Skip to content

Commit 722d22f

Browse files
BohuTANGBohuTANG
committed
docs(ai): refine the layout of openai functions
1 parent 639ab43 commit 722d22f

File tree

2 files changed

+93
-83
lines changed

2 files changed

+93
-83
lines changed

‎docs/doc/15-sql-functions/61-ai-functions/01-ai-to-sql.md‎

Lines changed: 88 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,88 @@
1+
---
2+
title: 'AI_TO_SQL'
3+
---
4+
5+
Databend leverages the OpenAI **Code-Davinci-002** engine to convert natural language into SQL queries.
6+
7+
By integrating OLAP and AI, Databend streamlines the process of crafting SQL queries based on your table schema.
8+
9+
The `ai_to_sql` function enables the effortless generation of SQL queries using natural language.
10+
11+
## Syntax
12+
13+
```sql
14+
USE <your-database>;
15+
SELECT * FROM ai_to_sql('<prompt>', '<openai-api-key>');
16+
```
17+
18+
## Example
19+
20+
:::note
21+
Please note that the generated SQL query may need to be adapted to match Databend's syntax and functionality, as it might be based on PostgreSQL-standard SQL.
22+
:::
23+
24+
25+
```sql
26+
CREATE DATABASE IF NOT EXISTS openai;
27+
USE openai;
28+
29+
CREATE TABLE users(
30+
id INT,
31+
name VARCHAR,
32+
age INT,
33+
country VARCHAR
34+
);
35+
36+
CREATE TABLE orders(
37+
order_id INT,
38+
user_id INT,
39+
product_name VARCHAR,
40+
price DECIMAL(10,2),
41+
order_date DATE
42+
);
43+
44+
-- Insert sample data into the users table
45+
INSERT INTO users VALUES (1, 'Alice', 31, 'USA'),
46+
(2, 'Bob', 32, 'USA'),
47+
(3, 'Charlie', 45, 'USA'),
48+
(4, 'Diana', 29, 'USA'),
49+
(5, 'Eva', 35, 'Canada');
50+
51+
-- Insert sample data into the orders table
52+
INSERT INTO orders VALUES (1, 1, 'iPhone', 1000.00, '2022-03-05'),
53+
(2, 1, 'OpenAI Plus', 20.00, '2022-03-06'),
54+
(3, 2, 'OpenAI Plus', 20.00, '2022-03-07'),
55+
(4, 2, 'MacBook Pro', 2000.00, '2022-03-10'),
56+
(5, 3, 'iPad', 500.00, '2022-03-12'),
57+
(6, 3, 'AirPods', 200.00, '2022-03-14');
58+
```
59+
60+
AI-Powered SQL Query Generation:
61+
```sql
62+
-- Generate an SQL query using the ai_to_sql function
63+
SELECT * FROM ai_to_sql(
64+
'List the total amount spent by users from the USA who are older than 30 years, grouped by their names, along with the number of orders they made in 2022',
65+
'<openai-api-key>');
66+
```
67+
68+
Output:
69+
```sql
70+
*************************** 1. row ***************************
71+
database: openai
72+
generated_sql: SELECT name, SUM(price) AS total_spent, COUNT(order_id) AS total_orders
73+
FROM users
74+
JOIN orders ON users.id = orders.user_id
75+
WHERE country = 'USA' AND age > 30 AND order_date BETWEEN '2022-01-01' AND '2022-12-31'
76+
GROUP BY name;
77+
```
78+
79+
Query Result:
80+
```sql
81+
+---------+-------------+-------------+
82+
| name | order_count | total_spent |
83+
+---------+-------------+-------------+
84+
| Bob | 2 | 2020.00 |
85+
| Alice | 2 | 1020.00 |
86+
| Charlie | 2 | 700.00 |
87+
+---------+-------------+-------------+
88+
```

‎docs/doc/15-sql-functions/61-ai-functions/index.md‎

Lines changed: 5 additions & 83 deletions
Original file line numberDiff line numberDiff line change
@@ -1,88 +1,10 @@
11
---
2-
title: 'AI Functions'
2+
title: 'Databend AI Functions using OpenAI'
3+
description: 'Learn how to use AI functions in Databend with the help of the OpenAI engine.'
34
---
45

5-
Databend leverages the OpenAI **Code-Davinci-002** engine to convert natural language into SQL queries.
6+
Databend integrates AI functions with the help of the [OpenAI](https://openai.com/) engine, allowing users to generate SQL queries and interact with databases using natural language. This makes it easier for users to work with databases and query data without in-depth knowledge of SQL syntax.
67

7-
By integrating OLAP and AI, Databend streamlines the process of crafting SQL queries based on your table schema.
8+
## AI-Powered SQL Query Generation
89

9-
The `ai_to_sql` function enables the effortless generation of SQL queries using natural language.
10-
11-
## Syntax
12-
13-
```sql
14-
USE <your-database>;
15-
SELECT * FROM ai_to_sql('<prompt>', '<openai-api-key>');
16-
```
17-
18-
## Example
19-
20-
:::note
21-
Please note that the generated SQL query may need to be adapted to match Databend's syntax and functionality, as it might be based on PostgreSQL-standard SQL.
22-
:::
23-
24-
25-
```sql
26-
CREATE DATABASE IF NOT EXISTS openai;
27-
USE openai;
28-
29-
CREATE TABLE users(
30-
id INT,
31-
name VARCHAR,
32-
age INT,
33-
country VARCHAR
34-
);
35-
36-
CREATE TABLE orders(
37-
order_id INT,
38-
user_id INT,
39-
product_name VARCHAR,
40-
price DECIMAL(10,2),
41-
order_date DATE
42-
);
43-
44-
-- Insert sample data into the users table
45-
INSERT INTO users VALUES (1, 'Alice', 31, 'USA'),
46-
(2, 'Bob', 32, 'USA'),
47-
(3, 'Charlie', 45, 'USA'),
48-
(4, 'Diana', 29, 'USA'),
49-
(5, 'Eva', 35, 'Canada');
50-
51-
-- Insert sample data into the orders table
52-
INSERT INTO orders VALUES (1, 1, 'iPhone', 1000.00, '2022-03-05'),
53-
(2, 1, 'OpenAI Plus', 20.00, '2022-03-06'),
54-
(3, 2, 'OpenAI Plus', 20.00, '2022-03-07'),
55-
(4, 2, 'MacBook Pro', 2000.00, '2022-03-10'),
56-
(5, 3, 'iPad', 500.00, '2022-03-12'),
57-
(6, 3, 'AirPods', 200.00, '2022-03-14');
58-
```
59-
60-
AI-Powered SQL Query Generation:
61-
```sql
62-
-- Generate an SQL query using the ai_to_sql function
63-
SELECT * FROM ai_to_sql(
64-
'List the total amount spent by users from the USA who are older than 30 years, grouped by their names, along with the number of orders they made in 2022',
65-
'<openai-api-key>');
66-
```
67-
68-
Output:
69-
```sql
70-
*************************** 1. row ***************************
71-
database: openai
72-
generated_sql: SELECT name, SUM(price) AS total_spent, COUNT(order_id) AS total_orders
73-
FROM users
74-
JOIN orders ON users.id = orders.user_id
75-
WHERE country = 'USA' AND age > 30 AND order_date BETWEEN '2022-01-01' AND '2022-12-31'
76-
GROUP BY name;
77-
```
78-
79-
Query Result:
80-
```sql
81-
+---------+-------------+-------------+
82-
| name | order_count | total_spent |
83-
+---------+-------------+-------------+
84-
| Bob | 2 | 2020.00 |
85-
| Alice | 2 | 1020.00 |
86-
| Charlie | 2 | 700.00 |
87-
+---------+-------------+-------------+
88-
```
10+
Databend leverages the OpenAI Code-Davinci-002 engine to convert natural language into SQL queries and provide assistance with database interactions. By integrating OLAP and AI, Databend streamlines the process of crafting SQL queries based on your table schema. The ai_to_sql function enables the effortless generation of SQL queries using natural language, and the chat capabilities of the OpenAI engine can assist in answering database-related questions.

0 commit comments

Comments
 (0)