使用 OpenAI、Vanna 托管向量数据库（推荐）为 SQLite 生成 SQL

本 notebook 将介绍如何使用 vanna Python 包，通过 AI（RAG + LLMs）生成 SQL，包括连接数据库和训练。如果您还没有准备好在自己的数据库上进行训练，您仍然可以使用样本 SQLite 数据库进行尝试。

您想使用哪个大型语言模型（LLM）？

您想在哪里存储 '训练' 数据？

[Selected] Vanna 托管向量数据库（推荐）
免费使用 Vanna.AI 托管的向量数据库 (pgvector)。无需额外设置，可在多台机器上使用。
ChromaDB
免费在本地使用 ChromaDB 的开源向量数据库。无需额外设置 -- 所有数据库文件将在本地创建和存储。
Qdrant
使用 Qdrant 的开源向量数据库
Marqo
免费在本地使用 Marqo。需要额外设置。或使用其托管选项。
其他向量数据库
使用任何其他向量数据库。需要额外设置。

设置

%pip install 'vanna[openai]'

from vanna.openai import OpenAI_Chat
from vanna.vannadb import VannaDB_VectorStore

class MyVanna(VannaDB_VectorStore, OpenAI_Chat):
    def __init__(self, config=None):
        MY_VANNA_MODEL = # Your model name from https://vanna.org.cn/account/profile
        VannaDB_VectorStore.__init__(self, vanna_model=MY_VANNA_MODEL, vanna_api_key=MY_VANNA_API_KEY, config=config)
        OpenAI_Chat.__init__(self, config=config)

vn = MyVanna(config={'api_key': 'sk-...', 'model': 'gpt-4-...'})

您想查询哪个数据库？

vn.connect_to_sqlite('my-database.sqlite')

训练

您只需训练一次。除非想添加更多训练数据，否则无需再次训练。

df_ddl = vn.run_sql("SELECT type, sql FROM sqlite_master WHERE sql is not null")

for ddl in df_ddl['sql'].to_list():
  vn.train(ddl=ddl)

# 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()
training_data

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

```## Asking the AI
Whenever you ask a new question, it will find the 10 most relevant pieces of training data and use it as part of the LLM prompt to generate the SQL.
```python
vn.ask(question=...)

启动用户界面

vanna-flask

from vanna.flask import VannaFlaskApp
app = VannaFlaskApp(vn)
app.run()