How to Use Knowledge Bases

This section contains examples of usage of knowledge bases.

Sales Data

Here is the data that will be inserted into the knowledge base.

+----------+-------------------+------------------------+
| order_id | product           | notes                  |
+----------+-------------------+------------------------+
| A1B      | Wireless Mouse    | Request color: black   |
| 3XZ      | Bluetooth Speaker | Gift wrap requested    |
| Q7P      | Laptop Stand      | Prefer aluminum finish |
+----------+-------------------+------------------------+

You can access this sample data as below:

CREATE DATABASE sample_data
WITH ENGINE = 'postgres',
PARAMETERS = {
    "user": "demo_user",
    "password": "demo_password",
    "host": "samples.mindsdb.com",
    "port": "5432",
    "database": "demo",
    "schema": "demo_data"
};

SELECT * FROM sample_data.orders;

Here is how to create a knowledge base specifically for the data.

CREATE KNOWLEDGE_BASE my_kb
USING
    embedding_model = {
        "provider": "openai",
        "model_name" : "text-embedding-3-large",
        "api_key": "sk-abc123"
    },
    reranking_model = {
        "provider": "openai",
        "model_name": "gpt-4o",
        "api_key": "sk-abc123"
    },
    metadata_columns = ['product'],
    content_columns = ['notes'],
    id_column = 'order_id';

Here is how to insert the data.

INSERT INTO my_kb
SELECT order_id, product, notes
FROM sample_data.orders;

Here is how to query the knowledge base.

SELECT *
FROM my_kb
WHERE product = 'Wireless Mouse'
AND content = 'color'
AND relevance > 0.5;

Financial Data

You can access the sample data as below:

CREATE DATABASE sample_data
WITH ENGINE = 'postgres',
PARAMETERS = {
    "user": "demo_user",
    "password": "demo_password",
    "host": "samples.mindsdb.com",
    "port": "5432",
    "database": "demo",
    "schema": "demo_data"
};

SELECT * FROM sample_data.financial_headlines;

Here is how to create a knowledge base specifically for the data.

CREATE KNOWLEDGE_BASE my_kb
USING
    embedding_model = {
        "provider": "openai",
        "model_name" : "text-embedding-3-large",
        "api_key": "sk-xxx"
    },
    reranking_model = {
        "provider": "openai",
        "model_name": "gpt-4o",
        "api_key": "sk-xxx"
    },
    metadata_columns = ['sentiment_labelled'],
    content_columns = ['headline'];

Here is how to insert the data.

INSERT INTO my_kb
SELECT *
FROM sample_data.financial_headlines
USING
    batch_size = 500,
    threads = 10;

Here is how to query the knowledge base.

• Query without defined LIMIT

SELECT *
FROM my_kb
WHERE content = 'investors';

This query returns 10 rows, as the default LIMIT is set to 10.

• Query with defined LIMIT

SELECT *
FROM my_kb
WHERE content = 'investors'
LIMIT 20;

This query returns 20 rows, as the user-defined LIMIT is set to 20.

• Query with defined LIMIT and relevance

SELECT *
FROM my_kb
WHERE content = 'investors'
AND relevance >= 0.8
LIMIT 20;

This query may return 20 or less rows, depending on whether the relevance scores of the rows match the user-defined condition.