!pip install vannaimport vannafrom vanna.remote import VannaDefaultvn = VannaDefault(model='chinook', api_key=vanna.get_api_key('my-email@example.com'))vn.connect_to_sqlite('https://vanna.ai/Chinook.sqlite')vn.ask('What are the top 10 artists by sales?')
from vanna.flask import VannaFlaskAppVannaFlaskApp(vn).run()

sql = vn.generate_sql(question='What are the top 10 customers by Sales?')print(sql)

SELECT customer_name, total_salesFROM (SELECT c.c_name as customer_name, sum(l.l_extendedprice * (1 - l.l_discount)) as total_sales, row_number() OVER (ORDER BY sum(l.l_extendedprice * (1 - l.l_discount)) desc) as row_numFROM snowflake_sample_data.tpch_sf1.lineitem l join snowflake_sample_data.tpch_sf1.orders oON l.l_orderkey = o.o_orderkey join snowflake_sample_data.tpch_sf1.customer cON o.o_custkey = c.c_custkeyGROUP BY customer_name)WHERErow_num <= 10;

# The information schema query may need some tweaking depending on your database. This is a good starting point.df_information_schema = vn.run_sql("SELECT * FROM INFORMATION_SCHEMA.COLUMNS")
# This will break up the information schema into bite-sized chunks that can be referenced by the LLMplan = vn.get_training_plan_generic(df_information_schema)plan
# If you like the plan, then uncomment this and run it to train# vn.train(plan=plan)

from vanna.openai import OpenAI_Chatfrom vanna.qdrant import Qdrant_VectorStorefrom qdrant_client import QdrantClient
class MyVanna(Qdrant, OpenAI_Chat):def __init__(self, config=None):Qdrant_VectorStore.__init__(self, config=config)OpenAI_Chat.__init__(self, config=config)
vn = MyVanna(config={'client': QdrantClient(...),'api_key': sk-...,'model': gpt-4-...,})

vn.connect_to_postgres(host='my-host', dbname='my-dbname', user='my-user', password='my-password', port='my-port')

# You can add DDL statements that specify table names, column names, types, and potentially relationshipsvn.train(ddl="""CREATE TABLE IF NOT EXISTS my-table (id INT PRIMARY KEY,name VARCHAR(100),age INT)""")
# You can add documentation about your business terminology or definitions.vn.train(documentation="Our business defines OTIF score as the percentage of orders that are delivered on time and in full")
# You can also add SQL queries to your training data. This is useful if you have some queries already laying around.vn.train(sql="SELECT * FROM my-table WHERE name = 'John Doe'")
# You can remove training data if there's obsolete/incorrect information. vn.remove_training_data(id='1-ddl')
# Whenever you ask a new question, Vanna will retrieve 10 most relevant pieces of training data and use it as part of the LLM prompt to generate the SQL.
vn.ask(question="<YOUR_QUESTION>")