This is an automated email from the ASF dual-hosted git repository. acosentino pushed a commit to branch 2721 in repository https://gitbox.apache.org/repos/asf/camel-kamelets.git
commit 4b856d7f11aea644e8b0d8e46923cf5897114a58 Author: Andrea Cosentino <[email protected]> AuthorDate: Tue Feb 17 10:42:44 2026 +0100 Create a Google Vertex AI Sink Kamelet Signed-off-by: Andrea Cosentino <[email protected]> --- .../partials/google-vertexai-sink-description.adoc | 26 ++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/docs/modules/ROOT/partials/google-vertexai-sink-description.adoc b/docs/modules/ROOT/partials/google-vertexai-sink-description.adoc new file mode 100644 index 000000000..942bcb28e --- /dev/null +++ b/docs/modules/ROOT/partials/google-vertexai-sink-description.adoc @@ -0,0 +1,26 @@ +== Google Vertex AI Sink Kamelet Description + +=== Authentication + +This Kamelet uses Google Cloud service account authentication. The service account key is optional - if not provided, the Kamelet will use Application Default Credentials (ADC). + +If you provide a service account key, it must be base64-encoded. Ensure that the service account has the `aiplatform.endpoints.predict` permission (typically granted through the `Vertex AI User` role). + +=== Required Configuration + +- **Project ID**: The Google Cloud Project ID +- **Location**: The Google Cloud region where Vertex AI models are available (e.g., `us-central1`) +- **Model ID**: The model identifier to use for predictions (e.g., `gemini-2.5-pro`) + +=== Optional Configuration + +- **Service Account Key**: Base64-encoded service account credentials +- **Operation**: The operation to perform (default: `generateText`). Supported operations are `generateText`, `generateChat`, `generateImage`, `generateEmbeddings`, `generateCode`, `generateMultimodal`, and `rawPredict` +- **Temperature**: Controls randomness in generation (0.0 to 1.0) +- **Max Output Tokens**: Maximum number of tokens to generate in the response +- **Top P**: Nucleus sampling parameter (0.0 to 1.0) +- **Top K**: Only sample from the top K options for each subsequent token + +=== Content Generation + +The Kamelet sends the message body as a prompt to the specified Google Vertex AI model and returns the generated content. It supports Google native models (Gemini, Imagen) as well as partner models (Claude, Llama, Mistral) through the `rawPredict` operation.
