{
  "workflow": {
    "id": 3302,
    "name": "Transform press releases (PDF & Word) into polished articles with Gmail & OpenAI",
    "views": 3074,
    "recentViews": 0,
    "totalViews": 3074,
    "createdAt": "2025-03-24T08:01:17.609Z",
    "description": "This n8n workflow automates the transformation of press releases into polished articles. It converts the content of an email and its attachments (PDF or Word documents) into an AI-written article/blog post. \n\n## What does it do?\nThis workflow assists editors and journalists in managing incoming press-releases from governments, companies, NGOs, or individuals. The result is a draft article that can easily be reviewed by the editor, who receives it in a reply email containing both the original input and the output, plus an AI-generated self-assessment. This self-assessment represents an additional feedback loop where the AI compares the input with the output to evaluate the quality and accuracy of its transformation.\n\n## How does it work?\nTriggered by incoming emails in Google, it first filters attachments, retaining only Word and PDF files while removing other formats like JPGs. The workflow then follows one of three paths:\n\n    - If no attachments remain, it processes the inline email message directly.\n    - For PDF attachments, it uses an extractor to obtain the document content.\n    - For Word attachments, it extracts the text content by a http request.\n\nIn each case, the extracted content is then passed to an AI agent that converts the press release into a well-structured article according to predefined prompts. A separate AI evaluation step provides a self-assessment by comparing the output with the original input to ensure quality and accuracy. Finally, the workflow generates a reply email to the sender containing three components: the original input, the AI-generated article, and the self-assessment. This streamlined process helps editors and journalists efficiently manage incoming press releases, delivering draft articles that require minimal additional editing.\"  \n\n## How to set it up\n### 1. Configure Gmail Connection: \n- Create or use an existing Gmail address\n- Connect it through the n8n credentials manager\n- Configure polling frequency according to your needs\n- Set the trigger event to \"Message Received\"\n        Optional: Filter incoming emails by specifying authorized senders\n- Enable the \"Download Attachments\" option\n\n### 2. Set Up AI Integration:\n- Create an OpenAI account if you don't have one\n- Create a new AI assistant or use an existing one\n- Customize the assistant with specific instructions, style guidelines, or response templates\n- Configure your API credentials in n8n to enable the connection\n\n### 3. Configure Google Drive Integration:\n- Connect your Google Drive credentials in n8n\n- Set the operation mode to \"Upload\"\n- Configure the input data field name as \"data\"\n-Set the file naming format to dynamic: {{ $json.fileName }}\n\n### 4. Configure HTTP Request Node:\n- Set request method to \"POST\"\n- Enter the appropriate Google API endpoint URL\n- Include all required authorization headers\n- Structure the request body according to API specifications\n- Ensure proper error handling for API responses\n\n### 5. Configure HTTP Request Node 2:\n\n- Set request method to \"GET\"\n- Enter the appropriate Google API endpoint URL\n- Include all required authorization headers\n- Configure query parameters as needed\n- Implement response validation and error handling\n\n\n\n### 6.  Configure Self-Assessment Node:\n\n- Set operation to \"Message a Model\"\n- Select an appropriate AI model (e.g., GPT-4, Claude)\n- Configure the following prompt in the Message field:\n\n\n\nPlease analyze and compare the following input and output content:\n\n(for example)\n\nOriginal Input:\n{{ $('HTTP Request3').item.json.data }}\n{{ $('Gmail Trigger').item.json.text }}\n\nGenerated Output:\n{{ $json.output }}\n\nProvide a detailed self-assessment that evaluates:\n1. Content accuracy and completeness\n2. Structure and readability improvements\n3. Tone and style appropriateness\n4. Any information that may have been omitted or misrepresented\n5. Overall quality of the transformation\n\n### 7. Configure Reply Email Node:\n\n- Set operation to \"Send\" and select your Gmail account\n- Configure the \"To\" field to respond to the original sender: {{ $('Gmail Trigger').item.json.from }}\n- Set an appropriate subject line: RE: {{ $('Gmail Trigger').item.json.subject }}\n- Structure the email body with clear sections using the following template:\n\nhandlebars\n\n***EDITED ARTICLE***   \n\n{{ $('AI Article Writer 2').item.json.output }}\n\n***SELF-ASSESSMENT***\nRating: 1 (poor) to 5 (excellent)\n{{ $json.message.content }}\n\n***ORIGINAL MESSAGE***\n\n{{ $('Gmail Trigger').item.json.text }}\n\n***ATTACHMENT CONTENT***\n\n{{ $('HTTP Request3').item.json.data }}\n\n    Note: Adjust the template fields according to the input source (PDF, Word document, or inline message). For inline messages, you may not need the \"ATTACHMENT CONTENT\" section.\n",
    "workflow": {
      "id": "l1wMIoms9BgoA2lV",
      "meta": {
        "instanceId": "05b0588df0f58c91cb668a930710fae1c12db867675e52c5c2912a7beee5342b",
        "templateCredsSetupCompleted": true
      },
      "name": "\"E-Mail to article/blog post\" - converter",
      "tags": [],
      "nodes": [
        {
          "id": "e24d8d7a-88b2-4ee2-9c38-4b6f4a88102c",
          "name": "Gmail Trigger",
          "type": "n8n-nodes-base.gmailTrigger",
          "position": [
            -100,
            360
          ],
          "parameters": {
            "simple": false,
            "filters": {
              "sender": "*@somedia.ch"
            },
            "options": {
              "downloadAttachments": true,
              "dataPropertyAttachmentsPrefixName": "attachment_"
            },
            "pollTimes": {
              "item": [
                {
                  "mode": "everyX",
                  "unit": "minutes",
                  "value": 1
                }
              ]
            }
          },
          "credentials": {
            "gmailOAuth2": {
              "id": "credential-id",
              "name": "gmailOAuth2 Credential"
            }
          },
          "notesInFlow": false,
          "typeVersion": 1.2
        },
        {
          "id": "b265f364-b246-4244-ab77-9812b90817e1",
          "name": "Extrahiere aus PDF1",
          "type": "n8n-nodes-base.extractFromFile",
          "position": [
            1120,
            -80
          ],
          "parameters": {
            "options": {},
            "operation": "pdf"
          },
          "typeVersion": 1
        },
        {
          "id": "2ff7ca6c-7ba6-4526-94fc-cb82b052648a",
          "name": "HTTP Request2",
          "type": "n8n-nodes-base.httpRequest",
          "position": [
            1260,
            280
          ],
          "parameters": {
            "url": "=https://www.googleapis.com/drive/v3/files/{{$json[\"id\"]}}/copy\n",
            "method": "POST",
            "options": {},
            "jsonBody": "{\n  \"mimeType\": \"application/vnd.google-apps.document\"\n}\n",
            "sendBody": true,
            "jsonHeaders": "{\n  \"Authorization\": \"Bearer {{$credentials.googleDriveOAuth2.access_token}}\",\n  \"Content-Type\": \"application/json\"\n}\n",
            "sendHeaders": true,
            "specifyBody": "json",
            "authentication": "predefinedCredentialType",
            "specifyHeaders": "json",
            "nodeCredentialType": "googleDocsOAuth2Api"
          },
          "credentials": {
            "oAuth2Api": {
              "id": "credential-id",
              "name": "oAuth2Api Credential"
            },
            "googleDocsOAuth2Api": {
              "id": "credential-id",
              "name": "googleDocsOAuth2Api Credential"
            }
          },
          "typeVersion": 4.2
        },
        {
          "id": "1889bbb3-287b-4105-aea9-1b1f31e1bc1b",
          "name": "HTTP Request3",
          "type": "n8n-nodes-base.httpRequest",
          "position": [
            1480,
            280
          ],
          "parameters": {
            "url": "=https://www.googleapis.com/drive/v3/files/{{$json[\"id\"]}}/export?mimeType=text/plain\n",
            "options": {
              "response": {
                "response": {
                  "responseFormat": "text"
                }
              }
            },
            "jsonHeaders": "{\n  \"Authorization\": \"Bearer {{$credentials.googleDriveOAuth2.access_token}}\"\n}\n",
            "sendHeaders": true,
            "authentication": "predefinedCredentialType",
            "specifyHeaders": "json",
            "nodeCredentialType": "googleDocsOAuth2Api"
          },
          "credentials": {
            "oAuth2Api": {
              "id": "credential-id",
              "name": "oAuth2Api Credential"
            },
            "googleDocsOAuth2Api": {
              "id": "credential-id",
              "name": "googleDocsOAuth2Api Credential"
            }
          },
          "typeVersion": 4.2
        },
        {
          "id": "f6f0d96f-f1c8-4d6a-88c5-bfe86ff6a359",
          "name": "Anthropic Chat Model",
          "type": "@n8n/n8n-nodes-langchain.lmChatAnthropic",
          "position": [
            660,
            740
          ],
          "parameters": {
            "model": "claude-3-5-sonnet-20241022",
            "options": {}
          },
          "credentials": {
            "anthropicApi": {
              "id": "credential-id",
              "name": "anthropicApi Credential"
            }
          },
          "typeVersion": 1.2
        },
        {
          "id": "0f3fee05-3444-4046-96f6-b0978eb9d16e",
          "name": "Anthropic Chat Model1",
          "type": "@n8n/n8n-nodes-langchain.lmChatAnthropic",
          "position": [
            1780,
            500
          ],
          "parameters": {
            "model": "claude-3-5-sonnet-20241022",
            "options": {}
          },
          "credentials": {
            "anthropicApi": {
              "id": "credential-id",
              "name": "anthropicApi Credential"
            }
          },
          "typeVersion": 1.2
        },
        {
          "id": "34321fc9-ecaa-4f4c-a01c-b8cf0cd3df50",
          "name": "Anthropic Chat Model2",
          "type": "@n8n/n8n-nodes-langchain.lmChatAnthropic",
          "position": [
            1400,
            80
          ],
          "parameters": {
            "model": "claude-3-5-sonnet-20241022",
            "options": {}
          },
          "credentials": {
            "anthropicApi": {
              "id": "credential-id",
              "name": "anthropicApi Credential"
            }
          },
          "typeVersion": 1.2
        },
        {
          "id": "86315ae8-f456-4e06-a281-b04f75886232",
          "name": "Code: delete all but pdf and word",
          "type": "n8n-nodes-base.code",
          "position": [
            140,
            360
          ],
          "parameters": {
            "jsCode": "const allItems = $input.all();\nlet data = [];\nallItems.forEach(item => {\n  const binaryData = item.binary;\n  if (binaryData) {\n    Object.keys(binaryData).forEach(key => {\n      // MIME-Types für PDF und Word\n      const allowedMimeTypes = [\n        'application/pdf',\n        'application/msword',\n        'application/vnd.openxmlformats-officedocument.wordprocessingml.document'\n      ];\n      \n      if (allowedMimeTypes.includes(binaryData[key]?.mimeType)) {\n        data.push({\n          binary: { data: binaryData[key] },\n          json: {\n            fileName: binaryData[key].fileName,\n            mimeType: binaryData[key].mimeType\n          }\n        });\n      }\n    });\n  }\n});\nreturn data;"
          },
          "executeOnce": false,
          "typeVersion": 2,
          "alwaysOutputData": true
        },
        {
          "id": "6b95290e-4304-4187-8294-15f32e3227c9",
          "name": "has attachment?",
          "type": "n8n-nodes-base.if",
          "position": [
            380,
            360
          ],
          "parameters": {
            "options": {},
            "conditions": {
              "options": {
                "version": 2,
                "leftValue": "",
                "caseSensitive": true,
                "typeValidation": "loose"
              },
              "combinator": "or",
              "conditions": [
                {
                  "id": "0cd4c70c-9562-486e-95bd-497ba4816aac",
                  "operator": {
                    "type": "number",
                    "operation": "gt"
                  },
                  "leftValue": "={{ Object.keys($binary).length }}\n",
                  "rightValue": 0
                }
              ]
            },
            "looseTypeValidation": true
          },
          "typeVersion": 2.2
        },
        {
          "id": "59688c51-64aa-47bb-80e3-33185e358122",
          "name": "PDF or WORD?",
          "type": "n8n-nodes-base.if",
          "position": [
            680,
            240
          ],
          "parameters": {
            "options": {},
            "conditions": {
              "options": {
                "version": 2,
                "leftValue": "",
                "caseSensitive": true,
                "typeValidation": "loose"
              },
              "combinator": "or",
              "conditions": [
                {
                  "id": "0cd4c70c-9562-486e-95bd-497ba4816aac",
                  "operator": {
                    "type": "string",
                    "operation": "contains"
                  },
                  "leftValue": "={{ $json.mimeType }}",
                  "rightValue": "pdf"
                }
              ]
            },
            "looseTypeValidation": true
          },
          "typeVersion": 2.2
        },
        {
          "id": "8d767385-4e77-434f-8c47-1e5bbaae807f",
          "name": "OpenAI self assesment",
          "type": "@n8n/n8n-nodes-langchain.openAi",
          "position": [
            1020,
            520
          ],
          "parameters": {
            "modelId": {
              "__rl": true,
              "mode": "list",
              "value": "gpt-4o-mini",
              "cachedResultName": "GPT-4O-MINI"
            },
            "options": {},
            "messages": {
              "values": [
                {
                  "content": "=Deine Aufgabe ist es, den gegebenen Input-Text mit dem Output-Artikel zu vergleichen.\nBewerte, ob alle wesentlichen Informationen aus dem Input-Text im Output-Artikel korrekt enthalten sind, ohne dass neue, nicht im Input vorhandene Informationen hinzugefügt wurden.\nVorgehensweise:\n\n    Vollständigkeit prüfen: Sind alle relevanten Informationen aus dem Input im Output enthalten?\n    Genauigkeit bewerten: Wurde der Inhalt korrekt wiedergegeben, ohne Änderungen oder Auslassungen?\n    Zusätzliche Informationen erkennen: Wurden Inhalte hinzugefügt, die nicht im Input vorhanden sind? Falls ja, welche?\n\nAusgabe:\n\n    Bewertung (1 bis 5):\n        1 = Sehr schlecht (viele fehlende oder falsche Informationen, erhebliche neue Inhalte)\n        2 = Unzureichend (mehrere wichtige Auslassungen oder falsche Inhalte)\n        3 = Mittelmäßig (einige kleinere Fehler oder Ergänzungen)\n        4 = Gut (fast alles korrekt, minimale Abweichungen)\n        5 = Sehr gut (vollständige, korrekte Übereinstimmung)\n    Textuelle Begründung: Eine kurze Analyse, warum diese Bewertung vergeben wurde.\n\n\nHier der Input:\n\n{{ $('Gmail Trigger').item.json.text }}\n\nUnd hier der Output:\n{{ $json.output }}"
                },
                {
                  "role": "assistant",
                  "content": "sei pedantisch"
                }
              ]
            }
          },
          "credentials": {
            "openAiApi": {
              "id": "credential-id",
              "name": "openAiApi Credential"
            }
          },
          "typeVersion": 1.8
        },
        {
          "id": "f9c7b8a8-2148-49f1-b604-4766deafadd1",
          "name": "OpenAI self-assesment2",
          "type": "@n8n/n8n-nodes-langchain.openAi",
          "onError": "continueRegularOutput",
          "position": [
            1740,
            -80
          ],
          "parameters": {
            "modelId": {
              "__rl": true,
              "mode": "list",
              "value": "gpt-4o-mini",
              "cachedResultName": "GPT-4O-MINI"
            },
            "options": {},
            "messages": {
              "values": [
                {
                  "content": "=Deine Aufgabe ist es, den gegebenen Input-Text mit dem Output-Artikel zu vergleichen.\nBewerte, ob alle wesentlichen Informationen aus dem Input-Text im Output-Artikel korrekt enthalten sind, ohne dass neue, nicht im Input vorhandene Informationen hinzugefügt wurden.\nVorgehensweise:\n\n    Vollständigkeit prüfen: Sind alle relevanten Informationen aus dem Input im Output enthalten?\n    Genauigkeit bewerten: Wurde der Inhalt korrekt wiedergegeben, ohne Änderungen oder Auslassungen?\n    Zusätzliche Informationen erkennen: Wurden Inhalte hinzugefügt, die nicht im Input vorhanden sind? Falls ja, welche?\n\nAusgabe:\n\n    Bewertung (1 bis 5):\n        1 = Sehr schlecht (viele fehlende oder falsche Informationen, erhebliche neue Inhalte)\n        2 = Unzureichend (mehrere wichtige Auslassungen oder falsche Inhalte)\n        3 = Mittelmäßig (einige kleinere Fehler oder Ergänzungen)\n        4 = Gut (fast alles korrekt, minimale Abweichungen)\n        5 = Sehr gut (vollständige, korrekte Übereinstimmung)\n    Textuelle Begründung: Eine kurze Analyse, warum diese Bewertung vergeben wurde.\n\n\nHier der Input:\n{{ $('Extrahiere aus PDF1').item.json.text }}\n{{ $('Gmail Trigger').item.json.text }}\n\nUnd hier der Output:\n {{ $json.output }}"
                },
                {
                  "role": "assistant",
                  "content": "sei pedantisch"
                }
              ]
            }
          },
          "credentials": {
            "openAiApi": {
              "id": "credential-id",
              "name": "openAiApi Credential"
            }
          },
          "retryOnFail": true,
          "typeVersion": 1.8
        },
        {
          "id": "0c2c1c4d-b3ec-4e1d-b663-27c43dddb523",
          "name": "reply to sender (no attachment)",
          "type": "n8n-nodes-base.gmail",
          "position": [
            1440,
            520
          ],
          "webhookId": "521f7992-d12c-4485-92d8-41cc5567938b",
          "parameters": {
            "message": "=***REDIGIERTER ARTIKEL***  !!!-CLAUDE-!!!\n\n{{ $('AI Article Writer 3').item.json.output }}\n\n***SELBSTKRITIK***\n\n{{ $json.message.content }}\n\n***ORIGINALNACHRICHT***\n\n{{ $('Gmail Trigger').item.json.text }}",
            "options": {},
            "emailType": "text",
            "messageId": "={{ $('Gmail Trigger').item.json.id }}",
            "operation": "reply"
          },
          "credentials": {
            "gmailOAuth2": {
              "id": "credential-id",
              "name": "gmailOAuth2 Credential"
            }
          },
          "typeVersion": 2.1
        },
        {
          "id": "de88f6fb-0e75-41d9-8e0c-7377ca1bdca4",
          "name": "reply to sender (word)",
          "type": "n8n-nodes-base.gmail",
          "position": [
            2360,
            280
          ],
          "webhookId": "5767887a-ca7a-41f9-9745-34d49bb79691",
          "parameters": {
            "message": "=***REDIGIERTER ARTIKEL***   !!!! CLAUDE !!!!\n\n\n{{ $('AI Article Writer 2').item.json.output }}\n\n***SELBSTKRITIK***\nBewertung: 1 (schlecht) bis 5 (sehr gut)\n{{ $json.message.content }}\n***ORIGINALNACHRICHT***\n\n{{ $('Gmail Trigger').item.json.text }}\n\n***INHALT ANHANG***\n\n{{ $('HTTP Request3').item.json.data }}",
            "options": {},
            "emailType": "text",
            "messageId": "={{ $('Gmail Trigger').item.json.id }}",
            "operation": "reply"
          },
          "credentials": {
            "gmailOAuth2": {
              "id": "credential-id",
              "name": "gmailOAuth2 Credential"
            }
          },
          "typeVersion": 2.1
        },
        {
          "id": "0d9c55f9-3c53-44aa-b0d0-09141570b72b",
          "name": "reply to sender (pdf)",
          "type": "n8n-nodes-base.gmail",
          "position": [
            2140,
            -80
          ],
          "webhookId": "523f355b-404f-4a60-b393-e2c5d8f29098",
          "parameters": {
            "message": "=*****REDIGIERTE NACHRICHT*****   !!!!- CLAUDE -!!!\n{{ $('AI Article Writer 1').item.json.output }}\n\n*****SELBSTKRITIK****\nBewertung 1 (schlecht) bis 5 (sehr gut):\n{{ $json.message.content }}\n\n*****ORIGINAL-E-MAIL*****\n\n{{ $('Gmail Trigger').item.json.text }}\n\n\n*****TEXT AUS PDF*****\n\n{{ $('Extrahiere aus PDF1').item.json.text }}\n\n\n",
            "options": {},
            "emailType": "text",
            "messageId": "={{ $('Gmail Trigger').item.json.id }}",
            "operation": "reply"
          },
          "credentials": {
            "gmailOAuth2": {
              "id": "credential-id",
              "name": "gmailOAuth2 Credential"
            }
          },
          "typeVersion": 2.1
        },
        {
          "id": "695e80d4-dbe2-4476-b680-b90732a6136a",
          "name": "AI Article Writer 1",
          "type": "@n8n/n8n-nodes-langchain.agent",
          "onError": "continueRegularOutput",
          "maxTries": 5,
          "position": [
            1380,
            -80
          ],
          "parameters": {
            "text": "=Du bist Redakteur*in beim Schweizer Kulturmagazin Terra Grischuna. Erstelle aus den Textinformationen einen publikationsfertigen Artikel mit folgender Struktur und Vorgehensweise:\n\n    Stil und Sprache\n    – Schreibe in einer neutralen, reduzierten und klaren Sprache.\n    – Verwende die Schweizer Rechtschreibung.\n    – Halte dich an ein genderneutrales, aktives und verständliches Wording.\n\n    Form und Aufbau\n    – Nutze die Form der umgekehrten Pyramide (wichtigste Informationen zuerst, abnehmende Wichtigkeit im Verlauf).\n    – Verfasse einen Titel und klare Zwischentitel (keine Bulletpoints).\n    – Bei Veranstaltungshinweisen beginne den Artikel mit einem Satz, der Wer, wann, wo, was beantwortet (z. B. „Franz Tomaschett spricht am 5. Dezember in Chur über das Thema Arbeit.“).\n    – Der Fliesstext sollte zwischen 250 und 500 Wörtern umfassen.\n\n    Inhalte und Daten\n    – Fasse alle relevanten Inhalte verständlich zusammen.\n- halte dich an die Informationen aus der E-Mail. Erfinde nichts! Sei genau!\n- wenn dir Informationen fehlen, konstruiere keine neuen. \n    – Ignoriere alle anderen Dateiformate (z. B. Bilder, Excel-Tabellen).\n    – Verwende keine Aufzählungspunkte im finalen Artikel.\n- wenn subjektive oder streitbare Ansichten formuliert werden, attribuiere diese den Absendern dieser Ansichten. Nenne Quelle/Urheber solcher Äusserungen. Beispiel: \"ZITAT in direkter oder indirekter Rede\", schreibt die Gruppe Wolf in ihrer Mitteilung. \n\n    Zusätzliche Anweisung\n    – Extrahiere zunächst alle wichtigen Daten, Personen und Schlagworte. Liste sie strukturiert (z. B. mit Absätzen oder klarer Trennung) vor dem eigentlichen Artikel auf. Zähle zudem die Anzahl Zeichen und Wörter des Artikels.\n\nBeispielhafte Ausgabe-Struktur\n\nWichtige Daten und Personen\nNennehierknappundstrukturiertallerelevantenNamen,Daten,Orte,Termineetc.NennehierknappundstrukturiertallerelevantenNamen,Daten,Orte,Termineetc.\n\nTitel\nKurzer,pra¨gnanterTitelKurzer,pra¨gnanterTitel\n\n\nEinfu¨hrenderAbsatzmitdenwichtigstenInfos(wer,wann,wo,was)Einfu¨hrenderAbsatzmitdenwichtigstenInfos(wer,wann,wo,was)\n\nZwischentitel 1\nHintergrund,weitereZusammenha¨nge,abnehmendwichtigeDetailsHintergrund,weitereZusammenha¨nge,abnehmendwichtigeDetails\n\nZwischentitel 2\nRestlicheInformationen,kontextualisiertundzusammengefasstRestlicheInformationen,kontextualisiertundzusammengefasst\n\n(Ende des Artikels, maximal 500 Wörter.)\n\nNutze bitte diese Vorgaben, um den Artikel in hochwertiger, schweizkonformer Sprache zu verfassen.\n\nHier die Informationen aus dem E-Mail\n\n {{ $('Gmail Trigger').item.json.text }}\n\n{{ $json.text }}",
            "options": {},
            "promptType": "define"
          },
          "retryOnFail": true,
          "typeVersion": 1.7
        },
        {
          "id": "1d3988ea-b8ec-450a-a512-f5463953554b",
          "name": "AI Article Writer 2",
          "type": "@n8n/n8n-nodes-langchain.agent",
          "position": [
            1700,
            280
          ],
          "parameters": {
            "text": "=Du bist Redakteur*in beim Schweizer Kulturmagazin Terra Grischuna. Erstelle aus den Textinformationen einen publikationsfertigen Artikel mit folgender Struktur und Vorgehensweise:\n\n    Stil und Sprache\n    – Schreibe in einer neutralen, reduzierten und klaren Sprache.\n    – Verwende die Schweizer Rechtschreibung.\n    – Halte dich an ein genderneutrales, aktives und verständliches Wording.\n\n    Form und Aufbau\n    – Nutze die Form der umgekehrten Pyramide (wichtigste Informationen zuerst, abnehmende Wichtigkeit im Verlauf).\n    – Verfasse einen Titel und klare Zwischentitel (keine Bulletpoints).\n    – Bei Veranstaltungshinweisen beginne den Artikel mit einem Satz, der Wer, wann, wo, was beantwortet (z. B. „Franz Tomaschett spricht am 5. Dezember in Chur über das Thema Arbeit.“).\n    – Der Fliesstext sollte zwischen 250 und 500 Wörtern umfassen.\n\n    Inhalte und Daten\n    – Fasse alle relevanten Inhalte verständlich zusammen.\n- halte dich an die Informationen aus der E-Mail. Erfinde nichts! Sei genau!\n- wenn dir Informationen fehlen, konstruiere keine neuen. \n    – Ignoriere alle anderen Dateiformate (z. B. Bilder, Excel-Tabellen).\n    – Verwende keine Aufzählungspunkte im finalen Artikel.\n- wenn subjektive oder streitbare Ansichten formuliert werden, attribuiere diese den Absendern dieser Ansichten. Nenne Quelle/Urheber solcher Äusserungen. Beispiel: \"ZITAT in direkter oder indirekter Rede\", schreibt die Gruppe Wolf in ihrer Mitteilung. \n\n    Zusätzliche Anweisung\n    – Extrahiere zunächst alle wichtigen Daten, Personen und Schlagworte. Liste sie strukturiert (z. B. mit Absätzen oder klarer Trennung) vor dem eigentlichen Artikel auf. Zähle zudem die Anzahl Zeichen und Wörter des Artikels.\n\nBeispielhafte Ausgabe-Struktur\n\nWichtige Daten und Personen\nNennehierknappundstrukturiertallerelevantenNamen,Daten,Orte,Termineetc.NennehierknappundstrukturiertallerelevantenNamen,Daten,Orte,Termineetc.\n\nTitel\nKurzer,pra¨gnanterTitelKurzer,pra¨gnanterTitel\n\n\nEinfu¨hrenderAbsatzmitdenwichtigstenInfos(wer,wann,wo,was)Einfu¨hrenderAbsatzmitdenwichtigstenInfos(wer,wann,wo,was)\n\nZwischentitel 1\nHintergrund,weitereZusammenha¨nge,abnehmendwichtigeDetailsHintergrund,weitereZusammenha¨nge,abnehmendwichtigeDetails\n\nZwischentitel 2\nRestlicheInformationen,kontextualisiertundzusammengefasstRestlicheInformationen,kontextualisiertundzusammengefasst\n\n(Ende des Artikels, maximal 500 Wörter.)\n\nNutze bitte diese Vorgaben, um den Artikel in hochwertiger, schweizkonformer Sprache zu verfassen.\n\nHier die Informationen aus dem E-Mail\n\n {{ $('Gmail Trigger').item.json.text }}{{ $json.data }}",
            "options": {},
            "promptType": "define"
          },
          "typeVersion": 1.7
        },
        {
          "id": "99b5a06e-5d1b-4797-a934-2c37b49caf47",
          "name": "AI Article Writer 3",
          "type": "@n8n/n8n-nodes-langchain.agent",
          "position": [
            660,
            520
          ],
          "parameters": {
            "text": "=Du bist Redakteur*in beim Schweizer Kulturmagazin Terra Grischuna. Erstelle aus den Textinformationen einen publikationsfertigen Artikel mit folgender Struktur und Vorgehensweise:\n\n    Stil und Sprache\n    – Schreibe in einer neutralen, reduzierten und klaren Sprache.\n    – Verwende die Schweizer Rechtschreibung.\n    – Halte dich an ein genderneutrales, aktives und verständliches Wording.\n\n    Form und Aufbau\n    – Nutze die Form der umgekehrten Pyramide (wichtigste Informationen zuerst, abnehmende Wichtigkeit im Verlauf).\n    – Verfasse einen Titel und klare Zwischentitel (keine Bulletpoints).\n    – Bei Veranstaltungshinweisen beginne den Artikel mit einem Satz, der Wer, wann, wo, was beantwortet (z. B. „Franz Tomaschett spricht am 5. Dezember in Chur über das Thema Arbeit.“).\n    – Der Fliesstext sollte zwischen 250 und 500 Wörtern umfassen.\n- wenn subjektive oder streitbare Ansichten formuliert werden, attribuiere diese den Absendern dieser Ansichten. Nenne Quelle/Urheber solcher Äusserungen. Beispiel: \"ZITAT in direkter oder indirekter Rede\", schreibt die Gruppe Wolf in ihrer Mitteilung. \n\n    Inhalte und Daten\n    – Fasse alle relevanten Inhalte verständlich zusammen.\n- halte dich an die Informationen aus der E-Mail. Erfinde nichts! Sei genau!\n- wenn dir Informationen fehlen, konstruiere keine neuen. \n    – Ignoriere alle anderen Dateiformate (z. B. Bilder, Excel-Tabellen).\n    – Verwende keine Aufzählungspunkte im finalen Artikel.\n\n    Zusätzliche Anweisung\n    – Extrahiere zunächst alle wichtigen Daten, Personen und Schlagworte. Liste sie strukturiert (z. B. mit Absätzen oder klarer Trennung) vor dem eigentlichen Artikel auf. Zähle zudem die Anzahl Zeichen und Wörter des Artikels.\n\nBeispielhafte Ausgabe-Struktur\n\nWichtige Daten und Personen\nNennehierknappundstrukturiertallerelevantenNamen,Daten,Orte,Termineetc.NennehierknappundstrukturiertallerelevantenNamen,Daten,Orte,Termineetc.\n\nTitel\nKurzer,pra¨gnanterTitelKurzer,pra¨gnanterTitel\n\n\nEinfu¨hrenderAbsatzmitdenwichtigstenInfos(wer,wann,wo,was)Einfu¨hrenderAbsatzmitdenwichtigstenInfos(wer,wann,wo,was)\n\nZwischentitel 1\nHintergrund,weitereZusammenha¨nge,abnehmendwichtigeDetailsHintergrund,weitereZusammenha¨nge,abnehmendwichtigeDetails\n\nZwischentitel 2\nRestlicheInformationen,kontextualisiertundzusammengefasstRestlicheInformationen,kontextualisiertundzusammengefasst\n\n(Ende des Artikels, maximal 500 Wörter.)\n\nNutze bitte diese Vorgaben, um den Artikel in hochwertiger, Schweizkonformer Sprache zu verfassen.\n\nHier die Informationen aus dem E-Mail\n\n {{ $('Gmail Trigger').item.json.text }}",
            "options": {},
            "promptType": "define"
          },
          "typeVersion": 1.7
        },
        {
          "id": "f7280703-4570-4771-8a53-cac3a661f416",
          "name": "Google Drive",
          "type": "n8n-nodes-base.googleDrive",
          "position": [
            960,
            280
          ],
          "parameters": {
            "name": "={{ $json.fileName }}",
            "driveId": {
              "__rl": true,
              "mode": "list",
              "value": "My Drive"
            },
            "options": {
              "useContentAsIndexableText": false
            },
            "folderId": {
              "__rl": true,
              "mode": "list",
              "value": "root",
              "cachedResultName": "/ (Root folder)"
            }
          },
          "credentials": {
            "googleDriveOAuth2Api": {
              "id": "credential-id",
              "name": "googleDriveOAuth2Api Credential"
            }
          },
          "typeVersion": 3
        },
        {
          "id": "a83189ab-027d-4ed7-aa69-82e29270cd7c",
          "name": "OpenAI self-assesment",
          "type": "@n8n/n8n-nodes-langchain.openAi",
          "position": [
            2020,
            280
          ],
          "parameters": {
            "modelId": {
              "__rl": true,
              "mode": "list",
              "value": "gpt-4o-mini",
              "cachedResultName": "GPT-4O-MINI"
            },
            "options": {},
            "messages": {
              "values": [
                {
                  "content": "=Deine Aufgabe ist es, den gegebenen Input-Text mit dem Output-Artikel zu vergleichen.\nBewerte, ob alle wesentlichen Informationen aus dem Input-Text im Output-Artikel korrekt enthalten sind, ohne dass neue, nicht im Input vorhandene Informationen hinzugefügt wurden.\nVorgehensweise:\n\n    Vollständigkeit prüfen: Sind alle relevanten Informationen aus dem Input im Output enthalten?\n    Genauigkeit bewerten: Wurde der Inhalt korrekt wiedergegeben, ohne Änderungen oder Auslassungen?\n    Zusätzliche Informationen erkennen: Wurden Inhalte hinzugefügt, die nicht im Input vorhanden sind? Falls ja, welche?\n\nAusgabe:\n\n    Bewertung (1 bis 5):\n        1 = Sehr schlecht (viele fehlende oder falsche Informationen, erhebliche neue Inhalte)\n        2 = Unzureichend (mehrere wichtige Auslassungen oder falsche Inhalte)\n        3 = Mittelmäßig (einige kleinere Fehler oder Ergänzungen)\n        4 = Gut (fast alles korrekt, minimale Abweichungen)\n        5 = Sehr gut (vollständige, korrekte Übereinstimmung)\n    Textuelle Begründung: Eine kurze Analyse, warum diese Bewertung vergeben wurde.\n\n\nHier der Input:\n{{ $('HTTP Request3').item.json.data }}\n{{ $('Gmail Trigger').item.json.text }}\nUnd hier der Output:\n{{ $json.output }}"
                },
                {
                  "role": "assistant",
                  "content": "sei pedantisch"
                }
              ]
            }
          },
          "credentials": {
            "openAiApi": {
              "id": "credential-id",
              "name": "openAiApi Credential"
            }
          },
          "typeVersion": 1.8
        }
      ],
      "active": false,
      "pinData": {},
      "settings": {
        "timezone": "Europe/Rome",
        "callerPolicy": "workflowsFromSameOwner",
        "executionOrder": "v1"
      },
      "versionId": "0e0eba57-a154-48ee-a86a-d4c787805456",
      "connections": {
        "Google Drive": {
          "main": [
            [
              {
                "node": "HTTP Request2",
                "type": "main",
                "index": 0
              }
            ]
          ]
        },
        "PDF or WORD?": {
          "main": [
            [
              {
                "node": "Extrahiere aus PDF1",
                "type": "main",
                "index": 0
              }
            ],
            [
              {
                "node": "Google Drive",
                "type": "main",
                "index": 0
              }
            ]
          ]
        },
        "Gmail Trigger": {
          "main": [
            [
              {
                "node": "Code: delete all but pdf and word",
                "type": "main",
                "index": 0
              }
            ]
          ]
        },
        "HTTP Request2": {
          "main": [
            [
              {
                "node": "HTTP Request3",
                "type": "main",
                "index": 0
              }
            ]
          ]
        },
        "HTTP Request3": {
          "main": [
            [
              {
                "node": "AI Article Writer 2",
                "type": "main",
                "index": 0
              }
            ]
          ]
        },
        "has attachment?": {
          "main": [
            [
              {
                "node": "PDF or WORD?",
                "type": "main",
                "index": 0
              }
            ],
            [
              {
                "node": "AI Article Writer 3",
                "type": "main",
                "index": 0
              }
            ]
          ]
        },
        "AI Article Writer 1": {
          "main": [
            [
              {
                "node": "OpenAI self-assesment2",
                "type": "main",
                "index": 0
              }
            ]
          ]
        },
        "AI Article Writer 2": {
          "main": [
            [
              {
                "node": "OpenAI self-assesment",
                "type": "main",
                "index": 0
              }
            ]
          ]
        },
        "AI Article Writer 3": {
          "main": [
            [
              {
                "node": "OpenAI self assesment",
                "type": "main",
                "index": 0
              }
            ]
          ]
        },
        "Extrahiere aus PDF1": {
          "main": [
            [
              {
                "node": "AI Article Writer 1",
                "type": "main",
                "index": 0
              }
            ]
          ]
        },
        "Anthropic Chat Model": {
          "ai_languageModel": [
            [
              {
                "node": "AI Article Writer 3",
                "type": "ai_languageModel",
                "index": 0
              }
            ]
          ]
        },
        "Anthropic Chat Model1": {
          "ai_languageModel": [
            [
              {
                "node": "AI Article Writer 2",
                "type": "ai_languageModel",
                "index": 0
              }
            ]
          ]
        },
        "Anthropic Chat Model2": {
          "ai_languageModel": [
            [
              {
                "node": "AI Article Writer 1",
                "type": "ai_languageModel",
                "index": 0
              }
            ]
          ]
        },
        "OpenAI self assesment": {
          "main": [
            [
              {
                "node": "reply to sender (no attachment)",
                "type": "main",
                "index": 0
              }
            ]
          ]
        },
        "OpenAI self-assesment": {
          "main": [
            [
              {
                "node": "reply to sender (word)",
                "type": "main",
                "index": 0
              }
            ]
          ]
        },
        "OpenAI self-assesment2": {
          "main": [
            [
              {
                "node": "reply to sender (pdf)",
                "type": "main",
                "index": 0
              }
            ]
          ]
        },
        "Code: delete all but pdf and word": {
          "main": [
            [
              {
                "node": "has attachment?",
                "type": "main",
                "index": 0
              }
            ]
          ]
        }
      }
    },
    "lastUpdatedBy": 29,
    "workflowInfo": {
      "nodeCount": 20,
      "nodeTypes": {
        "n8n-nodes-base.if": {
          "count": 2
        },
        "n8n-nodes-base.code": {
          "count": 1
        },
        "n8n-nodes-base.gmail": {
          "count": 3
        },
        "n8n-nodes-base.googleDrive": {
          "count": 1
        },
        "n8n-nodes-base.httpRequest": {
          "count": 2
        },
        "n8n-nodes-base.gmailTrigger": {
          "count": 1
        },
        "@n8n/n8n-nodes-langchain.agent": {
          "count": 3
        },
        "n8n-nodes-base.extractFromFile": {
          "count": 1
        },
        "@n8n/n8n-nodes-langchain.openAi": {
          "count": 3
        },
        "@n8n/n8n-nodes-langchain.lmChatAnthropic": {
          "count": 3
        }
      }
    },
    "status": "published",
    "readyToDemo": null,
    "user": {
      "name": "Julian Reich ",
      "username": "julianreich",
      "bio": "",
      "verified": true,
      "links": [
        "www.linkedin.com/in/julian-reich-8b3308245"
      ],
      "avatar": "https://gravatar.com/avatar/854a7462ee146ea7dbe42fafb96cf53247b160886481cda58e4cb3e4e7e785c4?r=pg&d=retro&size=200"
    },
    "nodes": [
      {
        "id": 19,
        "icon": "file:httprequest.svg",
        "name": "n8n-nodes-base.httpRequest",
        "codex": {
          "data": {
            "alias": [
              "API",
              "Request",
              "URL",
              "Build",
              "cURL"
            ],
            "resources": {
              "generic": [
                {
                  "url": "https://n8n.io/blog/2021-the-year-to-automate-the-new-you-with-n8n/",
                  "icon": "☀️",
                  "label": "2021: The Year to Automate the New You with n8n"
                },
                {
                  "url": "https://n8n.io/blog/why-business-process-automation-with-n8n-can-change-your-daily-life/",
                  "icon": "🧬",
                  "label": "Why business process automation with n8n can change your daily life"
                },
                {
                  "url": "https://n8n.io/blog/automatically-pulling-and-visualizing-data-with-n8n/",
                  "icon": "📈",
                  "label": "Automatically pulling and visualizing data with n8n"
                },
                {
                  "url": "https://n8n.io/blog/learn-how-to-automatically-cross-post-your-content-with-n8n/",
                  "icon": "✍️",
                  "label": "Learn how to automatically cross-post your content with n8n"
                },
                {
                  "url": "https://n8n.io/blog/automatically-adding-expense-receipts-to-google-sheets-with-telegram-mindee-twilio-and-n8n/",
                  "icon": "🧾",
                  "label": "Automatically Adding Expense Receipts to Google Sheets with Telegram, Mindee, Twilio, and n8n"
                },
                {
                  "url": "https://n8n.io/blog/running-n8n-on-ships-an-interview-with-maranics/",
                  "icon": "🛳",
                  "label": "Running n8n on ships: An interview with Maranics"
                },
                {
                  "url": "https://n8n.io/blog/what-are-apis-how-to-use-them-with-no-code/",
                  "icon": " 🪢",
                  "label": "What are APIs and how to use them with no code"
                },
                {
                  "url": "https://n8n.io/blog/5-tasks-you-can-automate-with-notion-api/",
                  "icon": "⚡️",
                  "label": "5 tasks you can automate with the new Notion API "
                },
                {
                  "url": "https://n8n.io/blog/world-poetry-day-workflow/",
                  "icon": "📜",
                  "label": "Celebrating World Poetry Day with a daily poem in Telegram"
                },
                {
                  "url": "https://n8n.io/blog/automate-google-apps-for-productivity/",
                  "icon": "💡",
                  "label": "15 Google apps you can combine and automate to increase productivity"
                },
                {
                  "url": "https://n8n.io/blog/automate-designs-with-bannerbear-and-n8n/",
                  "icon": "🎨",
                  "label": "Automate Designs with Bannerbear and n8n"
                },
                {
                  "url": "https://n8n.io/blog/how-uproc-scraped-a-multi-page-website-with-a-low-code-workflow/",
                  "icon": " 🕸️",
                  "label": "How uProc scraped a multi-page website with a low-code workflow"
                },
                {
                  "url": "https://n8n.io/blog/building-an-expense-tracking-app-in-10-minutes/",
                  "icon": "📱",
                  "label": "Building an expense tracking app in 10 minutes"
                },
                {
                  "url": "https://n8n.io/blog/5-workflow-automations-for-mattermost-that-we-love-at-n8n/",
                  "icon": "🤖",
                  "label": "5 workflow automations for Mattermost that we love at n8n"
                },
                {
                  "url": "https://n8n.io/blog/how-to-use-the-http-request-node-the-swiss-army-knife-for-workflow-automation/",
                  "icon": "🧰",
                  "label": "How to use the HTTP Request Node - The Swiss Army Knife for Workflow Automation"
                },
                {
                  "url": "https://n8n.io/blog/learn-how-to-use-webhooks-with-mattermost-slash-commands/",
                  "icon": "🦄",
                  "label": "Learn how to use webhooks with Mattermost slash commands"
                },
                {
                  "url": "https://n8n.io/blog/how-a-membership-development-manager-automates-his-work-and-investments/",
                  "icon": "📈",
                  "label": "How a Membership Development Manager automates his work and investments"
                },
                {
                  "url": "https://n8n.io/blog/a-low-code-bitcoin-ticker-built-with-questdb-and-n8n-io/",
                  "icon": "📈",
                  "label": "A low-code bitcoin ticker built with QuestDB and n8n.io"
                },
                {
                  "url": "https://n8n.io/blog/how-to-set-up-a-ci-cd-pipeline-with-no-code/",
                  "icon": "🎡",
                  "label": "How to set up a no-code CI/CD pipeline with GitHub and TravisCI"
                },
                {
                  "url": "https://n8n.io/blog/automations-for-activists/",
                  "icon": "✨",
                  "label": "How Common Knowledge use workflow automation for activism"
                },
                {
                  "url": "https://n8n.io/blog/creating-scheduled-text-affirmations-with-n8n/",
                  "icon": "🤟",
                  "label": "Creating scheduled text affirmations with n8n"
                },
                {
                  "url": "https://n8n.io/blog/how-goomer-automated-their-operations-with-over-200-n8n-workflows/",
                  "icon": "🛵",
                  "label": "How Goomer automated their operations with over 200 n8n workflows"
                },
                {
                  "url": "https://n8n.io/blog/aws-workflow-automation/",
                  "label": "7 no-code workflow automations for Amazon Web Services"
                }
              ],
              "primaryDocumentation": [
                {
                  "url": "https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-base.httprequest/"
                }
              ]
            },
            "categories": [
              "Development",
              "Core Nodes"
            ],
            "nodeVersion": "1.0",
            "codexVersion": "1.0",
            "subcategories": {
              "Core Nodes": [
                "Helpers"
              ]
            }
          }
        },
        "group": "[\"output\"]",
        "defaults": {
          "name": "HTTP Request",
          "color": "#0004F5"
        },
        "iconData": {
          "type": "file",
          "fileBuffer": "data:image/svg+xml;base64,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"
        },
        "displayName": "HTTP Request",
        "typeVersion": 4,
        "nodeCategories": [
          {
            "id": 5,
            "name": "Development"
          },
          {
            "id": 9,
            "name": "Core Nodes"
          }
        ]
      },
      {
        "id": 20,
        "icon": "fa:map-signs",
        "name": "n8n-nodes-base.if",
        "codex": {
          "data": {
            "alias": [
              "Router",
              "Filter",
              "Condition",
              "Logic",
              "Boolean",
              "Branch"
            ],
            "details": "The IF node can be used to implement binary conditional logic in your workflow. You can set up one-to-many conditions to evaluate each item of data being inputted into the node. That data will either evaluate to TRUE or FALSE and route out of the node accordingly.\n\nThis node has multiple types of conditions: Bool, String, Number, and Date & Time.",
            "resources": {
              "generic": [
                {
                  "url": "https://n8n.io/blog/learn-to-automate-your-factorys-incident-reporting-a-step-by-step-guide/",
                  "icon": "🏭",
                  "label": "Learn to Automate Your Factory's Incident Reporting: A Step by Step Guide"
                },
                {
                  "url": "https://n8n.io/blog/2021-the-year-to-automate-the-new-you-with-n8n/",
                  "icon": "☀️",
                  "label": "2021: The Year to Automate the New You with n8n"
                },
                {
                  "url": "https://n8n.io/blog/why-business-process-automation-with-n8n-can-change-your-daily-life/",
                  "icon": "🧬",
                  "label": "Why business process automation with n8n can change your daily life"
                },
                {
                  "url": "https://n8n.io/blog/create-a-toxic-language-detector-for-telegram/",
                  "icon": "🤬",
                  "label": "Create a toxic language detector for Telegram in 4 step"
                },
                {
                  "url": "https://n8n.io/blog/no-code-ecommerce-workflow-automations/",
                  "icon": "store",
                  "label": "6 e-commerce workflows to power up your Shopify s"
                },
                {
                  "url": "https://n8n.io/blog/how-to-build-a-low-code-self-hosted-url-shortener/",
                  "icon": "🔗",
                  "label": "How to build a low-code, self-hosted URL shortener in 3 steps"
                },
                {
                  "url": "https://n8n.io/blog/automate-your-data-processing-pipeline-in-9-steps-with-n8n/",
                  "icon": "⚙️",
                  "label": "Automate your data processing pipeline in 9 steps"
                },
                {
                  "url": "https://n8n.io/blog/how-to-get-started-with-crm-automation-and-no-code-workflow-ideas/",
                  "icon": "👥",
                  "label": "How to get started with CRM automation (with 3 no-code workflow ideas"
                },
                {
                  "url": "https://n8n.io/blog/5-tasks-you-can-automate-with-notion-api/",
                  "icon": "⚡️",
                  "label": "5 tasks you can automate with the new Notion API "
                },
                {
                  "url": "https://n8n.io/blog/automate-google-apps-for-productivity/",
                  "icon": "💡",
                  "label": "15 Google apps you can combine and automate to increase productivity"
                },
                {
                  "url": "https://n8n.io/blog/automation-for-maintainers-of-open-source-projects/",
                  "icon": "🏷️",
                  "label": "How to automatically manage contributions to open-source projects"
                },
                {
                  "url": "https://n8n.io/blog/how-uproc-scraped-a-multi-page-website-with-a-low-code-workflow/",
                  "icon": " 🕸️",
                  "label": "How uProc scraped a multi-page website with a low-code workflow"
                },
                {
                  "url": "https://n8n.io/blog/5-workflow-automations-for-mattermost-that-we-love-at-n8n/",
                  "icon": "🤖",
                  "label": "5 workflow automations for Mattermost that we love at n8n"
                },
                {
                  "url": "https://n8n.io/blog/why-this-product-manager-loves-workflow-automation-with-n8n/",
                  "icon": "🧠",
                  "label": "Why this Product Manager loves workflow automation with n8n"
                },
                {
                  "url": "https://n8n.io/blog/sending-automated-congratulations-with-google-sheets-twilio-and-n8n/",
                  "icon": "🙌",
                  "label": "Sending Automated Congratulations with Google Sheets, Twilio, and n8n "
                },
                {
                  "url": "https://n8n.io/blog/how-to-set-up-a-ci-cd-pipeline-with-no-code/",
                  "icon": "🎡",
                  "label": "How to set up a no-code CI/CD pipeline with GitHub and TravisCI"
                },
                {
                  "url": "https://n8n.io/blog/benefits-of-automation-and-n8n-an-interview-with-hubspots-hugh-durkin/",
                  "icon": "🎖",
                  "label": "Benefits of automation and n8n: An interview with HubSpot's Hugh Durkin"
                },
                {
                  "url": "https://n8n.io/blog/aws-workflow-automation/",
                  "label": "7 no-code workflow automations for Amazon Web Services"
                }
              ],
              "primaryDocumentation": [
                {
                  "url": "https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-base.if/"
                }
              ]
            },
            "categories": [
              "Core Nodes"
            ],
            "nodeVersion": "1.0",
            "codexVersion": "1.0",
            "subcategories": {
              "Core Nodes": [
                "Flow"
              ]
            }
          }
        },
        "group": "[\"transform\"]",
        "defaults": {
          "name": "If",
          "color": "#408000"
        },
        "iconData": {
          "icon": "map-signs",
          "type": "icon"
        },
        "displayName": "If",
        "typeVersion": 2,
        "nodeCategories": [
          {
            "id": 9,
            "name": "Core Nodes"
          }
        ]
      },
      {
        "id": 58,
        "icon": "file:googleDrive.svg",
        "name": "n8n-nodes-base.googleDrive",
        "codex": {
          "data": {
            "resources": {
              "generic": [
                {
                  "url": "https://n8n.io/blog/your-business-doesnt-need-you-to-operate/",
                  "icon": " 🖥️",
                  "label": "Hey founders! Your business doesn't need you to operate"
                },
                {
                  "url": "https://n8n.io/blog/why-this-product-manager-loves-workflow-automation-with-n8n/",
                  "icon": "🧠",
                  "label": "Why this Product Manager loves workflow automation with n8n"
                },
                {
                  "url": "https://n8n.io/blog/aws-workflow-automation/",
                  "label": "7 no-code workflow automations for Amazon Web Services"
                }
              ],
              "primaryDocumentation": [
                {
                  "url": "https://docs.n8n.io/integrations/builtin/app-nodes/n8n-nodes-base.googledrive/"
                }
              ],
              "credentialDocumentation": [
                {
                  "url": "https://docs.n8n.io/integrations/builtin/credentials/google/oauth-single-service/"
                }
              ]
            },
            "categories": [
              "Data & Storage"
            ],
            "nodeVersion": "1.0",
            "codexVersion": "1.0"
          }
        },
        "group": "[\"input\"]",
        "defaults": {
          "name": "Google Drive"
        },
        "iconData": {
          "type": "file",
          "fileBuffer": "data:image/svg+xml;base64,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"
        },
        "displayName": "Google Drive",
        "typeVersion": 3,
        "nodeCategories": [
          {
            "id": 3,
            "name": "Data & Storage"
          }
        ]
      },
      {
        "id": 356,
        "icon": "file:gmail.svg",
        "name": "n8n-nodes-base.gmail",
        "codex": {
          "data": {
            "alias": [
              "email",
              "human",
              "form",
              "wait",
              "hitl",
              "approval"
            ],
            "resources": {
              "generic": [
                {
                  "url": "https://n8n.io/blog/why-business-process-automation-with-n8n-can-change-your-daily-life/",
                  "icon": "🧬",
                  "label": "Why business process automation with n8n can change your daily life"
                },
                {
                  "url": "https://n8n.io/blog/supercharging-your-conference-registration-process-with-n8n/",
                  "icon": "🎫",
                  "label": "Supercharging your conference registration process with n8n"
                },
                {
                  "url": "https://n8n.io/blog/no-code-ecommerce-workflow-automations/",
                  "icon": "store",
                  "label": "6 e-commerce workflows to power up your Shopify s"
                },
                {
                  "url": "https://n8n.io/blog/how-to-get-started-with-crm-automation-and-no-code-workflow-ideas/",
                  "icon": "👥",
                  "label": "How to get started with CRM automation (with 3 no-code workflow ideas"
                },
                {
                  "url": "https://n8n.io/blog/automate-google-apps-for-productivity/",
                  "icon": "💡",
                  "label": "15 Google apps you can combine and automate to increase productivity"
                },
                {
                  "url": "https://n8n.io/blog/your-business-doesnt-need-you-to-operate/",
                  "icon": " 🖥️",
                  "label": "Hey founders! Your business doesn't need you to operate"
                },
                {
                  "url": "https://n8n.io/blog/using-automation-to-boost-productivity-in-the-workplace/",
                  "icon": "💪",
                  "label": "Using Automation to Boost Productivity in the Workplace"
                }
              ],
              "primaryDocumentation": [
                {
                  "url": "https://docs.n8n.io/integrations/builtin/app-nodes/n8n-nodes-base.gmail/"
                }
              ],
              "credentialDocumentation": [
                {
                  "url": "https://docs.n8n.io/integrations/builtin/credentials/google/oauth-single-service/"
                }
              ]
            },
            "categories": [
              "Communication",
              "HITL"
            ],
            "nodeVersion": "1.0",
            "codexVersion": "1.0",
            "subcategories": {
              "HITL": [
                "Human in the Loop"
              ]
            }
          }
        },
        "group": "[\"transform\"]",
        "defaults": {
          "name": "Gmail"
        },
        "iconData": {
          "type": "file",
          "fileBuffer": "data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHdpZHRoPSIyNTYiIGhlaWdodD0iMTkzIiBwcmVzZXJ2ZUFzcGVjdFJhdGlvPSJ4TWlkWU1pZCI+PHBhdGggZmlsbD0iIzQyODVGNCIgZD0iTTU4LjE4MiAxOTIuMDVWOTMuMTRMMjcuNTA3IDY1LjA3NyAwIDQ5LjUwNHYxMjUuMDkxYzAgOS42NTggNy44MjUgMTcuNDU1IDE3LjQ1NSAxNy40NTV6Ii8+PHBhdGggZmlsbD0iIzM0QTg1MyIgZD0iTTE5Ny44MTggMTkyLjA1aDQwLjcyN2M5LjY1OSAwIDE3LjQ1NS03LjgyNiAxNy40NTUtMTcuNDU1VjQ5LjUwNWwtMzEuMTU2IDE3LjgzNy0yNy4wMjYgMjUuNzk4eiIvPjxwYXRoIGZpbGw9IiNFQTQzMzUiIGQ9Im01OC4xODIgOTMuMTQtNC4xNzQtMzguNjQ3IDQuMTc0LTM2Ljk4OUwxMjggNjkuODY4bDY5LjgxOC01Mi4zNjQgNC42NyAzNC45OTItNC42NyA0MC42NDRMMTI4IDE0NS41MDR6Ii8+PHBhdGggZmlsbD0iI0ZCQkMwNCIgZD0iTTE5Ny44MTggMTcuNTA0VjkzLjE0TDI1NiA0OS41MDRWMjYuMjMxYzAtMjEuNTg1LTI0LjY0LTMzLjg5LTQxLjg5LTIwLjk0NXoiLz48cGF0aCBmaWxsPSIjQzUyMjFGIiBkPSJtMCA0OS41MDQgMjYuNzU5IDIwLjA3TDU4LjE4MiA5My4xNFYxNy41MDRMNDEuODkgNS4yODZDMjQuNjEtNy42NiAwIDQuNjQ2IDAgMjYuMjN6Ii8+PC9zdmc+"
        },
        "displayName": "Gmail",
        "typeVersion": 2,
        "nodeCategories": [
          {
            "id": 6,
            "name": "Communication"
          },
          {
            "id": 28,
            "name": "HITL"
          }
        ]
      },
      {
        "id": 824,
        "icon": "file:gmail.svg",
        "name": "n8n-nodes-base.gmailTrigger",
        "codex": {
          "data": {
            "resources": {
              "generic": [
                {
                  "url": "https://n8n.io/blog/why-business-process-automation-with-n8n-can-change-your-daily-life/",
                  "icon": "🧬",
                  "label": "Why business process automation with n8n can change your daily life"
                },
                {
                  "url": "https://n8n.io/blog/supercharging-your-conference-registration-process-with-n8n/",
                  "icon": "🎫",
                  "label": "Supercharging your conference registration process with n8n"
                },
                {
                  "url": "https://n8n.io/blog/no-code-ecommerce-workflow-automations/",
                  "icon": "store",
                  "label": "6 e-commerce workflows to power up your Shopify s"
                },
                {
                  "url": "https://n8n.io/blog/how-to-get-started-with-crm-automation-and-no-code-workflow-ideas/",
                  "icon": "👥",
                  "label": "How to get started with CRM automation (with 3 no-code workflow ideas"
                },
                {
                  "url": "https://n8n.io/blog/automate-google-apps-for-productivity/",
                  "icon": "💡",
                  "label": "15 Google apps you can combine and automate to increase productivity"
                },
                {
                  "url": "https://n8n.io/blog/your-business-doesnt-need-you-to-operate/",
                  "icon": " 🖥️",
                  "label": "Hey founders! Your business doesn't need you to operate"
                },
                {
                  "url": "https://n8n.io/blog/using-automation-to-boost-productivity-in-the-workplace/",
                  "icon": "💪",
                  "label": "Using Automation to Boost Productivity in the Workplace"
                }
              ],
              "primaryDocumentation": [
                {
                  "url": "https://docs.n8n.io/integrations/builtin/trigger-nodes/n8n-nodes-base.gmailtrigger/"
                }
              ],
              "credentialDocumentation": [
                {
                  "url": "https://docs.n8n.io/integrations/builtin/credentials/google/oauth-single-service/"
                }
              ]
            },
            "categories": [
              "Communication"
            ],
            "nodeVersion": "1.0",
            "codexVersion": "1.0"
          }
        },
        "group": "[\"trigger\"]",
        "defaults": {
          "name": "Gmail Trigger"
        },
        "iconData": {
          "type": "file",
          "fileBuffer": "data:image/svg+xml;base64,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"
        },
        "displayName": "Gmail Trigger",
        "typeVersion": 1,
        "nodeCategories": [
          {
            "id": 6,
            "name": "Communication"
          }
        ]
      },
      {
        "id": 834,
        "icon": "file:code.svg",
        "name": "n8n-nodes-base.code",
        "codex": {
          "data": {
            "alias": [
              "cpde",
              "Javascript",
              "JS",
              "Python",
              "Script",
              "Custom Code",
              "Function"
            ],
            "details": "The Code node allows you to execute JavaScript in your workflow.",
            "resources": {
              "primaryDocumentation": [
                {
                  "url": "https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-base.code/"
                }
              ]
            },
            "categories": [
              "Development",
              "Core Nodes"
            ],
            "nodeVersion": "1.0",
            "codexVersion": "1.0",
            "subcategories": {
              "Core Nodes": [
                "Helpers",
                "Data Transformation"
              ]
            }
          }
        },
        "group": "[\"transform\"]",
        "defaults": {
          "name": "Code"
        },
        "iconData": {
          "type": "file",
          "fileBuffer": "data:image/svg+xml;base64,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"
        },
        "displayName": "Code",
        "typeVersion": 2,
        "nodeCategories": [
          {
            "id": 5,
            "name": "Development"
          },
          {
            "id": 9,
            "name": "Core Nodes"
          }
        ]
      },
      {
        "id": 1119,
        "icon": "fa:robot",
        "name": "@n8n/n8n-nodes-langchain.agent",
        "codex": {
          "data": {
            "alias": [
              "LangChain",
              "Chat",
              "Conversational",
              "Plan and Execute",
              "ReAct",
              "Tools"
            ],
            "resources": {
              "primaryDocumentation": [
                {
                  "url": "https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/"
                }
              ]
            },
            "categories": [
              "AI",
              "Langchain"
            ],
            "subcategories": {
              "AI": [
                "Agents",
                "Root Nodes"
              ]
            }
          }
        },
        "group": "[\"transform\"]",
        "defaults": {
          "name": "AI Agent",
          "color": "#404040"
        },
        "iconData": {
          "icon": "robot",
          "type": "icon"
        },
        "displayName": "AI Agent",
        "typeVersion": 3,
        "nodeCategories": [
          {
            "id": 25,
            "name": "AI"
          },
          {
            "id": 26,
            "name": "Langchain"
          }
        ]
      },
      {
        "id": 1145,
        "icon": "file:anthropic.svg",
        "name": "@n8n/n8n-nodes-langchain.lmChatAnthropic",
        "codex": {
          "data": {
            "alias": [
              "claude",
              "sonnet",
              "opus"
            ],
            "resources": {
              "primaryDocumentation": [
                {
                  "url": "https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatanthropic/"
                }
              ]
            },
            "categories": [
              "AI",
              "Langchain"
            ],
            "subcategories": {
              "AI": [
                "Language Models",
                "Root Nodes"
              ],
              "Language Models": [
                "Chat Models (Recommended)"
              ]
            }
          }
        },
        "group": "[\"transform\"]",
        "defaults": {
          "name": "Anthropic Chat Model"
        },
        "iconData": {
          "type": "file",
          "fileBuffer": "data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHdpZHRoPSI0NiIgaGVpZ2h0PSIzMiIgZmlsbD0ibm9uZSI+PHBhdGggZmlsbD0iIzdEN0Q4NyIgZD0iTTMyLjczIDBoLTYuOTQ1TDM4LjQ1IDMyaDYuOTQ1ek0xMi42NjUgMCAwIDMyaDcuMDgybDIuNTktNi43MmgxMy4yNWwyLjU5IDYuNzJoNy4wODJMMTkuOTI5IDB6bS0uNzAyIDE5LjMzNyA0LjMzNC0xMS4yNDYgNC4zMzQgMTEuMjQ2eiIvPjwvc3ZnPg=="
        },
        "displayName": "Anthropic Chat Model",
        "typeVersion": 2,
        "nodeCategories": [
          {
            "id": 25,
            "name": "AI"
          },
          {
            "id": 26,
            "name": "Langchain"
          }
        ]
      },
      {
        "id": 1235,
        "icon": "file:extractFromFile.svg",
        "name": "n8n-nodes-base.extractFromFile",
        "codex": {
          "data": {
            "alias": [
              "CSV",
              "Spreadsheet",
              "Excel",
              "xls",
              "xlsx",
              "ods",
              "tabular",
              "decode",
              "decoding",
              "Move Binary Data",
              "Binary",
              "File",
              "PDF",
              "JSON",
              "HTML",
              "ICS",
              "iCal",
              "txt",
              "Text",
              "RTF",
              "XML",
              "64",
              "Base64",
              "Convert"
            ],
            "resources": {
              "primaryDocumentation": [
                {
                  "url": "https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-base.extractfromfile/"
                }
              ]
            },
            "categories": [
              "Core Nodes"
            ],
            "nodeVersion": "1.0",
            "codexVersion": "1.0",
            "subcategories": {
              "Core Nodes": [
                "Files",
                "Data Transformation"
              ]
            }
          }
        },
        "group": "[\"input\"]",
        "defaults": {
          "name": "Extract from File"
        },
        "iconData": {
          "type": "file",
          "fileBuffer": "data:image/svg+xml;base64,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"
        },
        "displayName": "Extract from File",
        "typeVersion": 1,
        "nodeCategories": [
          {
            "id": 9,
            "name": "Core Nodes"
          }
        ]
      },
      {
        "id": 1250,
        "icon": "file:openAi.svg",
        "name": "@n8n/n8n-nodes-langchain.openAi",
        "codex": {
          "data": {
            "alias": [
              "LangChain",
              "ChatGPT",
              "Sora",
              "DallE",
              "whisper",
              "audio",
              "transcribe",
              "tts",
              "assistant"
            ],
            "resources": {
              "primaryDocumentation": [
                {
                  "url": "https://docs.n8n.io/integrations/builtin/app-nodes/n8n-nodes-langchain.openai/"
                }
              ]
            },
            "categories": [
              "AI",
              "Langchain"
            ],
            "subcategories": {
              "AI": [
                "Agents",
                "Miscellaneous",
                "Root Nodes"
              ]
            }
          }
        },
        "group": "[\"transform\"]",
        "defaults": {
          "name": "OpenAI"
        },
        "iconData": {
          "type": "file",
          "fileBuffer": "data:image/svg+xml;base64,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"
        },
        "displayName": "OpenAI",
        "typeVersion": 2,
        "nodeCategories": [
          {
            "id": 25,
            "name": "AI"
          },
          {
            "id": 26,
            "name": "Langchain"
          }
        ]
      }
    ],
    "categories": [
      {
        "id": 31,
        "name": "Content Creation"
      },
      {
        "id": 51,
        "name": "Multimodal AI"
      }
    ],
    "image": []
  }
}