pluginsplugin-gcpvertex-ai

MultimodalCompletion​Multimodal​Completion

Use Multimodal completion using the Google Vertex AI Gemini LLM.

See Overview of multimodal models for more information.

yaml
type: "io.kestra.plugin.gcp.vertexai.MultimodalCompletion"

Text completion using the Vertex Gemini API

yaml
id: gcp_vertexai_multimodal_completion
namespace: company.team

tasks:
  - id: multimodal_completion
    type: io.kestra.plugin.gcp.vertexai.MultimodalCompletion
    region: us-central1
    projectId: my-project
    contents:
      - content: Please tell me a joke

Multimodal completion using the Vertex Gemini API

yaml
id: gcp_vertexai_multimodal_completion
namespace: company.team

inputs:
  - id: image
    type: FILE

tasks:
  - id: multimodal_completion
    type: io.kestra.plugin.gcp.vertexai.MultimodalCompletion
    region: us-central1
    projectId: my-project
    contents:
      - content: Can you describe this image?
      - mimeType: image/jpeg
        content: "{{ inputs.image }}"
Properties
Min items 1

The chat content prompt for the model to respond to

The GCP region.

The GCP service account to impersonate.

Default gemini-pro

The identifier of the Vertex AI model to use.

Specifies which generative model (e.g., 'gemini-1.5-flash', 'gemini-1.0-pro') to use for the completion.

Default { "temperature": 0.2, "maxOutputTokens": 128, "topK": 40, "topP": 0.95 }

The model parameters.

The GCP project ID.

SubType string
Default ["https://www.googleapis.com/auth/cloud-platform"]

The GCP scopes to be used.

The GCP service account.

Default false

Whether the response has been blocked for safety reasons

The reason the generation has finished

The response safety ratings

The generated response text

The content itself, should be a string for text content or a Kestra internal storage URI for other content types.

If the content is not text, the mimeType property must be set.

Mime type of the content, use it only when the content is not text.

Whether the response has been blocked for safety reasons.

Safety category.

Safety rating probability.

Default 128
Minimum >= 1
Maximum <= 1024

Maximum number of tokens that can be generated in the response.

Specify a lower value for shorter responses and a higher value for longer responses. A token may be smaller than a word. A token is approximately four characters. 100 tokens correspond to roughly 60-80 words.

Default 0.2
Minimum >
Maximum <= 1

Temperature used for sampling during the response generation, which occurs when topP and topK are applied.

Temperature controls the degree of randomness in token selection. Lower temperatures are good for prompts that require a more deterministic and less open-ended or creative response, while higher temperatures can lead to more diverse or creative results. A temperature of 0 is deterministic: the highest probability response is always selected. For most use cases, try starting with a temperature of 0.2.

Default 40
Minimum >= 1
Maximum <= 40

Top-k changes how the model selects tokens for output.

A top-k of 1 means the selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a top-k of 3 means that the next token is selected from among the 3 most probable tokens (using temperature). For each token selection step, the top K tokens with the highest probabilities are sampled. Then tokens are further filtered based on topP with the final token selected using temperature sampling. Specify a lower value for less random responses and a higher value for more random responses.

Default 0.95
Minimum >
Maximum <= 1

Top-p changes how the model selects tokens for output.

Tokens are selected from most K (see topK parameter) probable to least until the sum of their probabilities equals the top-p value. For example, if tokens A, B, and C have a probability of 0.3, 0.2, and 0.1 and the top-p value is 0.5, then the model will select either A or B as the next token (using temperature) and doesn't consider C. The default top-p value is 0.95. Specify a lower value for less random responses and a higher value for more random responses.