vanna-ai / vanna Goto Github PK

The chart generated by vn.ask() cannot be replotted if it is not to the user's liking. But they should be able to. Otherwise, users might have to reshape the resultant df, and do the plotting themselves. The value presented by Vanna might be diminished somewhat in this instance

Can we create mermaid charts that do flow diagrams for how a SQL statement gets executed and the different entities involved?

vn.get_training_data() should return

id
type (question-sql, ddl, documentation)
data

Is there a way to get a confidence score in terms of how likely the SQL is to be correct? Or whether there are enough similar queries / etc to give Vanna enough context to generate the SQL?

Maybe this could be calculated via embedding distances?

Model is a lot easier for people to understand.

• create_model
• train
• get_training_data
• delete_model
• update_model_visibility
• etc

Can we print out some key stats for a dataset - like name, description, training questions, asked questions, successful questions, visibility, users, admins, firstquestiondate, lastquestiondate, etc

Not an issue, but a reminder that sample notebooks for vn.ask() need to show that four objects are returned with vn.ask

we should include who has permission to do this action (eg admin or anyone), for the dataset functions / write functions especially.

https://github.com/vanna-ai/vanna-py/blob/feb8443194e433654888d9a6995eeb55a1aaabc1/src/vanna/__init__.py#L790C28-L790C28

Add a parameter to vn.generate_plotly_code so that the user can specify that they want a line chart vs a bar chart etc

We need documentation for contributors on how to develop/test/etc

Please use flake8 for lint purposes.

Could we have a delete_dataset function?

Right now vn.ask() prints the table in markdown format when you run it in a notebook. We should get it to display using the native display widget.

Should we make a vn.use_df function that loads data into sqlite and connects to it so that you can run Vanna on dataframes that you might have brought in via CSV or some other method?

Running vn.train() returns True regardless of whether the SQL that is trained is correct or not. It also does not show whether the question that is being trained already exists. If it does, then what does vn.train() do? This raises the following issues:

1. Returning True is not informative. It gives the impression that the SQL trained is correct but it might not be. I was able to train on erroneous SQL queries and it returned True as well.
2. In what scenarios will False be returned?
3. Are existing questions and their SQL code overwritten when vn.train() is run with an existing question?

Can Vanna automatically get the last X historical SQL queries from dw that support this functionality, like Snowflake and BQ, if provided the connection?

Right now vn.generate_questions only references DDL

In order to get the postgres connector to work on a mac, I had to do:
pip install psycopg2-binary

I think we should consider pg8000 to avoid compatibility issues:

https://wiki.postgresql.org/wiki/Python

Instead of having the user separately define a vn.run_sql() function, could it be integrated within vn.ask() or perhaps a vn.select_db()

Can we implement a bootstrapping one line "agent"? For example -

conn = snowflake connection
vn.set_dataset('dataset')
vn.bootstrap()

where bootstrap does the following -

1. gets DDL and stores
2. gets historical queries and stores along w generated questions
3. generates 10 qs
4. generates sql for those 10 questions
5. runs sql, prints results, charts etc.

On the Code Reference site, it should be vn.get_models() and vn.get_model() as shown in the screengrab

Can't add user to a dataset, returns an error you can only add a user to your own organisation. This is for an organisation that i just created and must have the ownership rights of it.

vn.train should take in

question: str or None
sql: str or None
ddl: str or None
documentation: str or None
json_file: str or None
sql_file: str or None

• If just question, throw an error and print out example usage
• If just sql, do vn.generate_question to generate the question and then vn.add_sql
• If just DDL, do vn.add_ddl
• If just documentation, do vn.store_documentation
• If just a json_file, read the json file using pd.read_json and then iterate through rows to get question and sql columns to do vn.add_sql
• If just a sql_file, use sqlparse to separate the sql statements. Anything that's a create table should go into vn.add_DDL and other statements should do vn.generate_question and then vn.add_sql

All parameters defaults should be None and if the user passes in any combination of invalid parameters it should raise an exception

Instead of returning True/False, output nothing when the status.success is true otherwise throw an exception with the status.message

The ability to send in

1. a JSON of question / SQL pairs, or
2. a SQL file full of semicolon delimited SQL queries

and have Vanna automatically train against a dataset. For 2, would need to auto generate the questions as well

Can we omit the print outs that come after the chart in vn.ask()? Unnecessary, repetitive, and result in a lot of scrolling

This function will take in a question and use training data as a reference to answer questions about the data instead of returning SQL

In order to avoid confusion and also to make the dataset name url safe, on input of the dataset name we should:

• make it lowercase
• replace spaces with a hyphen -
• replace special characters with hyphen or remove it altogether

There should be a deterministic mapping of the input dataset string to the actual dataset name so that users can do vn.set_dataset('my WEirD dataset name!') and it will still work

Can we have Vanna generate documentation for tables and columns automatically? For example ..

vn.generate_docs(entity='table', name='<tablename>') would generate a docstring for a particular table, and
vn.generate_docs(entity='column', name='<columnname>') would generate a docstring for a particular column

and perhaps there could be a flag on the table call to also generate docs for cols within that table automatically?

Add GH action that:

1. Runs on every push to the PR
2. Runs a notebook: https://github.com/marketplace/actions/run-notebook
3. Convert the notebook into docs using nbconvert

ENV variables required, should be fed from GH secrets to the action's context (find their values in Slack).

VANNA_API_KEY=xxx
VANNA_MODEL=xxx
SNOWFLAKE_ACCOUNT=xxx
SNOWFLAKE_USERNAME=xxx
SNOWFLAKE_PASSWORD=xxx
SNOWFLAKE_DATABASE=xxx

We'll likely have to begin using setuptools for this

instead of manually putting the DDL using store_dll(), can Vanna automatically get the DDL directly from the database if provided the connection string, and put each table in separately? at least for snowflake, bq and pg?

If one query has an error, the subsequent queries to postgres will fail. We either need to open a new connection for each query or we need to do a rollback on error.

Encountered the following error when saving the outputs of vn.ask() to four objects (query, df, plot, qns):

This error does not appear if the parameter print_results = False is passed.

When we do vn.generate_sql, we pull from the cache if the SQL already exists. However, if the SQL is flagged or otherwise not in the training set, we should bypass the cache

Our tests are on the server repo -- they need to be migrated to this repo