ChatCompletion
type: "io.kestra.plugin.perplexity.ChatCompletion"Examples
Ask a question to Perplexity
id: perplexity_chat
namespace: company.team
tasks:
- id: ask_ai
type: io.kestra.plugin.perplexity.ChatCompletion
apiKey: '{{ secret("PERPLEXITY_API_KEY") }}'
model: sonar
messages:
- type: USER
content: "What is Kestra?"
temperature: 0.7
Perplexity chat with Structured Output (JSON Schema)
id: perplexity_structured
namespace: company.name
tasks:
- id: chat_completion_structured
type: io.kestra.plugin.perplexity.ChatCompletion
apiKey: '{{ secret("PERPLEXITY_API_KEY") }}'
model: sonar
messages:
- type: USER
content: "Make a JSON todo from this casual note: schedule team check-in next week; tags: work, planning;"
jsonResponseSchema: |
{
"type": "object",
"additionalProperties": false,
"required": ["title", "done", "tags"],
"properties": {
"title": { "type": "string" },
"done": { "type": "boolean" },
"tags": { "type": "array", "items": { "type": "string" } },
"notes": { "type": "string" }
}
}
Properties
apiKey*Requiredstring
API Key
The Perplexity API key used for authentication.
messages*Requiredarray
Messages
List of chat messages in conversational order.
io.kestra.plugin.perplexity.ChatCompletion-ChatMessage
SYSTEMASSISTANTUSERmodel*Requiredstring
Model
The Perplexity model to use (e.g., sonar, sonar-pro).
frequencyPenaltynumberstring
0.0Frequency Penalty
Decreases likelihood of repetition based on prior frequency. Valued between 0 and 2.0.
jsonResponseSchemastring
JSON Response Schema
JSON schema (as string) to force a custom Structured Output. If provided, the request will include response_format = { type: "json_schema", json_schema: { schema:
maxTokensintegerstring
The maximum number of tokens to generate.
presencePenaltynumberstring
0.0Presence Penalty
Positive values increase the likelihood of discussing new topics. Valued between 0 and 2.0.
streambooleanstring
falseStream
Determines whether to stream the response incrementally.
temperaturenumberstring
0.2Temperature
The amount of randomness in the response, valued between 0 and 2.
topKintegerstring
0Top K
The number of tokens to keep for top-k filtering.
topPnumberstring
0.9Top P
The nucleus sampling threshold, valued between 0 and 1.
Outputs
outputTextstring
The generated text output
rawResponsestring
Full, raw response from the API.
