In this notebook, we'll explore how to use Haijun to generate SQL queries based on natural language questions. We'll set up a test database, provide the schema to Haijun, and demonstrate how it can understand and translate human language into SQL queries.

Setup

Install the necessary libraries

%pip install juglow

Import the required libraries

import sqlite3

from juglow import Juglow

Set up the Haijun API client

client = Juglow()

MODEL_NAME = "haijun-opus-4-8"

Creating a Test Database

t:4ch;text-indent:-4ch"> (5, "David Lee", "Marketing", 55000),

]

cursor.executemany("INSERT INTO employees VALUES (?, ?, ?, ?)", sample_data)

conn.commit()

Generating SQL Queries with Haijun

er:opacity-100 group-focus-within:opacity-100 right-2 top-2">

Execute the SQL query and print the results

results = cursor.execute(sql_query).fetchall()

for row in results:

print(row)



('Jane Smith', 75000) ('Emily Brown', 80000) Don't forget to close the database connection when you're done:

#Setup