使用其他大语言模型、Vanna 托管向量数据库（推荐）为 DuckDB 生成 SQL

本 Notebook 将引导你使用 vanna Python 包通过 AI（RAG + 大语言模型）生成 SQL 的过程，包括连接数据库和训练。如果你尚未准备好使用自己的数据库进行训练，仍然可以使用示例 SQLite 数据库进行尝试。

你想使用哪个大语言模型？

你想在哪里存储“训练”数据？

[Selected] Vanna 托管向量数据库（推荐）
免费使用 Vanna.AI 的托管向量数据库（pgvector）。无需额外设置，可在不同机器上使用。
ChromaDB
在本地免费使用 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
在本地免费使用 Marqo。需要额外设置。或者使用他们的托管选项。
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[duckdb]'

from vanna.vannadb import VannaDB_VectorStore
from vanna.base import VannaBase

class MyCustomLLM(VannaBase):
  def __init__(self, config=None):
    # Implement here
    pass

  def submit_prompt(self, prompt, **kwargs) -> str:
    # Implement here
    # See an example implementation here: https://github.com/vanna-ai/vanna/blob/main/src/vanna/mistral/mistral.py


class MyVanna(VannaDB_VectorStore, MyCustomLLM):
    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)
        MyCustomLLM.__init__(self, config=config)

vn = MyVanna()

你想查询哪个数据库？

vn.connect_to_duckdb(url='motherduck:')

训练

你只需要训练一次。除非你想添加更多训练数据，否则无需再次训练。

# 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()