vanna.base.base

class VannaBase(abc.ABC):

Helper class that provides a standard way to create an ABC using inheritance.

config

run_sql_is_set

def generate_sql(self, question: str, **kwargs) -> str:

def generate_followup_questions(self, question: str, **kwargs) -> str:

def generate_questions(self, **kwargs) -> list[str]:

Example:

vn.generate_questions()

Generate a list of questions that you can ask Vanna.AI.

@abstractmethod

def generate_embedding(self, data: str, **kwargs) -> list[float]:

@abstractmethod

def get_similar_question_sql(self, question: str, **kwargs) -> list:

@abstractmethod

def get_related_ddl(self, question: str, **kwargs) -> list:

@abstractmethod

def get_related_documentation(self, question: str, **kwargs) -> list:

@abstractmethod

def add_question_sql(self, question: str, sql: str, **kwargs) -> str:

@abstractmethod

def add_ddl(self, ddl: str, **kwargs) -> str:

@abstractmethod

def add_documentation(self, doc: str, **kwargs) -> str:

@abstractmethod

def get_training_data(self, **kwargs) -> pandas.core.frame.DataFrame:

@abstractmethod

def remove_training_data(id: str, **kwargs) -> bool:

@abstractmethod

def get_sql_prompt( self, question: str, question_sql_list: list, ddl_list: list, doc_list: list, **kwargs):

@abstractmethod

def get_followup_questions_prompt( self, question: str, question_sql_list: list, ddl_list: list, doc_list: list, **kwargs):

@abstractmethod

def submit_prompt(self, prompt, **kwargs) -> str:

@abstractmethod

def generate_question(self, sql: str, **kwargs) -> str:

@abstractmethod

def generate_plotly_code( self, question: str = None, sql: str = None, df_metadata: str = None, **kwargs) -> str:

def connect_to_snowflake( self, account: str, username: str, password: str, database: str, role: Optional[str] = None, warehouse: Optional[str] = None):

def connect_to_sqlite(self, url: str):

Connect to a SQLite database. This is just a helper function to set [vn.run_sql][vanna.run_sql]

Arguments:

url (str): The URL of the database to connect to.

Returns:

None

def connect_to_postgres( self, host: str = None, dbname: str = None, user: str = None, password: str = None, port: int = None):

Connect to postgres using the psycopg2 connector. This is just a helper function to set [vn.run_sql][vanna.run_sql] Example:

vn.connect_to_postgres(
    host="myhost",
    dbname="mydatabase",
    user="myuser",
    password="mypassword",
    port=5432
)

Arguments:

host (str): The postgres host.
dbname (str): The postgres database name.
user (str): The postgres user.
password (str): The postgres password.
port (int): The postgres Port.

def connect_to_bigquery(self, cred_file_path: str = None, project_id: str = None):

Connect to gcs using the bigquery connector. This is just a helper function to set [vn.run_sql][vanna.run_sql] Example:

vn.connect_to_bigquery(
    project_id="myprojectid",
    cred_file_path="path/to/credentials.json",
)

Arguments:

project_id (str): The gcs project id.
cred_file_path (str): The gcs credential file path

def run_sql(sql: str, **kwargs) -> pandas.core.frame.DataFrame:

def ask( self, question: Optional[str] = None, print_results: bool = True, auto_train: bool = True) -> Optional[Tuple[Optional[str], Optional[pandas.core.frame.DataFrame], Optional[plotly.graph_objs._figure.Figure]]]:

def train( self, question: str = None, sql: str = None, ddl: str = None, documentation: str = None, plan: vanna.types.TrainingPlan = None) -> str:

Example:

vn.train()

Train Vanna.AI on a question and its corresponding SQL query. If you call it with no arguments, it will check if you connected to a database and it will attempt to train on the metadata of that database. If you call it with the sql argument, it's equivalent to [add_sql()][vanna.add_sql]. If you call it with the ddl argument, it's equivalent to [add_ddl()][vanna.add_ddl]. If you call it with the documentation argument, it's equivalent to [add_documentation()][vanna.add_documentation]. Additionally, you can pass a [TrainingPlan][vanna.TrainingPlan] object. Get a training plan with [vn.get_training_plan_experimental()][vanna.get_training_plan_experimental].

Arguments:

question (str): The question to train on.
sql (str): The SQL query to train on.
ddl (str): The DDL statement.
documentation (str): The documentation to train on.
plan (TrainingPlan): The training plan to train on.

def get_training_plan_generic(self, df) -> vanna.types.TrainingPlan:

def get_training_plan_snowflake( self, filter_databases: Optional[List[str]] = None, filter_schemas: Optional[List[str]] = None, include_information_schema: bool = False, use_historical_queries: bool = True) -> vanna.types.TrainingPlan:

def get_plotly_figure( self, plotly_code: str, df: pandas.core.frame.DataFrame, dark_mode: bool = True) -> plotly.graph_objs._figure.Figure:

Example:

fig = vn.get_plotly_figure(
    plotly_code="fig = px.bar(df, x='name', y='salary')",
    df=df
)
fig.show()

Get a Plotly figure from a dataframe and Plotly code.

Arguments:

df (pd.DataFrame): The dataframe to use.
plotly_code (str): The Plotly code to use.

Returns:

plotly.graph_objs.Figure: The Plotly figure.

class SplitStorage(VannaBase):

Helper class that provides a standard way to create an ABC using inheritance.

def get_similar_question_sql(self, embedding: str, **kwargs) -> list:

def get_related_ddl(self, embedding: str, **kwargs) -> list:

def get_related_documentation(self, embedding: str, **kwargs) -> list:

@abstractmethod

def store_question_sql_embedding(self, embedding: str, **kwargs) -> str:

@abstractmethod

def store_ddl_embedding(self, embedding: str, **kwargs) -> str:

@abstractmethod

def store_documentation_embedding(self, embedding: str, **kwargs) -> str:

@abstractmethod

def get_similar_question_sql_ids(self, embedding: str, **kwargs) -> list:

@abstractmethod

def get_related_ddl_ids(self, embedding: str, **kwargs) -> list:

@abstractmethod

def get_related_documentation_ids(self, embedding: str, **kwargs) -> list:

@abstractmethod

def get_question_sql(self, question_sql_ids: list, **kwargs) -> list:

@abstractmethod

def get_documentation(self, doc_ids: list, **kwargs) -> list:

@abstractmethod

def get_ddl(self, ddl_ids: list, **kwargs) -> list:

Inherited Members

VannaBase: config; run_sql_is_set; generate_sql; generate_followup_questions; generate_questions; generate_embedding; add_question_sql; add_ddl; add_documentation; get_training_data; remove_training_data; get_sql_prompt; get_followup_questions_prompt; submit_prompt; generate_question; generate_plotly_code; connect_to_snowflake; connect_to_sqlite; connect_to_postgres; connect_to_bigquery; run_sql; ask; train; get_training_plan_generic; get_training_plan_snowflake; get_plotly_figure