Vanna 离线环境部署

!pip install vanna
import vanna
from vanna.remote import VannaDefault
vn = 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 albums by sales?")

$ pip install 'vanna[chromadb,openai,mysql]'

$ wget https://chroma-onnx-models.s3.amazonaws.com/all-MiniLM-L6-v2/onnx.tar.gz

from openai import OpenAI


client = OpenAI(api_key='sk-xxx', base_url='http://127.0.0.1:19131/v1/')

class MyVanna(ChromaDB_VectorStore, OpenAI_Chat):
    def __init__(self, config=None):
        ChromaDB_VectorStore.__init__(self, config=config)
        OpenAI_Chat.__init__(self, client=client, config=config)

vn = MyVanna(config={'model': 'qwen1.5-72b-chat'})

vn.connect_to_mysql(host='my-host', dbname='my-db', user='my-user', password='my-password', port=123)

# 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 LLM
plan = vn.get_training_plan_generic(df_information_schema)
print(plan)

# If you like the plan, then uncomment this and run it to train
vn.train(plan=plan)

# The following are methods for adding training data. Make sure you modify the examples to match your database.

# DDL statements are powerful because they specify table names, colume names, types, and potentially relationships
vn.train(ddl='''
    CREATE TABLE IF NOT EXISTS my-table (
        id INT PRIMARY KEY,
        name VARCHAR(100),
        age INT
    )
''')

# Sometimes you may want to 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. You can just copy and paste those from your editor to begin generating new SQL.
vn.train(sql="SELECT * FROM my-table WHERE name = 'John Doe'")

# At any time you can inspect what training data the package is able to reference
training_data = vn.get_training_data()
print(training_data)

# You can remove training data if there's obsolete/incorrect information. 
vn.remove_training_data(id='1-ddl')

vn.ask(question='有哪些表')

from vanna.flask import VannaFlaskApp
VannaFlaskApp(vn, allow_llm_to_see_data=True).run(port=8085, host='0.0.0.0')