Ask a question to get started
Enter to send•Shift+Enter new line
AwaDB( self, table_name: str = _DEFAULT_TABLE_NAME, embedding: Optional[Embeddings] =
VectorStore
table_name
str
_DEFAULT_TABLE_NAME
Name of the table created, default _DEFAULT_TABLE_NAME.
embedding
Optional[Embeddings]
None
Optional Embeddings initially set.
log_and_data_dir
Optional[str]
client
Optional[awadb.Client]
kwargs
Any
{}
Run more texts through the embeddings and add to the vectorstore. Args: texts: Iterable of strings to add to the vectorstore. metadatas: Optional list of metadatas associated with the texts. is_duplicate_texts: Optional whether to duplicate texts. Defaults to True. kwargs: any possible extend parameters in the future.
Load the local specified table.
Return docs most similar to query.
The most k similar documents and scores of the specified query.
Return docs most similar to embedding vector.
Return docs selected using the maximal marginal relevance.
Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents.
Return docs according ids.
Delete the documents which have the specified ids.
Update the documents which have the specified ids.
Create a new table.
Use the specified table. Don't know the tables, please invoke list_tables.
List all the tables created by the client.
Get the current table.
Create an AwaDB vectorstore from a raw documents.
Create an AwaDB vectorstore from a list of documents.
If a log_and_data_dir specified, the table will be persisted there.
AwaDB vector store.
AwaDB
Optional the root directory of log and data.
Optional AwaDB client.
Any possible extend parameters in the future.
