Gemini ChatCompletion

Gemini ChatCompletion

Certified

Run chat turns with a Gemini model

Streams an ordered list of chat messages to the Gemini chat API and returns the generated replies. Token metrics are emitted; use roles SYSTEM/USER/AI to guide behavior.

yaml
type: io.kestra.plugin.gemini.ChatCompletion

Chat completion using the Gemini Client.

yaml
id: gemini_chat_completion
namespace: company.team

tasks:
  - id: chat_completion
    type: io.kestra.plugin.gemini.ChatCompletion
    apiKey: "{{ secret('GEMINI_API_KEY') }}"
    model: "gemini-2.5-flash"
    messages:
      - type: SYSTEM
        content: You are a helpful assistant, answer concisely, avoid overly casual language or unnecessary verbosity.
      - type: USER
        content: "What is the capital of France?"
Properties

Gemini API key

Secret used for direct Gemini API calls; render from a secure variable.

Chat messages

Ordered conversation history; renderable content per message. Use role SYSTEM/USER/AI to match Gemini expectations.

Definitions
contentstring
typestring
Possible Values
SYSTEMAIUSER

Generative model

Gemini model identifier to call (e.g., gemini-2.5-flash, gemini-1.5-pro). Must support the requested input type.

Reference (ref) of the pluginDefaults to apply to this task.

List of text predictions made by the model

Definitions
citationMetadata
contentstring
safetyRatingsarray

The number of candidate tokens generated by the Gemini model.

The number of tokens used in the input prompt.

The total number of tokens processed by the Gemini model (prompt + generated).

More Plugins in this Category

Weaviate
Weaviate

Tasks that manage and query vectors in Weaviate.

DataAI

4 tasks

2 blueprints

Timefold
Timefold

Timefold plugin for Kestra

DataAI

2 tasks