使用 Mistral 通过 Mistral API、ChromaDB 为 BigQuery 生成 SQL
本笔记本将介绍如何使用 vanna
Python 包通过 AI(RAG + LLMs)生成 SQL,包括连接数据库和进行训练。如果您还没准备好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。
您想使用哪个大型语言模型 (LLM)?
-
OpenAI使用您自己的 API 密钥连接 OpenAI
-
Azure OpenAI如果您在 Azure 上部署了 OpenAI 模型
-
Anthropic使用您的 Anthropic API 密钥连接 Anthropic 的 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 密钥连接 Google Gemini
-
[Selected] 通过 Mistral API 使用 Mistral如果您有 Mistral API 密钥
-
其他大型语言模型 (LLM)如果您有不同的 LLM 模型
您想将“训练”数据存储在哪里?
-
[Selected] 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。
-
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。或使用他们的托管选项。
-
其他向量数据库 (VectorDB)使用任何其他向量数据库。需要额外设置。
设置
%pip install 'vanna[chromadb,mistralai,bigquery]'
from vanna.chromadb import ChromaDB_VectorStore
from vanna.mistral import Mistral
class MyVanna(ChromaDB_VectorStore, Mistral):
def __init__(self, config=None):
ChromaDB_VectorStore.__init__(self, config=config)
Mistral.__init__(self, config={'api_key': MISTRAL_API_KEY, 'model': 'mistral-tiny'})
vn = MyVanna()
您想查询哪个数据库?
-
Postgres
-
Microsoft SQL Server
-
MySQL
-
DuckDB
-
Snowflake
-
[Selected] BigQuery
-
SQLite
-
Oracle
-
其他数据库使用 Vanna 为任何 SQL 数据库生成查询
vn.connect_to_bigquery(project_id='my-project')
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
from vanna.flask import VannaFlaskApp
app = VannaFlaskApp(vn)
app.run()