converts the documents into vectors, and adds them to the store.
Array of Document
instances.
Promise that resolves when the documents have been added.
Method to add vectors to the vector store. It converts the vectors into rows and inserts them into the database.
Array of vectors.
Array of Document
instances.
Promise that resolves when the vectors have been added.
Method to perform a similarity search in the vector store. It returns
the k
most similar documents to the query vector, along with their
similarity scores.
Query vector.
Number of most similar documents to return.
Optional
filter: MetadataOptional filter to apply to the search.
Promise that resolves with an array of tuples, each containing a TypeORMVectorStoreDocument
and its similarity score.
Static
fromStatic method to create a new TypeORMVectorStore
instance from a
DataSource
. It initializes the DataSource
if it is not already
initialized.
Embeddings instance.
TypeORMVectorStoreArgs
instance.
A new instance of TypeORMVectorStore
.
Static
fromStatic method to create a new TypeORMVectorStore
instance from an
array of Document
instances. It adds the documents to the store.
Array of Document
instances.
Embeddings instance.
TypeORMVectorStoreArgs
instance.
Promise that resolves with a new instance of TypeORMVectorStore
.
Static
fromStatic method to create a new TypeORMVectorStore
instance from an
existing index.
Embeddings instance.
TypeORMVectorStoreArgs
instance.
Promise that resolves with a new instance of TypeORMVectorStore
.
Static
fromStatic method to create a new TypeORMVectorStore
instance from an
array of texts and their metadata. It converts the texts into
Document
instances and adds them to the store.
Array of texts.
Array of metadata objects or a single metadata object.
Embeddings instance.
TypeORMVectorStoreArgs
instance.
Promise that resolves with a new instance of TypeORMVectorStore
.
Generated using TypeDoc
Class that provides an interface to a Postgres vector database. It extends the
VectorStore
base class and implements methods for adding documents and vectors, performing similarity searches, and ensuring the existence of a table in the database.