Method●Since v0.3

from_texts

Creates an instance of DuckDB and populates it with texts and their embeddings.

from_texts(
  cls: Type[VST],
  texts: List[str],
  embedding: Embeddings,
  metadatas: Optional[List[dict]] = None,
  **kwargs: Any = {}
) -> DuckDB

Parameters

Name	Type	Description
`texts`*	`List[str]`	List of strings to add to the vector store.
`embedding`*	`Embeddings`	The embedding function or model to use for generating embeddings.
`metadatas`	`Optional[List[dict]]`	Default:`None` Optional list of metadata dictionaries associated with the texts.
`kwargs`	`Any`	Default:`{}` Additional keyword arguments including: connection: DuckDB connection. If not provided, a new connection will be created. vector_key: The column name for storing vectors. Default "vector". id_key: The column name for storing unique identifiers. Default "id". text_key: The column name for storing text. Defaults to "text". table_name: The name of the table to use for storing embeddings. Defaults to "embeddings".