Large Language Models
Cohere
This documentation describes the integration of MindsDB with Cohere, a technology company focused on artificial intelligence for the enterprise. The integration allows for the deployment of Cohere models within MindsDB, providing the models with access to data from various data sources.
Prerequisites
Before proceeding, ensure the following prerequisites are met:
- Install MindsDB locally via Docker or Docker Desktop.
- To use Cohere within MindsDB, install the required dependencies following this instruction.
- Obtain the Cohere API key required to deploy and use Cohere models within MindsDB. Sign up for a Cohere account and request an API key from the Cohere dashboard. Learn more here.
Setup
Create an AI engine from the Cohere handler.
CREATE ML_ENGINE cohere_engine
FROM cohere
USING
cohere_api_key = 'your-cohere-api-key';
Create a model using cohere_engine
as an engine.
CREATE MODEL cohere_model
PREDICT target_column
USING
engine = 'cohere_engine', -- engine name as created via CREATE ML_ENGINE
task = 'task_name', -- choose one of 'language-detection', 'text-summarization', 'text-generation'
column = 'column_name'; -- column that stores input/question to the model
Usage
The following usage examples utilize cohere_engine
to create a model with the CREATE MODEL
statement.
Create a model to detect language of a given input text.
CREATE MODEL cohere_model
PREDICT language
USING
engine = 'cohere_engine',
task = 'language-detection',
column = 'text';
Where:
Name | Description |
---|---|
task | It defines the task to be accomplished. |
column | It defines the column with the text to be acted upon. |
engine | It defines the Cohere engine. |
Query the model to get predictions.
SELECT text, language
FROM cohere_model
WHERE text = '¿Cómo estás?';
Here is the output:
+--------------+----------+
| text | language |
+--------------+----------+
| ¿Cómo estás? | Spanish |
+--------------+----------+
Next Steps
Go to the Use Cases section to see more examples.
Was this page helpful?