使用 Azure OpenAI、Qdrant 为 MySQL 生成 SQL

本 notebook 详细介绍了如何使用 vanna Python 包通过 AI（RAG + LLM）生成 SQL，包括连接到数据库和进行训练。如果您还不准备在自己的数据库上进行训练，仍然可以使用示例 SQLite 数据库进行尝试。

您想使用哪个 LLM？

OpenAI
使用您自己的 API 密钥使用 OpenAI
[Selected] Azure OpenAI
如果您在 Azure 上部署了 OpenAI 模型
Anthropic
使用您的 Anthropic API 密钥使用 Anthropics Claude
Ollama
免费在本地使用 Ollama。需要额外设置。
Google Gemini
使用您的 Gemini 或 Vertex API 密钥使用 Google Gemini
通过 Mistral API 使用 Mistral
如果您有 Mistral API 密钥
其他 LLM
如果您有不同的 LLM 模型

您想在哪里存储“训练”数据？

ChromaDB
免费在本地使用 ChromaDB 的开源向量数据库。无需额外设置——所有数据库文件都将在本地创建和存储。
[Selected] 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 VectorDB
使用任何其他向量数据库。需要额外设置。

设置

%pip install 'vanna[qdrant,openai,mysql]'

from vanna.openai import OpenAI_Chat
from openai import AzureOpenAI
from vanna.qdrant import Qdrant_VectorStore
from qdrant_client import QdrantClient

class MyVanna(Qdrant_VectorStore, OpenAI_Chat):
    def __init__(self, config=None):
        Qdrant_VectorStore.__init__(self, config=config)
        OpenAI_Chat.__init__(self, client=AzureOpenAI(...), config=config) # Make sure to put your AzureOpenAI client here

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

您想查询哪个数据库？

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

训练

您只需要训练一次。除非您想添加更多训练数据，否则请勿再次训练。

# 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)
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()
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()