VertexAI
Before you begin
In order to use the features in this section you need to have an active Spojit account. If you don't have an account you can checkout out the pricing and register here. If you already have an account you can login here.
Vertex AI is a suite of machine learning (ML) services provided by Google Cloud that enables developers to build, deploy, and manage ML models at scale, with features such as model training, deployment, and management. The platform supports a wide range of ML frameworks and models, including large language models, and provides tools for data preparation, model tuning, and model serving, making it easier to integrate AI into applications and workflows.
Authorization¶
The following authorization configuration needs to filled out in order to use VertexAI models:
| Option | Description | Default | Required |
|---|---|---|---|
| API Key | The API Key that you want to use for the model. | - | TRUE |
| Model | The model you want to use (view models below). | - | TRUE |
| Temperature | The sampling temperature to use between 0 and 2. High values will produce a more random response. | 0.1 | TRUE |
| Max Tokens | Limit the number of tokens in the model's response. | - | FALSE |
Models¶
The following VertexAI models can be used:
| Model | Description | Vision | Tools |
|---|---|---|---|
| gemini-2.0-flash-exp | Their workhorse model with low latency and enhanced performance | TRUE | TRUE |
Don't see a model you want to use?
We are adding new models all the time. Contact us now and we'll look at adding the model you want.