Gemini ChatCompletion
CertifiedRun chat turns with a Gemini model
Gemini ChatCompletion
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.
type: io.kestra.plugin.gemini.ChatCompletionExamples
Chat completion using the Gemini Client.
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
apiKey *string
Gemini API key
Secret used for direct Gemini API calls; render from a secure variable.
messages *array
Chat messages
Ordered conversation history; renderable content per message. Use role SYSTEM/USER/AI to match Gemini expectations.
io.kestra.plugin.gemini.ChatCompletion-ChatMessage
SYSTEMAIUSERmodel *string
Generative model
Gemini model identifier to call (e.g., gemini-2.5-flash, gemini-1.5-pro). Must support the requested input type.
assets
Assets this task consumes as inputs or produces as outputs, for lineage tracking and the asset graph (Enterprise Edition). A flow declaring this property on a task is rejected in the open-source edition.
io.kestra.core.models.assets.AssetsDeclaration
IGNOREFAILWARNAsset failure behavior
Behavior applied to the task state when a declared asset fails to render, emit, or be persisted (e.g. a lock conflict): FAIL escalates it to FAILED, WARN (default) warns it if it would otherwise succeed, IGNORE leaves the state untouched.
Whether to auto-register assets referenced dynamically at runtime that are not statically declared in inputs or outputs.
The assets consumed as inputs.
io.kestra.core.models.assets.AssetIdentifier
1The assets produced as outputs.
io.kestra.plugin.ee.assets.Dataset
1150{}1150io.kestra.plugin.ee.assets.File
1150{}1150io.kestra.plugin.ee.assets.Table
1150{}1150io.kestra.plugin.ee.assets.VM
1150{}1150io.kestra.core.models.assets.External
1150{}1150io.kestra.core.models.assets.Custom
11501Custom asset type
{}1150Outputs
predictions array
List of text predictions made by the model
io.kestra.plugin.gemini.AbstractGemini-Prediction
com.google.genai.types.CitationMetadata
com.google.genai.types.SafetyRating
Metrics
candidate.token.count counter
The number of candidate tokens generated by the Gemini model.
prompt.token.count counter
The number of tokens used in the input prompt.
total.token.count counter
The total number of tokens processed by the Gemini model (prompt + generated).
