Perplexity API Webhook

The workflow JSON

Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →

{
  "nodes": [
    {
      "parameters": {
        "httpMethod": "POST",
        "path": "chat",
        "responseMode": "responseNode",
        "options": {}
      },
      "type": "n8n-nodes-base.webhook",
      "typeVersion": 2.1,
      "position": [
        0,
        0
      ],
      "id": "2cfe661b-fdd4-4026-a082-867b2a1ab328",
      "name": "Incoming_request"
    },
    {
      "parameters": {
        "jsCode": "const input = $input.item.json;\nconst messages = [];\n\n// System message\nmessages.push({\n  role: \"system\",\n  content: `You are an assistant that extracts stock or crypto tickers if they exist.\n\nReturn VALID JSON ONLY in this format:\n{\n  \"text\": string,\n  \"ticker\": string | null\n}\n\nRules:\n- Use standard tickers (AAPL, TSLA, BTCUSDT, SPX)\n- If no ticker is clearly mentioned or implied, set ticker to null\n- Do not invent tickers\n- No markdown code blocks\n- No backticks\n- Raw JSON only`\n});\n\n// Add conversation history if provided\nif (Array.isArray(input.history)) {\n  for (const msg of input.history) {\n    if (msg.role && msg.content) {\n      messages.push({ role: msg.role, content: msg.content });\n    }\n  }\n}\n\n// Add current user message\nconst userMessage = input.message || input.body?.message || \"\";\nif (userMessage.trim()) {\n  messages.push({ role: \"user\", content: userMessage });\n}\n\nreturn { \n  session_id: input.session_id || input.body?.session_id || \"default-session\", \n  messages \n};"
      },
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        240,
        0
      ],
      "id": "prepare-prompt",
      "name": "Prepare Prompt"
    },
    {
      "parameters": {
        "method": "POST",
        "url": "https://api.perplexity.ai/chat/completions",
        "authentication": "predefinedCredentialType",
        "nodeCredentialType": "httpBearerAuth",
        "sendBody": true,
        "specifyBody": "json",
        "jsonBody": "={{ JSON.stringify({\n  model: \"sonar-pro\",\n  messages: $json.messages,\n  temperature: 0\n}) }}",
        "options": {
          "timeout": 30000
        }
      },
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.3,
      "position": [
        480,
        0
      ],
      "id": "perplexity-api",
      "name": "Perplexity API",
      "credentials": {
        "httpBearerAuth": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "jsCode": "const response = $input.item.json;\n\n// Extract content from Perplexity response\nlet content = response.choices?.[0]?.message?.content || \"\";\n\n// Remove markdown code blocks and backticks\ncontent = content\n  .replace(/```json\\s*/gi, '')\n  .replace(/```\\s*/g, '')\n  .replace(/^`+|`+$/g, '')\n  .trim();\n\n// Try to extract JSON if there's extra text\nconst jsonMatch = content.match(/\\{[\\s\\S]*\\}/);\nif (jsonMatch) {\n  content = jsonMatch[0];\n}\n\n// Parse JSON\nlet parsed;\ntry {\n  parsed = JSON.parse(content);\n} catch (error) {\n  // One more attempt with line breaks removed\n  content = content.replace(/[\\r\\n]+/g, ' ');\n  try {\n    parsed = JSON.parse(content);\n  } catch (e) {\n    throw new Error(`Failed to parse JSON: ${content}`);\n  }\n}\n\n// Get session_id from previous node\nconst sessionId = $('Prepare Prompt').item.json.session_id;\n\n// Return clean result\nreturn {\n  session_id: sessionId,\n  text: parsed.text || \"\",\n  ticker: parsed.ticker || null\n};"
      },
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        720,
        0
      ],
      "id": "parse-response",
      "name": "Parse Response"
    },
    {
      "parameters": {
        "options": {}
      },
      "type": "n8n-nodes-base.respondToWebhook",
      "typeVersion": 1.5,
      "position": [
        960,
        0
      ],
      "id": "19950702-5d61-46e0-a30a-a60fa1249c0d",
      "name": "Respond to Webhook"
    }
  ],
  "connections": {
    "Incoming_request": {
      "main": [
        [
          {
            "node": "Prepare Prompt",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Prepare Prompt": {
      "main": [
        [
          {
            "node": "Perplexity API",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Perplexity API": {
      "main": [
        [
          {
            "node": "Parse Response",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Parse Response": {
      "main": [
        [
          {
            "node": "Respond to Webhook",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "meta": {
    "templateCredsSetupCompleted": true
  }
}

Credentials you'll need

Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.

• httpBearerAuth

About this workflow

Perplexity Node. Uses httpRequest. Webhook trigger; 5 nodes.

Source: https://github.com/aryan4184/CandleCodexAI/blob/c84acbe30c5c71278df6fbfa534e0ab19563b618/n8n/perplexity_node.json — original creator credit. Request a take-down →

More Web Scraping workflows → · Browse all categories →

Related workflows

Workflows that share integrations, category, or trigger type with this one. All free to copy and import.