Chat Completions (Advanced) with Perplexity API

Pipedream makes it easy to connect APIs for Perplexity and 2,800+ other apps remarkably fast.

Trigger workflow on

HTTP requests, schedules and app events

Next, do this

Chat Completions (Advanced) with the Perplexity API

No credit card required

▶

Watch us build a workflow

8 min

Watch now ➜

Trusted by 1,000,000+ developers from startups to Fortune 500 companies

Developers ♥ Pipedream

Getting Started#

Create a workflow to Chat Completions (Advanced) with the Perplexity API. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Configure the Chat Completions (Advanced) action
1. Connect your Perplexity account
2. Select a Model
3. Optional- Configure Messages (JSON strings or UI collection)
4. Optional- Configure System
5. Optional- Select a Role
6. Optional- Configure Content
7. Optional- Configure Temperature
8. Optional- Configure Top-p
9. Optional- Configure Max Output Tokens
10. Optional- Configure Stream
11. Optional- Configure Search Domain Filter
12. Optional- Configure Search Recency Filter
13. Optional- Configure Top K
14. Optional- Configure Return Images
15. Optional- Configure Return Related Questions
Select a trigger to run your workflow on HTTP requests, schedules or app events
Deploy the workflow
Send a test event to validate your setup
Turn on the trigger

Integrations#

Chat Completions (Advanced) with Perplexity API on New Requests (Payload Only) from HTTP / Webhook API

HTTP / Webhook + Perplexity

Try it

Chat Completions (Advanced) with Perplexity API on New Submission from Typeform API

Typeform + Perplexity

Try it

Chat Completions (Advanced) with Perplexity API on New Submission (Instant) from Jotform API

Jotform + Perplexity

Try it

Chat Completions (Advanced) with Perplexity API on New Scheduled Tasks from Pipedream API

Pipedream + Perplexity

Try it

Chat Completions (Advanced) with Perplexity API on New Download Counts from npm API

npm + Perplexity

Try it

Details#

This is a pre-built, source-available component from Pipedream's GitHub repo. The component is developed by Pipedream and the community, and verified and maintained by Pipedream.

To contribute an update to an existing component or create a new component, create a PR on GitHub. If you're new to Pipedream component development, you can start with quickstarts for trigger span and action development, and then review the component API reference.

Chat Completions (Advanced) on Perplexity

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:0.0.1

Key:perplexity-chat-completions-advanced

View on GitHub

Code#

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: "0.0.1",
  annotations: {
    destructiveHint: false,
    openWorldHint: true,
    readOnlyHint: false,
  },
  type: "action",
  props: {
    app,
    model: {
      propDefinition: [
        app,
        "model",
      ],
    },
    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,
    },
    temperature: {
      type: "string",
      label: "Temperature",
      description: "Sampling temperature. Higher values = more diverse output.",
      optional: true,
    },
    topP: {
      type: "string",
      label: "Top-p",
      description: "Nucleus sampling probability mass. Use either temperature or top_p.",
      optional: true,
    },
    maxTokens: {
      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,
    },
    searchDomainFilter: {
      type: "string[]",
      label: "Search Domain Filter",
      description: "Limit web search to these domains (e.g., ['sec.gov','ft.com'])",
      optional: true,
    },
    searchRecencyFilter: {
      type: "string",
      label: "Search Recency Filter",
      description: "Prefer recent sources (e.g., 'day', 'week', 'month', 'year')",
      optional: true,
    },
    topK: {
      type: "integer",
      label: "Top K",
      description: "Restrict number of retrieved items considered",
      optional: true,
    },
    returnImages: {
      type: "boolean",
      label: "Return Images",
      description: "Ask API to include images when applicable",
      optional: true,
      default: false,
    },
    returnRelatedQuestions: {
      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.topP != null && {
        top_p: +this.topP,
      }),
      ...(this.maxTokens != null && {
        max_tokens: this.maxTokens,
      }),
      ...(this.stream != null && {
        stream: this.stream,
      }),
      // Perplexity search controls
      ...(this.searchDomainFilter && {
        search_domain_filter: this.searchDomainFilter,
      }),
      ...(this.searchRecencyFilter && {
        search_recency_filter: this.searchRecencyFilter,
      }),
      ...(this.topK != null && {
        top_k: this.topK,
      }),
      ...(this.returnImages != null && {
        return_images: this.returnImages,
      }),
      ...(this.returnRelatedQuestions != null && {
        return_related_questions: this.returnRelatedQuestions,
      }),
    };

    const response = await this.app.chatCompletions({
      $,
      data,
    });

    $.export(
      "$summary",
      `Perplexity ${this.model} responded${
        this.stream
          ? " (streaming buffered)"
          : ""
      }`,
    );

    return response;
  },
};

Configuration#

This component may be configured based on the props defined in the component code. Pipedream automatically prompts for input values in the UI and CLI.

Label	Prop	Type	Description
Perplexity	`app`	`app`	This component uses the Perplexity app.
Model	`model`	`string`	Select a value from the drop down menu:`sonarsonar-prosonar-reasoningsonar-reasoning-pro`
Messages (JSON strings or UI collection)	`messages`	`string[]`	Array of message objects: [{ role: 'system'\|'user'\|'assistant', content: '...' }, ...]. If provided, 'role' and 'content' are ignored.
System	`system`	`string`	Optional system prompt injected as the first message
Role	`role`	`string`	Select a value from the drop down menu:`systemuserassistant`
Content	`content`	`string`	The contents of the message in this turn of conversation
Temperature	`temperature`	`string`	Sampling temperature. Higher values = more diverse output.
Top-p	`topP`	`string`	Nucleus sampling probability mass. Use either temperature or top_p.
Max Output Tokens	`maxTokens`	`integer`	Cap response length (Sonar Pro practical max output ~8k).
Stream	`stream`	`boolean`	Enable server-side streaming. This action will still buffer and return the final text.
Search Domain Filter	`searchDomainFilter`	`string[]`	Limit web search to these domains (e.g., ['sec.gov','ft.com'])
Search Recency Filter	`searchRecencyFilter`	`string`	Prefer recent sources (e.g., 'day', 'week', 'month', 'year')
Top K	`topK`	`integer`	Restrict number of retrieved items considered
Return Images	`returnImages`	`boolean`	Ask API to include images when applicable
Return Related Questions	`returnRelatedQuestions`	`boolean`	Ask API to include related questions in response