Kinetica(
self,
config: KineticaSettings,
embedding_function: Embeddings,
collection_name: str | Name | Type | Description |
|---|---|---|
config* | KineticaSettings | Kinetica connection settings class. |
embedding_function* | Embeddings | Any embedding function implementing
|
collection_name | str | Default: _LANGCHAIN_DEFAULT_COLLECTION_NAMEThe name of the collection to use. (default: langchain) NOTE: This is not the name of the table, but the name of the collection. The tables will be created when initializing the store (if not exists) So, make sure the user has the right permissions to create tables. |
distance_strategy | DistanceStrategy | Default: DEFAULT_DISTANCE_STRATEGY |
pre_delete_collection | bool | Default: False |
engine_args* | unknown |
| Name | Type |
|---|---|
| config | KineticaSettings |
| embedding_function | Embeddings |
| collection_name | str |
| schema_name | str |
| distance_strategy | DistanceStrategy |
| pre_delete_collection | bool |
| logger | Optional[logging.Logger] |
| relevance_score_fn | Optional[Callable[[float], float]] |
Kinetica vector store.
To use, you should have the gpudb python package installed.
Example:
.. code-block:: python
from langchain_community.vectorstores import Kinetica, KineticaSettings from langchain_community.embeddings.openai import OpenAIEmbeddings
kinetica_settings = KineticaSettings( host="http://127.0.0.1", username="", password="" ) COLLECTION_NAME = "kinetica_store" embeddings = OpenAIEmbeddings() vectorstore = Kinetica.from_documents( documents=docs, embedding=embeddings, collection_name=COLLECTION_NAME, config=kinetica_settings, )
The distance strategy to use. (default: COSINE)
If True, will delete the collection if it exists. (default: False). Useful for testing.
SQLAlchemy's create engine arguments.