G a Topic Distiller

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 →

{
  "_meta": {
    "notes": "All credentials replaced with ${ENV_VAR} placeholders. Configure via Doppler or .env. Replace credential IDs with your own n8n credential IDs after import."
  },
  "name": "G_A_topic_distiller",
  "nodes": [
    {
      "parameters": {
        "rule": {
          "interval": [
            {
              "field": "cronExpression",
              "expression": "0 6 * * *"
            }
          ]
        },
        "triggerAtStartup": false,
        "timezone": "Europe/Berlin"
      },
      "id": "trigger-cron-daily",
      "name": "Daily 06:00 Berlin",
      "type": "n8n-nodes-base.scheduleTrigger",
      "typeVersion": 1.1,
      "position": [
        240,
        300
      ]
    },
    {
      "parameters": {
        "method": "GET",
        "url": "=${SUPABASE_GENESIS_URL}/rest/v1/trend_signals",
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth",
        "sendQuery": true,
        "queryParameters": {
          "parameters": [
            {
              "name": "select",
              "value": "id,source,source_id,title,url,score,captured_at"
            },
            {
              "name": "processed",
              "value": "eq.false"
            },
            {
              "name": "captured_at",
              "value": "=gt.{{ $now.minus({hours: 24}).toISO() }}"
            },
            {
              "name": "order",
              "value": "score.desc.nullslast"
            },
            {
              "name": "limit",
              "value": "100"
            }
          ]
        },
        "options": {
          "timeout": 15000
        }
      },
      "id": "fetch-signals",
      "name": "Fetch last-24h signals",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        460,
        300
      ],
      "credentials": {
        "httpHeaderAuth": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "jsCode": "// Build digest for LLM\nconst signals = $input.all().map(i => i.json).flat();\nif (!signals.length) { return []; }\nconst digest = signals.slice(0, 80).map((s, i) => `${i+1}. [${s.source}|${s.score ?? '-'}] ${s.title} :: ${s.url}`).join('\\n');\nconst ids = signals.map(s => s.id);\nreturn [{ json: { digest, ids, n: signals.length } }];"
      },
      "id": "build-digest",
      "name": "Build LLM digest",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        680,
        300
      ]
    },
    {
      "parameters": {
        "method": "POST",
        "url": "https://api.openai.com/v1/chat/completions",
        "authentication": "predefinedCredentialType",
        "nodeCredentialType": "openAiApi",
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
            {
              "name": "Content-Type",
              "value": "application/json"
            }
          ]
        },
        "sendBody": true,
        "specifyBody": "json",
        "jsonBody": "={{ { model: 'gpt-4.1-2025-04-14', response_format: { type: 'json_object' }, temperature: 0.4, messages: [ { role: 'system', content: 'You are senior editor of an AI blog. Input: list of trend signals (GitHub + HN). Task: pick 3-5 topics worth standalone articles for an AI architect audience. Drop clones (N libraries doing the same \u2192 one topic). Each topic \u2014 with clear pain point for the reader. Respond strict JSON: { \"topics\": [ { \"title_ru\": \"...\", \"title_en\": \"...\", \"slug_en\": \"kebab-case-short\", \"topic_category\": \"ai-agents|llm-tools|infra|products|research|other\", \"hype_score\": 0-100, \"rationale\": \"why write this \u2014 1-2 sentences\" } ] }' }, { role: 'user', content: 'Signals from last 24h:\\n' + $json.digest + '\\n\\nGenerate 3-5 topics.' } ] } }}",
        "options": {
          "timeout": 60000
        }
      },
      "id": "openai-distill",
      "name": "GPT-4.1 distill topics",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        900,
        300
      ],
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "jsCode": "// Parse GPT JSON, emit one item per topic, attach source_signal_ids\nconst resp = $input.first().json;\nconst content = resp.choices?.[0]?.message?.content || '{}';\nlet parsed; try { parsed = JSON.parse(content); } catch(e) { parsed = { topics: [] }; }\nconst topics = Array.isArray(parsed.topics) ? parsed.topics : [];\nconst ids = $('Build LLM digest').first().json.ids;\nreturn topics.map(t => {\n  const rawSlug = (t.slug_en || t.title_en || '').toLowerCase().replace(/[^a-z0-9-]/g,'-').replace(/-+/g,'-').replace(/^-|-$/g,'').slice(0, 80);\n  const slug = rawSlug || null;\n  return { json: {\n    source: 'distilled',\n    title_raw: t.title_en || t.title_ru || '',\n    title_ru: t.title_ru || null,\n    title_en: t.title_en || null,\n    slug_en: slug,\n    topic_category: t.topic_category || 'other',\n    hype_score: Number(t.hype_score) || 0,\n    priority: 50,\n    status: 'queued',\n    raw_signals: ids,\n    notes: t.rationale || null\n  }};\n});"
      },
      "id": "parse-topics",
      "name": "Parse topics",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        1120,
        300
      ]
    },
    {
      "parameters": {
        "method": "POST",
        "url": "=${SUPABASE_GENESIS_URL}/rest/v1/topics?on_conflict=slug_en",
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth",
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
            {
              "name": "Content-Type",
              "value": "application/json"
            },
            {
              "name": "Prefer",
              "value": "resolution=ignore-duplicates,return=minimal"
            }
          ]
        },
        "sendBody": true,
        "specifyBody": "json",
        "jsonBody": "={{ $json }}",
        "options": {
          "timeout": 15000
        }
      },
      "id": "supabase-upsert-topic",
      "name": "Supabase: upsert topic",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        1340,
        300
      ],
      "credentials": {
        "httpHeaderAuth": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "method": "PATCH",
        "url": "=${SUPABASE_GENESIS_URL}/rest/v1/trend_signals?id=in.({{ ($('Build LLM digest').first().json.ids || []).join(',') }})",
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth",
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
            {
              "name": "Content-Type",
              "value": "application/json"
            },
            {
              "name": "Prefer",
              "value": "return=minimal"
            }
          ]
        },
        "sendBody": true,
        "specifyBody": "json",
        "jsonBody": "={{ { processed: true } }}",
        "options": {
          "timeout": 15000
        }
      },
      "id": "mark-processed",
      "name": "Mark signals processed",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        1560,
        300
      ],
      "credentials": {
        "httpHeaderAuth": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "jsCode": "const n_topics = $('Parse topics').all().length;\nconst n_signals = ($('Build LLM digest').first().json.ids || []).length;\nreturn [{ json: { run_at: new Date().toISOString(), signals_processed: n_signals, topics_generated: n_topics } }];"
      },
      "id": "aggregate-run",
      "name": "Aggregate run report",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        1780,
        300
      ]
    }
  ],
  "connections": {
    "Daily 06:00 Berlin": {
      "main": [
        [
          {
            "node": "Fetch last-24h signals",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Fetch last-24h signals": {
      "main": [
        [
          {
            "node": "Build LLM digest",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Build LLM digest": {
      "main": [
        [
          {
            "node": "GPT-4.1 distill topics",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "GPT-4.1 distill topics": {
      "main": [
        [
          {
            "node": "Parse topics",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Parse topics": {
      "main": [
        [
          {
            "node": "Supabase: upsert topic",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Supabase: upsert topic": {
      "main": [
        [
          {
            "node": "Mark signals processed",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Mark signals processed": {
      "main": [
        [
          {
            "node": "Aggregate run report",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "settings": {
    "executionOrder": "v1",
    "saveManualExecutions": true,
    "saveExecutionProgress": true,
    "timezone": "Europe/Berlin"
  }
}

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.

• httpHeaderAuth
• openAiApi

About this workflow

G_A_topic_distiller. Uses httpRequest. Scheduled trigger; 8 nodes.

Source: https://github.com/DenisShokhirev041279/genesis-content-os/blob/main/workflows/G_A_topic_distiller.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.