Describe a Model

Description

The DESCRIBE statement is used to display the attributes of an existing model. The available options to describe a model depend on the underlying engine.

Syntax

Here is how to retrieve general information on the model:

DESCRIBE model_name;

Or:

DESCRIBE MODEL model_name;

This command is similar to the below command:

SELECT *
FROM models
WHERE name = 'model_name';

One difference between these two commands is that DESCRIBE outputs an additional column that stores all available options to describe a model, depending on the underlying engine.

Examples

NLP Models

MindsDB offers NLP models that utilize either Hugging Face or OpenAI engines. Let’s see how to describe such models.

DESCRIBE [MODEL] sentiment_classifier;

On execution we get:

+---------------------+----------------------+--------+---------+--------+---------+----------+----------+-----------+---------------+-----------------+--------+-------------------+---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+--------+
| tables              | NAME                 | ENGINE | PROJECT | ACTIVE | VERSION | STATUS   | ACCURACY | PREDICT   | UPDATE_STATUS | MINDSDB_VERSION | ERROR  | SELECT_DATA_QUERY | TRAINING_OPTIONS                                                                                                                                                                                                                                                                                              | TAG    |
+---------------------+----------------------+--------+---------+--------+---------+----------+----------+-----------+---------------+-----------------+--------+-------------------+---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+--------+
| ["args","metadata"] | sentiment_classifier | openai | mindsdb | true   | 1       | complete | [NULL]   | sentiment | up_to_date    | 23.1.3.2        | [NULL] | [NULL]            | {'target': 'sentiment', 'using': {'prompt_template': 'describe the sentiment of the reviews\n                     strictly as "positive", "neutral", or "negative".\n                     "I love the product":positive\n                     "It is a scam":negative\n                     "{{review}}.":'}} | [NULL] |
+---------------------+----------------------+--------+---------+--------+---------+----------+----------+-----------+---------------+-----------------+--------+-------------------+---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+--------+

The tables output column lists all available options to describe a model.

DESCRIBE args
DESCRIBE metadata

DESCRIBE [MODEL] sentiment_classifier.args;

The above command returns the following output columns:

Name	Description
`key`	It stores parameters, such as `prompt_template` and `target`.
`value`	It stores parameter values.

DESCRIBE [MODEL] sentiment_classifier.metadata;

The above command returns the following output columns:

Name	Description
`key`	It stores metadata parameters.
`value`	It stores parameter values.

Nixtla Models

MindsDB integrates Nixtla engines, such as StatsForecast, NeuralForecast, and HierarchicalForecast. Let’s see how to describe models based on Nixtla engines.

DESCRIBE [MODEL] quarterly_expenditure_forecaster;

On execution we get:

+-----------------------------+----------------------------------+---------------+---------+--------+---------+----------+----------+-------------+---------------+-----------------+--------+---------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------+--------+
| tables                      | NAME                             | ENGINE        | PROJECT | ACTIVE | VERSION | STATUS   | ACCURACY | PREDICT     | UPDATE_STATUS | MINDSDB_VERSION | ERROR  | SELECT_DATA_QUERY                     | TRAINING_OPTIONS                                                                                                                                    | TAG    |
+-----------------------------+----------------------------------+---------------+---------+--------+---------+----------+----------+-------------+---------------+-----------------+--------+---------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------+--------+
| ["info","features","model"] | quarterly_expenditure_forecaster | statsforecast | mindsdb | true   | 1       | complete | [NULL]   | expenditure | up_to_date    | 23.4.4.0        | [NULL] | SELECT * FROM historical_expenditures | {'target': 'expenditure', 'using': {}, 'timeseries_settings': {'is_timeseries': True, 'order_by': 'month', 'horizon': 3, 'group_by': ['category']}} | [NULL] |
+-----------------------------+----------------------------------+---------------+---------+--------+---------+----------+----------+-------------+---------------+-----------------+--------+---------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------+--------+

The tables output column lists all available options to describe a model.

DESCRIBE info
DESCRIBE features
DESCRIBE model

DESCRIBE [MODEL] quarterly_expenditure_forecaster.info;

The above command returns the following output columns:

Name	Description
`accuracies`	It lists the chosen model name and its accuracy score.
`outputs`	The target column.
`inputs`	All the feature columns.

DESCRIBE [MODEL] quarterly_expenditure_forecaster.features;

The above command returns the following output columns:

Name	Description
`ds`	It defines intervals between records. For example, here, we’ve got monthly expenditure records.
`y`	It stores the target column.
`unique_id`	It stores columns listed in the `GROUP BY` clause. It defines the column(s) in the dataset by which you can split it into multiple time series that track the same process or value for different entities or groups.

DESCRIBE [MODEL] quarterly_expenditure_forecaster.model;

The above command returns the following output columns:

Name	Description
`model_name`	It is the chosen model name.
`frequency`	It is the frequency
`season_length`	It indicates how many measurements until the next season occurs. For example, a time series with monthly measurements and a season length of 12 means that, every 12 months, a new season occurs. It can have a very strong effect on the final model’s performance.
`hierarchy`	It defines whether HierarchicalForecast is used (`true`) or not (`false`).

Other Models

Models that utlize LangChain or are brought to MindsDB via MLflow can be described as follows:

DESCRIBE [MODEL] other_model;

The above command returs ["info"] in its first output column.

DESCRIBE [MODEL] other_model.info;

The above command lists basic model information.

If you need more information on how to DESCRIBE [MODEL] or understand the results, feel free to ask us on the community Slack workspace.

Overview

Data Unification

Data Transformation

Data Automation

Describe a Model

Description

Syntax

Examples

NLP Models

Nixtla Models

Other Models

Overview

Data Unification

Data Transformation

Data Automation

​Description

​Syntax

​Examples

​NLP Models

​Nixtla Models

​Other Models

Description

Syntax

Examples

NLP Models

Nixtla Models

Other Models