Max Stepanov
b8cdf29c74
Co-authored-by: martyna-mindsdb <109554435+martyna-mindsdb@users.noreply.github.com>
132 lines
8.4 KiB
Plaintext
132 lines
8.4 KiB
Plaintext
---
|
||
title: Configure an ML Engine
|
||
sidebarTitle: Configure an ML Engine
|
||
---
|
||
|
||
MindsDB integrates with numerous AI and ML frameworks that are made available via the AI/ML engines. The AI/ML engines are used to create models based on the particular AI/ML framework.
|
||
|
||
## Description
|
||
|
||
The `CREATE ML_ENGINE` command creates an ML engine that uses one of the available AI/ML handlers.
|
||
|
||
## Syntax
|
||
|
||
Before creating an AI/ML engine, make sure that the AI/ML handler of your interest is available by querying for the ML handlers.
|
||
|
||
```sql
|
||
SELECT *
|
||
FROM information_schema.handlers;
|
||
-- or
|
||
SHOW HANDLERS;
|
||
```
|
||
|
||
<Info>
|
||
If you can’t find the AI/ML handler of your interest, you can contribute by [building a new AI/ML handler](/contribute/ml-handlers).
|
||
|
||
Please note that in the process of contributing new AI.ML engines, ML engines and/or their tests will only run correctly if all dependencies listed in the `requirements.txt` file are installed beforehand.
|
||
</Info>
|
||
|
||
If you find the AI/ML handler of your interest, then you can create an AI/ML engine using this command:
|
||
|
||
```sql
|
||
CREATE ML_ENGINE [IF NOT EXISTS] ml_engine_name
|
||
FROM handler_name
|
||
[USING argument_key = argument_value];
|
||
```
|
||
|
||
Please replace `ml_engine_name`, `handler_name`, and optionally, `argument_key` and `argument_value` with the real values.
|
||
|
||
<Note>
|
||
Please do not use the same `ml_engine_name` as the `handler_name` to avoid issue while dropping the ML engine.
|
||
</Note>
|
||
|
||
To verify that your AI/ML engine was successfully created, run the command below:
|
||
|
||
```sql
|
||
SELECT *
|
||
FROM information_schema.ml_engines;
|
||
-- or
|
||
SHOW ML_ENGINES;
|
||
```
|
||
|
||
If you want to drop an ML engine, run the command below:
|
||
|
||
```sql
|
||
DROP ML_ENGINE ml_engine_name;
|
||
```
|
||
|
||
## Example
|
||
|
||
Let's check what AI/ML handlers are currently available:
|
||
|
||
```sql
|
||
SHOW HANDLERS;
|
||
```
|
||
|
||
On execution, we get:
|
||
|
||
```sql
|
||
+-------------------+--------------------+-------------------------------------------------------+---------+-----------------------------------------------------------------------------------------------------------------------------------------------------+----------------+-----------------------------------------------------------------------------+
|
||
| NAME | TITLE | DESCRIPTION | VERSION | CONNECTION_ARGS | IMPORT_SUCCESS | IMPORT_ERROR |
|
||
+-------------------+--------------------+-------------------------------------------------------+---------+-----------------------------------------------------------------------------------------------------------------------------------------------------+----------------+-----------------------------------------------------------------------------+
|
||
| "ray_serve" | "RayServe" | "MindsDB handler for Ray Serve" | "0.0.1" | "[NULL]" | "true" | "[NULL]" |
|
||
| "autosklearn" | "Auto-Sklearn" | "MindsDB handler for Auto-Sklearn" | "0.0.2" | "[NULL]" | "false" | "No module named 'autosklearn'" |
|
||
| "mlflow" | "MLFlow" | "MindsDB handler for MLflow" | "0.0.2" | "[NULL]" | "false" | "No module named 'mlflow'" |
|
||
| "openai" | "OpenAI" | "MindsDB handler for OpenAI" | "0.0.1" | "[NULL]" | "true" | "[NULL]" |
|
||
| "merlion" | "Merlion" | "MindsDB handler for Merlion" | "0.0.1" | "[NULL]" | "false" | "object.__init__() takes exactly one argument (the instance to initialize)" |
|
||
| "byom" | "BYOM" | "MindsDB handler for BYOM" | "0.0.1" | "{'code': {'type': 'path', 'description': 'The path to model code'}, 'modules': {'type': 'path', 'description': 'The path to model requirements'}}" | "true" | "[NULL]" |
|
||
| "huggingface_api" | "Hugging Face API" | "MindsDB handler for Auto-Sklearn" | "0.0.2" | "[NULL]" | "false" | "No module named 'hugging_py_face'" |
|
||
| "huggingface" | "Hugging Face" | "MindsDB handler for Higging Face" | "0.0.1" | "[NULL]" | "true" | "[NULL]" |
|
||
| "TPOT" | "Tpot" | "MindsDB handler for TPOT " | "0.0.2" | "[NULL]" | "false" | "No module named 'tpot'" |
|
||
| "langchain" | "LangChain" | "MindsDB handler for LangChain" | "0.0.1" | "[NULL]" | "true" | "[NULL]" |
|
||
| "autokeras" | "Autokeras" | "MindsDB handler for Autokeras AutoML" | "0.0.1" | "[NULL]" | "false" | "No module named 'autokeras'" |
|
||
+-------------------+--------------------+-------------------------------------------------------+---------+-----------------------------------------------------------------------------------------------------------------------------------------------------+----------------+-----------------------------------------------------------------------------+
|
||
```
|
||
|
||
Here we create an AI/ML engine using the OpenAI handler and providing an OpenAI API key in the `USING` clause.
|
||
|
||
```sql
|
||
CREATE ML_ENGINE my_openai_engine
|
||
FROM openai
|
||
USING
|
||
openai_api_key = '<your opanai api key>';
|
||
```
|
||
|
||
On execution, we get:
|
||
|
||
```sql
|
||
Query successfully completed
|
||
```
|
||
|
||
Now let's verify that our ML engine exists.
|
||
|
||
```sql
|
||
SHOW ML_ENGINES;
|
||
```
|
||
|
||
On execution, we get:
|
||
|
||
```sql
|
||
+-------------------+------------+------------------------------------------------------+
|
||
|NAME |HANDLER |CONNECTION_DATA |
|
||
+-------------------+------------+------------------------------------------------------+
|
||
|huggingface |huggingface |{"key":["password"],"value":[""]} |
|
||
|openai |openai |{"key":["password"],"value":[""]} |
|
||
|my_openai_engine |openai |{"key":["openai_api_key","password"],"value":["",""]} |
|
||
+-------------------+------------+------------------------------------------------------+
|
||
```
|
||
|
||
Please note that the `USING` clause is optional, as it depends on the AI/ML handler whether it requires some arguments or not. Here, we created an OpenAI engine and provided own API key.
|
||
|
||
After creating your ML engine, you can create a model like this:
|
||
|
||
```sql
|
||
CREATE MODEL my_model
|
||
PREDICT answer
|
||
USING
|
||
engine = 'my_openai_engine',
|
||
prompt_template = 'ask a question to a model'
|
||
```
|
||
|
||
The `USING` clause specifies the ML engine to be used for creating a new model.
|