Jaguar

login to jaguardb server with a jaguar_api_key or let self._jag find a key Args: pod (str): name of a Pod store (str): name of a vector store optional jaguar_api_key (str): API key of user to jaguardb server Returns: True if successful; False if not successful

create the vector store on the backend database Args: metadata_str (str): columns and their types Returns: True if successful; False if not successful

Run any query statement in jaguardb Args: query (str): query statement to jaguardb Returns: None for invalid token, or json result string

Add texts through the embeddings and add to the vectorstore. Args: texts: list of text strings to add to the jaguar vector store. metadatas: Optional list of metadatas associated with the texts. [{"m1": "v11", "m2": "v12", "m3": "v13", "filecol": "path_file1.jpg" }, {"m1": "v21", "m2": "v22", "m3": "v23", "filecol": "path_file2.jpg" }, {"m1": "v31", "m2": "v32", "m3": "v33", "filecol": "path_file3.jpg" }, {"m1": "v41", "m2": "v42", "m3": "v43", "filecol": "path_file4.jpg" }] kwargs: vector_index=name_of_vector_index file_column=name_of_file_column

Return Jaguar documents most similar to query, along with scores. Args: query: Text to look up documents similar to. k: Number of Documents to return. Defaults to 3. lambda_val: lexical match parameter for hybrid search. where: the where clause in select similarity. For example a where can be "rating > 3.0 and (state = 'NV' or state = 'CA')" args: extra options passed to select similarity kwargs: vector_index=vcol, vector_type=cosine_fraction_float Returns: List of Documents most similar to the query and score for each. List of Tuples of (doc, similarity_score): [ (doc, score), (doc, score), ...]

Return Jaguar documents most similar to query, along with scores. Args: query: Text to look up documents similar to. k: Number of Documents to return. Defaults to 5. where: the where clause in select similarity. For example a where can be "rating > 3.0 and (state = 'NV' or state = 'CA')" Returns: List of Documents most similar to the query

Detect if given text is anomalous from the dataset Args: query: Text to detect if it is anomaly Returns: True or False

Delete all records in jaguardb Args: No args Returns: None

Delete records in jaguardb by a list of zero-ids Args: pod (str): name of a Pod ids (List[str]): a list of zid as string Returns: Do not return anything

Count records of a store in jaguardb Args: no args Returns: (int) number of records in pod store

Drop or remove a store in jaguardb Args: no args Returns: None

Logout to cleanup resources Args: no args Returns: None