Vertex AI
Vertex AI connects your flows to Vertex AI models, in your company’s Google Cloud project. You can use it in two ways: as the model of an agent, by connecting its Model output to the agent’s Model input, or on its own, so that it answers the text that reaches its Input.
When to use it
- Give an agent the model it uses to understand requests, decide which tools to use and answer.
- Write, summarise or classify texts inside a flow, without an agent.
- Process a list of texts one by one, for example all the reviews of a month, with Batch Mode.
- Use Google’s models inside your company’s Google Cloud project, under its contract terms.
Configuration
In the Common tab:
| Field | What it does |
|---|---|
| Credentials | Upload the service account key file of your Google Cloud project (a .json file). |
| Model Name | The name of the model that answers. You can type it or connect it from another component. Default: gemini-2.0-flash. |
| Temperature | How varied the answers are: low values give steadier, more predictable answers; high values, more creative ones. Default: 0.0. |
| Connection | What to connect |
|---|---|
| Input | The text the model must answer when it works on its own, for example the message of a Chat Input or the result of a Prompt. |
Advanced options
In the Advanced tab:
| Field | What it does |
|---|---|
| System Message | General instructions for the model when it works on its own: its role, the tone, what to avoid. You can type them or connect them from another component. |
| Stream | Shows the answer in the chat while it is being written, instead of waiting until it is finished. It only has an effect in the chat. Default: off. |
| Project | The identifier of your Google Cloud project. If you leave it empty, it is taken from the Credentials file. |
| Location | The Google Cloud region where the model runs. Default: us-central1. |
| Max Output Tokens | The maximum length of the answer, in tokens (pieces of words). |
| Max Retries | How many times the request is repeated if the service fails. Default: 1. |
| Top K and Top P | Other ways to control how varied the answer is. Temperature is usually enough. |
| Other options | Verbose: fine-tuning settings for advanced users. Leave them as they are if you don’t need them. |
Batch processing
With the Batch Mode switch on, the component runs once for each item of the list you connect to Batch Input and returns all the results together as a list. Parallel Executions sets how many items are processed at the same time (1 to 5). Skip if Empty Batch Input skips the component when the list arrives empty, and Skip Branch if Empty Output stops the following components when the result is empty. More in Key concepts.
Output
| Output | What it contains |
|---|---|
| Model | The configured model. It sits at the top of the component. Connect it to the Model input of an agent or of any other component that asks for a model. |
| Text | The model’s answer to the text received in Input. Connect it, for example, to a Chat Output or to another component that works with text. |
The two ways of using it exclude each other: when you connect the Model output, the component hides Input and Text, because the model now works inside the other component; and if you connect Input, Model is hidden.
Example
The Alimentación Serrano group runs on Google Cloud. It uploads its service account key file in Credentials, keeps the default model and connects the Model output to an agent that answers its suppliers.
Good practices
- Use a low Temperature when you need exact answers, such as classifying or extracting data, and raise it for more creative texts.
- If you use the model with an agent, configure only the model here: the instructions and the tools are set in the agent.