Create prompts for Gemini in Vertex AI Studio

Use Vertex AI Studio to design, test, and customize your prompts sent to Google's Gemini and PaLM 2 large language models (LLM). After an LLM processes your prompt, it sends you its response. You can also view the Gemini API in Vertex AI code used to generate the response. To learn more about the Vertex AI Studio, see Experiment with models in Vertex AI Studio.

Create a Google Cloud account to get started

In order to try this quickstart, you'll need to create a Google Cloud account. With this account, you'll get $300 in free credit, plus free usage of over 20 products— not charged against your $300 credit.

Get started for free

For more information on getting set up on Google Cloud after your account is created, see Get set up on Google Cloud.
  1. Go to the Vertex AI Studio page from the Vertex AI section in the Google Cloud console.
    Vertex AI Studio
  2. Click Open on the Language model option.
  3. From the Language studio, navigate to the Summarization section of the Prompt Gallery, and select Open on the Transcript Summary prompt example. The prompt, model, and parameters are prefilled with the values from the sample prompt.
  4. Click Submit to get a response from the test model. Scroll to see all of the results.
  5. To see different results, change the Model in the model drop-down, and adjust the parameters.
  6. Click Get Code to view the Vertex AI API code needed to generate a transcript summary.

Design and test your prompt

You can create and test your prompts (inputs) for tasks that are relevant to your business use case, and generate responses. By adding inputs and outputs, the LLM is capable of learning in-context from the examples of responses.

You can create a prompt, which gives a precise instruction, and asks the LLM to complete a sentence for you or to answer one-time questions.

  1. Go to the Vertex AI Studio page from the Vertex AI section in the Google Cloud console.
    Vertex AI Studio
  2. Click Open on the Language model option.
  3. Click Text Prompt on the Generate text option. An untitled prompt opens.
  4. In the prompt box, add a clear and concise description of the task that you want the model to do.
  5. As an example, ask the model to Suggest a name for a flower shop that sells bouquets of dried flowers.
  6. Click Submit.
  7. Responses appear in response box. If you want to view different results, adjust the parameters, and click Submit.
  8. Click Get Code to view the Vertex AI API code needed to generate a similar response.

What's next