| Name | Type | Description |
|---|---|---|
texts* | List[str] | Texts to add to the vectorstore. |
embedding* | Embeddings | Embedding function to use. |
metadatas | Optional[List[dict]] | Default: None |
session | Optional[Session] | Default: None |
keyspace | Optional[str] | Default: None |
table_name | str | Default: '' |
ids | Optional[List[str]] | Default: None |
ttl_seconds | Optional[int] | Default: None |
body_index_options | Optional[List[Tuple[str, Any]]] | Default: None |
metadata_deny_list | Optional[list[str]] | Default: None |
Create a CassandraGraphVectorStore from raw texts.
Optional list of metadatas associated with the texts.
Cassandra driver session. If not provided, it is resolved from cassio.
Cassandra key space. If not provided, it is resolved from cassio.
Cassandra table (required).
Optional list of IDs associated with the texts.
Optional time-to-live for the added texts.
Optional options used to create the body index. Eg. body_index_options = [cassio.table.cql.STANDARD_ANALYZER]
Optional list of metadata keys to not index.
i.e. to fine-tune which of the metadata fields are indexed.
Note: if you plan to have massive unique text metadata entries,
consider not indexing them for performance
(and to overcome max-length limitations).
Note: the metadata_indexing parameter from
langchain_community.utilities.cassandra.Cassandra is not
exposed since CassandraGraphVectorStore only supports the
deny_list option.
