abacusai.vector_store
Module Contents
Classes
A vector store that stores embeddings for a list of document trunks. |
- class abacusai.vector_store.VectorStore(client, name=None, vectorStoreId=None, createdAt=None, latestVectorStoreVersion={})
Bases:
abacusai.return_class.AbstractApiClass
A vector store that stores embeddings for a list of document trunks.
- Parameters:
client (ApiClient) – An authenticated API Client instance
name (str) – The name of the vector store.
vectorStoreId (str) – The unique identifier of the vector store.
createdAt (str) – When the vector store was created.
latestVectorStoreVersion (VectorStoreVersion) – The latest version of vector store.
- __repr__()
Return repr(self).
- to_dict()
Get a dict representation of the parameters in this class
- Returns:
The dict value representation of the class parameters
- Return type:
- update(feature_group_id=None, name=None)
Updates an existing vector store.
- Parameters:
- Returns:
The updated vector store.
- Return type:
- create_version()
Creates a vector store version from the latest version of the feature group that the vector store associated with.
- Parameters:
vector_store_id (str) – The unique ID associated with the vector store to create version with.
- Returns:
The newly created vector store version.
- Return type:
- refresh()
Calls describe and refreshes the current object’s fields
- Returns:
The current object
- Return type:
- describe()
Describe a Vector Store.
- Parameters:
vector_store_id (str) – A unique string identifier associated with the vector store.
- Returns:
The vector store object.
- Return type:
- delete()
Delete a Vector Store.
- Parameters:
vector_store_id (str) – A unique string identifier associated with the vector store.
- list_versions()
List all the vector store versions with a given vector store ID.
- Parameters:
vector_store_id (str) – A unique string identifier associated with the vector store.
- Returns:
All the vector store versions associated with the vector store.
- Return type:
- lookup(query, deployment_token, limit_results=None)
Lookup relevant documents from the vector store deployed with given query.
- Parameters:
- Returns:
The relevant documentation results found from the vector store.
- Return type: