Create a Milvus collection, indexes it with HNSW, and insert data.
from_texts(
cls,
texts: List[str],
embedding: Embeddings,
metadatas: Optional[List[dict]] = None,
collection_name: str = 'LangChainCollection',
connection_args: dict[str, Any] = DEFAULT_MILVUS_CONNECTION,
consistency_level: str = 'Session',
index_params: Optional[dict] = None,
search_params: Optional[dict] = None,
drop_old: bool = False,
*,
ids: Optional[List[str]] = None,
**kwargs: Any = {}
) -> Milvus| Name | Type | Description |
|---|---|---|
texts* | List[str] | Text data. |
embedding* | Embeddings | Embedding function. |
metadatas | Optional[List[dict]] | Default: NoneMetadata for each text if it exists. Defaults to None. |
collection_name | str | Default: 'LangChainCollection'Collection name to use. Defaults to "LangChainCollection". |
connection_args | dict[str, Any] | Default: DEFAULT_MILVUS_CONNECTIONConnection args to use. Defaults to DEFAULT_MILVUS_CONNECTION. |
consistency_level | str | Default: 'Session'Which consistency level to use. Defaults to "Session". |
index_params | Optional[dict] | Default: NoneWhich index_params to use. Defaults to None. |
search_params | Optional[dict] | Default: NoneWhich search params to use. Defaults to None. |
drop_old | Optional[bool] | Default: FalseWhether to drop the collection with that name if it exists. Defaults to False. |
ids | Optional[List[str]] | Default: NoneList of text ids. Defaults to None. |