KDBAI(
self,
table: Any,
embedding: Embeddings,
distance_strategy: Optional[DistanceStrategy| Name | Type | Description |
|---|---|---|
table* | Any | |
embedding* | Embeddings | |
distance_strategy | Optional[DistanceStrategy] | Default: DistanceStrategy.EUCLIDEAN_DISTANCE |
| Name | Type |
|---|---|
| table | Any |
| embedding | Embeddings |
| distance_strategy | Optional[DistanceStrategy] |
KDB.AI vector store.
See https://kdb.ai.
To use, you should have the kdbai_client python package installed.
See the example notebook.
kdbai_client.Table object to use as storage,
Any embedding function implementing
langchain.embeddings.base.Embeddings interface,
One option from DistanceStrategy.EUCLIDEAN_DISTANCE, DistanceStrategy.DOT_PRODUCT or DistanceStrategy.COSINE.
Run more texts through the embeddings and add to the vectorstore.
Run more documents through the embeddings and add to the vectorstore.
Run similarity search with distance from a query string.
Return documents most similar to embedding, along with scores.
Run similarity search from a query string.
Not implemented.