fredsa / hello-gemini-vertex-ai-api

Hello, Gemini using Vertex AI API.

Sample app showing how to access Gemini using the Vertex AI API.

Prerequisites

1. Download and install Go, see https://go.dev/. To determine the version of Go that is available on your path run:

   go version

2. [Optional] Install gcloud CLI, see https://cloud.google.com/sdk/docs/install.

Prepare sample project

1. Clone this repo.

   git clone [e-mail]:fredsa/hello-gemini-vertex-ai-api.git

2. Change into the project directory.

   cd hello-gemini-vertex-ai-api

3. Install the cloud.google.com/go/vertexai/genai package.

   go get cloud.google.com/go/vertexai/genai

Authorize the app

1. To use Application Default Credentials to authorize the app, run the following gcloud command:

   gcloud auth application-default login

   Alternatively, you can authorize the app using an API key by modifying main.go to use option.WithAPIKey when creating the client:

   // New client, authorize using an API KEY.
   option := option.WithAPIKey("YOUR_API_KEY")
   client, err := genai.NewClient(ctx, project, location, option)

Run the sample

1. Compile and run.

   go run main.go

   The output should look something like this

   >> Hello, who are you?
   I am a large language model, trained by Google.