Google Gemini
This documentation describes the integration of MindsDB with Google Gemini, a generative artificial intelligence model developed by Google. The integration allows for the deployment of Google Gemini 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 Google Gemini within MindsDB, install the required dependencies following this instruction.
- Obtain the Google Gemini API key required to deploy and use Google Gemini models within MindsDB. Follow the instructions for obtaining the API key.
Setup
Create an AI engine from the Google Gemini handler.
CREATE ML_ENGINE google_gemini_engine
FROM google_gemini
USING
api_key = 'api-key-value';
Create a model using google_gemini_engine
as an engine.
CREATE MODEL google_gemini_model
PREDICT target_column
USING
engine = 'google_gemini_engine', -- engine name as created via CREATE ML_ENGINE
column = 'input_column', -- column name that stores user input
model = 'gemini-pro'; -- model name to be used
Usage
The following usage examples utilize google_gemini_engine
to create a model with the CREATE MODEL
statement.
Create a model to generate text completions with the Gemini Pro model for your existing text data.
CREATE MODEL google_gemini_model
PREDICT answer
USING
engine = 'google_gemini_engine',
column = 'question',
model = 'gemini-pro';
Query the model to get predictions.
SELECT question, answer
FROM google_gemini_model
WHERE question = 'How are you?';
Alternatively, you can query for batch predictions:
SELECT t.question, m.answer
FROM google_gemini_model AS m
JOIN data_table AS t;
Next Steps
Go to the Use Cases section to see more examples.
Was this page helpful?