Making a Textual content to SQL App with OpenAI + FastAPI + SQLite
Picture by Creator# Introduction
Knowledge has develop into an indispensable useful resource for any profitable enterprise, because it supplies useful insights for knowledgeable decision-making. Given the significance of information, many corporations are constructing techniques to retailer and analyze it. Nonetheless, there are lots of instances when it’s laborious to amass and analyze the required knowledge, particularly with the growing complexity of the information system.
With the arrival of generative AI, knowledge work has develop into considerably simpler, as we will now use easy pure language to obtain largely correct output that carefully follows the enter we offer. It’s additionally relevant to knowledge processing and evaluation with SQL, the place we will ask for question growth.
On this article, we’ll develop a easy API utility that interprets pure language into SQL queries that our database understands. We’ll use three major instruments: OpenAI, FastAPI, and SQLite.
Right here’s the plan.
# Textual content-to-SQL App Improvement
First, we’ll put together every thing wanted for our mission. All it is advisable present is the OpenAI API key, which we’ll use to entry the generative mannequin. To containerize the applying, we’ll use Docker, which you’ll purchase for the native implementation utilizing Docker Desktop.
Different parts, corresponding to SQLite, will already be accessible if you set up Python, and FastAPI will probably be put in later.
For the general mission construction, we’ll use the next:
text_to_sql_app/
├── app/
│ ├── __init__.py
│ ├── database.py
│ ├── openai_utils.py
│ └── major.py
├── demo.db
├── init_db.sql
├── necessities.txt
├── Dockerfile
├── docker-compose.yml
├── .env
Create the construction like above, or you need to use the next repository to make issues simpler. We’ll nonetheless undergo every file to realize an understanding of develop the applying.
Let’s begin by populating the .env file with the OpenAI API key we beforehand acquired. You are able to do that with the next code:
OPENAI_API_KEY=YOUR-API-KEY
Then, go to the necessities.txt to fill within the crucial libraries we’ll use for
fastapi
uvicorn
sqlalchemy
openai
pydantic
python-dotenv
Subsequent, we transfer on to the __init__.py file, and we’ll put the next code inside:
from pathlib import Path
from dotenv import load_dotenv
load_dotenv(dotenv_path=Path(__file__).resolve().mum or dad.mum or dad / ".env", override=False)
The code above ensures that the setting accommodates all the required keys we want.
Then, we’ll develop Python code within the database.py file to hook up with the SQLite database we’ll create later (known asdemo.db) and supply a approach to run SQL queries.
from sqlalchemy import create_engine, textual content
from sqlalchemy.orm import Session
ENGINE = create_engine("sqlite:///demo.db", future=True, echo=False)
def run_query(sql: str) -> record[dict]:
with Session(ENGINE) as session:
rows = session.execute(textual content(sql)).mappings().all()
return [dict(r) for r in rows]
After that, we’ll put together the openai_utils.py file that may settle for the database schema and the enter questions. The output will probably be JSON containing the SQL question (with a guard to forestall any write operations).
import os
import json
from openai import OpenAI
consumer = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
_SYSTEM_PROMPT = """
You exchange natural-language questions into read-only SQLite SQL.
By no means output INSERT / UPDATE / DELETE.
Return JSON: { "sql": "..." }.
"""
def text_to_sql(query: str, schema: str) -> str:
response = consumer.chat.completions.create(
mannequin="gpt-4o-mini",
temperature=0.1,
response_format={"sort": "json_object"},
messages=[
{"role": "system", "content": _SYSTEM_PROMPT},
{"role": "user",
"content": f"schema:n{schema}nnquestion: {question}"}
]
)
payload = json.masses(response.selections[0].message.content material)
return payload["sql"]
With each the code and the connection prepared, we’ll put together the applying utilizing FastAPI. The appliance will settle for pure language questions and the database schema, convert them into SQL SELECT queries, run them by the SQLite database, and return the outcomes as JSON. The appliance will probably be an API we will entry through the CLI.
from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
from sqlalchemy import examine
from .database import ENGINE, run_query
from .openai_utils import text_to_sql
app = FastAPI(title="Textual content-to-SQL Demo")
class NLRequest(BaseModel):
query: str
@app.on_event("startup")
def capture_schema() -> None:
insp = examine(ENGINE)
international SCHEMA_STR
SCHEMA_STR = "n".be a part of(
f"CREATE TABLE {t} ({', '.be a part of(c['name'] for c in insp.get_columns(t))});"
for t in insp.get_table_names()
)
@app.submit("/question")
def question(req: NLRequest):
strive:
sql = text_to_sql(req.query, SCHEMA_STR)
if not sql.lstrip().decrease().startswith("choose"):
increase ValueError("Solely SELECT statements are allowed")
return {"sql": sql, "consequence": run_query(sql)}
besides Exception as e:
increase HTTPException(status_code=400, element=str(e))
That’s every thing we want for the primary utility. The following factor we’ll put together is the database. Use the database beneath within the init_db.sql for instance functions, however you’ll be able to at all times change it if you would like.
DROP TABLE IF EXISTS order_items;
DROP TABLE IF EXISTS orders;
DROP TABLE IF EXISTS funds;
DROP TABLE IF EXISTS merchandise;
DROP TABLE IF EXISTS prospects;
CREATE TABLE prospects (
id INTEGER PRIMARY KEY,
identify TEXT NOT NULL,
nation TEXT,
signup_date DATE
);
CREATE TABLE merchandise (
id INTEGER PRIMARY KEY,
identify TEXT NOT NULL,
class TEXT,
value REAL
);
CREATE TABLE orders (
id INTEGER PRIMARY KEY,
customer_id INTEGER,
order_date DATE,
complete REAL,
FOREIGN KEY (customer_id) REFERENCES prospects(id)
);
CREATE TABLE order_items (
order_id INTEGER,
product_id INTEGER,
amount INTEGER,
unit_price REAL,
PRIMARY KEY (order_id, product_id),
FOREIGN KEY (order_id) REFERENCES orders(id),
FOREIGN KEY (product_id) REFERENCES merchandise(id)
);
CREATE TABLE funds (
id INTEGER PRIMARY KEY,
order_id INTEGER,
payment_date DATE,
quantity REAL,
methodology TEXT,
FOREIGN KEY (order_id) REFERENCES orders(id)
);
INSERT INTO prospects (id, identify, nation, signup_date) VALUES
(1,'Alice','USA','2024-01-05'),
(2,'Bob','UK','2024-03-10'),
(3,'Choi','KR','2024-06-22'),
(4,'Dara','ID','2025-01-15');
INSERT INTO merchandise (id, identify, class, value) VALUES
(1,'Laptop computer Professional','Electronics',1500.00),
(2,'Noise-Canceling Headphones','Electronics',300.00),
(3,'Standing Desk','Furnishings',450.00),
(4,'Ergonomic Chair','Furnishings',250.00),
(5,'Monitor 27"','Electronics',350.00);
INSERT INTO orders (id, customer_id, order_date, complete) VALUES
(1,1,'2025-02-01',1850.00),
(2,2,'2025-02-03',600.00),
(3,3,'2025-02-05',350.00),
(4,1,'2025-02-07',450.00);
INSERT INTO order_items (order_id, product_id, amount, unit_price) VALUES
(1,1,1,1500.00),
(1,2,1,300.00),
(1,5,1,350.00),
(2,3,1,450.00),
(2,4,1,250.00),
(3,5,1,350.00),
(4,3,1,450.00);
INSERT INTO funds (id, order_id, payment_date, quantity, methodology) VALUES
(1,1,'2025-02-01',1850.00,'Credit score Card'),
(2,2,'2025-02-03',600.00,'PayPal'),
(3,3,'2025-02-05',350.00,'Credit score Card'),
(4,4,'2025-02-07',450.00,'Financial institution Switch');
Then, run the next code in your CLI to create a SQLite database for our mission.
sqlite3 demo.db < init_db.sql
With the database prepared, we’ll create a Dockerfile to containerize our utility.
FROM python:3.12-slim
WORKDIR /code
COPY necessities.txt .
RUN pip set up --no-cache-dir -r necessities.txt
COPY . .
CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]
We will even create a docker-compose.yml file for operating the applying extra easily.
companies:
text2sql:
construct: .
env_file: .env
ports:
- "8000:8000"
restart: unless-stopped
volumes:
- ./demo.db:/code/demo.db
With every thing prepared, begin your Docker Desktop and run the next code to construct the applying.
docker compose construct --no-cache
docker compose up -d
If every thing is completed effectively, you’ll be able to check the applying by utilizing the next code. We’ll ask what number of prospects we have now within the knowledge.
curl -X POST "http://localhost:8000/question" -H "Content material-Sort: utility/json" -d "{"query":"What number of prospects?"}"
The output will appear like this.
{"sql":"SELECT COUNT(*) AS customer_count FROM prospects;","consequence":[{"customer_count":4}]}
We are able to strive one thing extra advanced, just like the variety of orders for every buyer:
curl -X POST "http://localhost:8000/question" -H "Content material-Sort: utility/json" -d "{"query":"What's the variety of orders positioned by every buyer"}"
With output like beneath.
{"sql":"SELECT customer_id, COUNT(*) AS number_of_orders FROM orders GROUP BY customer_id;","consequence":[{"customer_id":1,"number_of_orders":2},{"customer_id":2,"number_of_orders":1},{"customer_id":3,"number_of_orders":1}]}
That’s all it is advisable construct a fundamental Textual content-to-SQL utility. You may improve it additional with a front-end interface and a extra advanced system tailor-made to your wants.
# Wrapping Up
Knowledge is the guts of any knowledge work, and firms use it to make selections. Many instances, the system we have now is simply too advanced, and we have to depend on generative AI to assist us navigate it.
On this article, we have now realized develop a easy Textual content-to-SQL utility utilizing the OpenAI mannequin, FastAPI, and SQLite.
I hope this has helped!
Cornellius Yudha Wijaya is a knowledge science assistant supervisor and knowledge author. Whereas working full-time at Allianz Indonesia, he likes to share Python and knowledge ideas through social media and writing media. Cornellius writes on quite a lot of AI and machine studying subjects.
