SemaDB(
self,
collection_name: str,
vector_size: int,
embedding: Embeddings,
distance_strategy:| Name | Type |
|---|---|
| collection_name | str |
| vector_size | int |
| embedding | Embeddings |
| distance_strategy | DistanceStrategy |
| api_key | str |
SemaDB vector store.
This vector store is a wrapper around the SemaDB database.
Example:
.. code-block:: python
from langchain_community.vectorstores import SemaDB
db = SemaDB('mycollection', 768, embeddings, DistanceStrategy.COSINE)
Return the common headers.
Return the embeddings.
Creates the corresponding collection in SemaDB.
Deletes the corresponding collection in SemaDB.
Add texts to the vector store.
Delete by vector ID or other criteria.
Return docs most similar to query.
Run similarity search with distance.
Return docs most similar to embedding vector.
Return VectorStore initialized from texts and embeddings.