[ACTION] Perplexity - add Props #18642
Description
Is there a specific app this action is for?
Perplexity: https://github.com/PipedreamHQ/pipedream/tree/master/components/perplexity
Please provide a link to the relevant API docs for the specific service / operation.
https://docs.perplexity.ai/guides/chat-completions-guide?utm_source=chatgpt.com
• Prop: messages | type: array of { role, content }
API: Chat Completions request schema (OpenAI-compatible) 
Comment: Lets you pass a full multi-turn conversation. Use this instead of single role+content.
• Prop: system | type: string
API: OpenAI-compatible system message pattern (stacked before user) 
Comment: Convenience prop. If set, it’s injected as the first messages item: {role:"system", content: system}.
• Prop: model | type: string
API: Chat Completions + model list (e.g., sonar, sonar-pro, sonar-reasoning(-pro)) 
Comment: Required; selects Perplexity model.
• Prop: temperature | type: number
API: Chat Completions params (OpenAI-compatible) 
Comment: Higher → more diverse generations.
• Prop: top_p | type: number
API: Chat Completions params (OpenAI-compatible) 
Comment: Nucleus sampling; use one of temperature or top_p to avoid odd sampling combos.
• Prop: max_tokens | type: integer
API: Chat Completions + practical note: Sonar Pro max output ≈ 8k tokens 
Comment: Caps output length.
• Prop: stream | type: boolean
API: Streaming guide (server supports token streaming) 
Comment: Server can stream; your Pipedream action can accept this flag even if you buffer and return once done.
• Prop: search_domain_filter | type: array of strings or null
API: Examples in Perplexity collections/community mention this param 
Comment: Restrict web search to certain domains (e.g., ["sec.gov","ft.com"]).
• Prop: search_recency_filter | type: string enum (common values seen: "day" | "week" | "month" | "year")
API: Example usage in Perplexity collections 
Comment: Prefer newer results; useful for newsy queries.
• Prop: top_k | type: integer
API: Example usage in Perplexity collections 
Comment: Limits number of retrieved docs/evidence considered.
• Prop: return_images | type: boolean
API: Example usage in Perplexity collections 
Comment: Include images in the response when supported by the model/content.
• Prop: return_related_questions | type: boolean
API: Example usage in Perplexity collections 
Comment: Ask the API to add “related questions” to the response payload.
• Prop: role | type: string (fallback)
API: Chat Completions schema (OpenAI-compatible) 
Comment: Back-compat with your current action if messages isn’t provided.
• Prop: content | type: string (fallback)
API: Chat Completions schema (OpenAI-compatible) 
Comment: Back-compat: single-turn prompt if messages isn’t provided.
import app from "../../perplexity.app.mjs";
export default {
key: "perplexity-chat-completions-advanced",
name: "Chat Completions (Advanced)",
description: "Generates a model's response for the given chat conversation with multi-message support and Perplexity search controls. Docs: https://docs.perplexity.ai/api-reference/chat-completions-post",
version: "1.0.0",
annotations: {
destructiveHint: false,
openWorldHint: true,
readOnlyHint: false,
},
type: "action",
props: {
app,
// --- Core ---
model: { propDefinition: [app, "model"] },
// Either provide messages/system OR fall back to role+content
messages: {
type: "string[]",
label: "Messages (JSON strings or UI collection)",
description: "Array of message objects: [{ role: 'system'|'user'|'assistant', content: '...' }, ...]. If provided, 'role' and 'content' are ignored.",
optional: true,
},
system: {
type: "string",
label: "System",
description: "Optional system prompt injected as the first message.",
optional: true,
},
role: { propDefinition: [app, "role"], optional: true },
content: { propDefinition: [app, "content"], optional: true },
// --- Generation controls (OpenAI-compatible) ---
temperature: {
type: "float",
label: "Temperature",
description: "Sampling temperature. Higher values = more diverse output.",
optional: true,
},
top_p: {
type: "float",
label: "Top-p",
description: "Nucleus sampling probability mass. Use either temperature or top_p.",
optional: true,
},
max_tokens: {
type: "integer",
label: "Max Output Tokens",
description: "Cap response length (Sonar Pro practical max output ~8k).",
optional: true,
},
stream: {
type: "boolean",
label: "Stream",
description: "Enable server-side streaming. This action will still buffer and return the final text.",
optional: true,
default: false,
},
// --- Perplexity search & response controls ---
search_domain_filter: {
type: "string[]",
label: "Search Domain Filter",
description: "Limit web search to these domains (e.g., ['sec.gov','ft.com']).",
optional: true,
},
search_recency_filter: {
type: "string",
label: "Search Recency Filter",
description: "Prefer recent sources (e.g., 'day', 'week', 'month', 'year').",
optional: true,
},
top_k: {
type: "integer",
label: "Top K",
description: "Restrict number of retrieved items considered.",
optional: true,
},
return_images: {
type: "boolean",
label: "Return Images",
description: "Ask API to include images when applicable.",
optional: true,
default: false,
},
return_related_questions: {
type: "boolean",
label: "Return Related Questions",
description: "Ask API to include related questions in response.",
optional: true,
default: false,
},
},
async run({ $ }) {
// Build messages array
let messages = [];
const provided = this.messages && this.messages.length > 0;
if (provided) {
// Accept messages as array of either objects or JSON strings
messages = this.messages.map((m) =>
typeof m === "string" ? JSON.parse(m) : m
);
} else {
if (!this.content) {
throw new Error("Either provide `messages` or `content`.");
}
// Back-compat single-turn
if (this.system) {
messages.push({ role: "system", content: this.system });
}
messages.push({
role: this.role || "user",
content: this.content,
});
}
const data = {
model: this.model,
messages,
// Generation knobs
...(this.temperature != null && { temperature: this.temperature }),
...(this.top_p != null && { top_p: this.top_p }),
...(this.max_tokens != null && { max_tokens: this.max_tokens }),
...(this.stream != null && { stream: this.stream }),
// Perplexity search controls
...(this.search_domain_filter && {
search_domain_filter: this.search_domain_filter,
}),
...(this.search_recency_filter && {
search_recency_filter: this.search_recency_filter,
}),
...(this.top_k != null && { top_k: this.top_k }),
...(this.return_images != null && { return_images: this.return_images }),
...(this.return_related_questions != null && {
return_related_questions: this.return_related_questions,
}),
};
const response = await this.app.chatCompletions({ $, data });
$.export(
"$summary",
`Perplexity ${this.model} responded${
this.stream ? " (streaming buffered)" : ""
}`
);
return response;
},
};