← Retour aux workflows
Workflow n8n

Automatisation n8n : génération d'articles de base de connaissances

Ce workflow n8n a pour objectif de faciliter la création d'articles pour une base de connaissances en automatisant le processus de génération de contenu. Dans un contexte où les entreprises cherchent à enrichir leur documentation et à améliorer l'accès à l'information pour leurs utilisateurs, cette automatisation n8n se révèle particulièrement utile. Elle permet de générer des articles de manière rapide et efficace, en utilisant des modèles d'intelligence artificielle pour créer du contenu pertinent et informatif. Le workflow commence par un déclencheur qui active le processus lorsqu'un message de chat est reçu. Ensuite, il utilise des nœuds comme 'Create Perplexity Content' pour générer le contenu initial, suivi par des agents d'écriture et d'édition AI qui affinent et améliorent le texte. Les modèles de chat OpenAI sont intégrés pour enrichir le contenu avec des réponses contextuelles. Une fois le contenu généré, il est formaté et publié automatiquement dans la base de connaissances. Ce processus réduit considérablement le temps nécessaire à la création d'articles tout en garantissant la qualité du contenu. En fin de compte, cette automatisation permet aux équipes de se concentrer sur des tâches à plus forte valeur ajoutée, tout en améliorant l'expérience utilisateur grâce à un accès rapide à des informations précises.

Tags clés :automatisationAIn8ngénération de contenubase de connaissances
🎯Pour qui ?🧩Problème résolu📋Étapes du flux🛠Guide de personnalisation
Catégorie: Webhook · Tags: automatisation, AI, n8n, génération de contenu, base de connaissances❤ 0

Workflow n8n génération de contenu, base de connaissances : vue d'ensemble

Schéma des nœuds et connexions de ce workflow n8n, généré à partir du JSON n8n.

React Flow
Besoin d'aide ?

Workflow n8n génération de contenu, base de connaissances : détail des nœuds

  • Create Perplexity Content

    Ce noeud envoie une requête HTTP pour créer du contenu sur Perplexity.

  • AI Writer Agent

    Ce noeud utilise un agent d'écriture AI pour générer du texte basé sur des options et un type de prompt.

  • AI Editor Agent

    Ce noeud utilise un agent d'édition AI pour modifier du texte selon des options et un type de prompt.

  • OpenAI Chat Model

    Ce noeud interagit avec le modèle de chat OpenAI pour générer des réponses basées sur des options.

  • OpenAI Chat Model1

    Ce noeud interagit avec un autre modèle de chat OpenAI pour produire des réponses en fonction des options fournies.

  • Accept and Publish

    Ce noeud accepte et publie un workflow en utilisant les entrées et la description fournies.

  • When chat message received

    Ce noeud déclenche le workflow lorsqu'un message de chat est reçu.

  • JSON.parse1

    Ce noeud exécute un code JavaScript pour analyser un JSON.

  • Merge

    Ce noeud fusionne les données provenant de plusieurs entrées.

  • Format

    Ce noeud exécute un code JavaScript pour formater des données.

  • JSON.parse

    Ce noeud exécute un code JavaScript pour analyser un JSON.

  • Format Perplexity Output & Add Citations

    Ce noeud formate la sortie de Perplexity et ajoute des citations.

  • Initialize Count

    Ce noeud initialise un compteur avec des valeurs spécifiées.

  • Increment Count

    Ce noeud incrémente le compteur en exécutant un code fonctionnel.

  • Check Limit

    Ce noeud vérifie si une condition de limite est atteinte.

  • Stop Here

    Ce noeud ne fait rien et sert de point d'arrêt dans le workflow.

  • Execute Workflow

    Ce noeud exécute un autre workflow avec les options et les entrées fournies.

  • JSON.parse3

    Ce noeud exécute un code JavaScript pour analyser un JSON.

  • should submit

    Ce noeud vérifie si une condition de soumission est remplie.

  • Sticky Note

    Ce noeud crée une note autocollante avec des paramètres de couleur, taille et contenu.

  • Sticky Note1

    Ce noeud crée une autre note autocollante avec des paramètres de couleur, taille et contenu.

  • Sticky Note2

    Ce noeud crée une note autocollante avec des paramètres de taille et de contenu.

  • Sticky Note3

    Ce noeud crée une note autocollante avec des paramètres de couleur, taille et contenu.

Inscris-toi pour voir l'intégralité du workflow

Inscription gratuite

S'inscrire gratuitementBesoin d'aide ?
{
  "id": "WwEFqNK4YP6UJcg2",
  "meta": {
    "instanceId": "6bcff5ef8a06e8086902526a05c2a4c7bf5da8101f89e582301ed78094606f40",
    "templateCredsSetupCompleted": true
  },
  "name": "Auto Knowledge Base Article Generator",
  "tags": [],
  "nodes": [
    {
      "id": "17900021-8da3-4bd9-9d79-5d20d879ddc7",
      "name": "Create Perplexity Content",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        1220,
        380
      ],
      "parameters": {
        "url": "https://api.perplexity.ai/chat/completions",
        "method": "POST",
        "options": {},
        "jsonBody": "={\n  \"model\": \"sonar-deep-research\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Conduct an in-depth research on '{{ $json.output.parseJson().title }}', covering essential topics, recommended resources, and best practices. Additionally, please address these improvements: '{{ $json.output.parseJson().improvements }}'. The returned data should be at least 1000 words and use a combination of headers, tables, bold, and italics\"\n    }\n  ],\n  \"max_tokens\": 60000,\n  \"temperature\": 0.7,\n  \"top_p\": 0.9,\n  \"top_k\": 50,\n  \"stream\": false,\n  \"presence_penalty\": 0,\n  \"frequency_penalty\": 0\n}",
        "sendBody": true,
        "jsonHeaders": "{\n  \"Authorization\": \"Bearer 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\",\n  \"Content-Type\": \"application/json\"\n}",
        "sendHeaders": true,
        "specifyBody": "json",
        "specifyHeaders": "json"
      },
      "typeVersion": 4.2
    },
    {
      "id": "0cb3f3a7-92bd-4ff3-8a89-b6fc29513e65",
      "name": "AI Writer Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        720,
        380
      ],
      "parameters": {
        "text": "=Please create or revise an article about \"{{ $json.chatInput }}\".\n\nOr an article is already written because title: {{ $json.title }} is defined. Reference it to rewrite the {{ $json.content }} field\n\nDo not change the title, either the chatinput or the input article title. This is the title, do not change it.\n\nIf an article is NOT given, pick new categories in:\n- getting-started\n- learning-paths\n- certifications\n- programming\n- applications\n- career\n\nDo not make up a category, it should be the same in the exact case as above\n\nIf an article is given, only make ammendments to the content based on these specific improvements to include: \"{{ $json.improvements }}\".\n\nInclude the improvements key only if it is an input, and in that case don't change it\n\nRemember to return valid JSON with the fields:\n{\n  \"title\": \"...\",\n  \"slug\": \"...\",\n  \"category\": {\n    \"id\": \"...\"\n  },\n  \"description\": \"...\",\n  \"keywords\": [...],\n  \"content\": \"...\",\n  \"metaTitle\": \"...\",\n  \"metaDescription\": \"...\",\n  \"readingTime\": \"...\",\n  \"difficulty\": \"...\"\n  \"content\": \"...\"\n}",
        "options": {
          "systemMessage": "You are a writing assistant. You will receive instructions to create or update an article in JSON format with the following structure:\n\n{\n  \"title\": \"<string>\",\n  \"slug\": \"<string>\",\n  \"category\": {\n    \"id\": \"<string>\" // e.g., \"getting-started\", \"learning-paths\", etc.\n  },\n  \"description\": \"<string>\",\n  \"keywords\": [\"<string>\", \"<string>\", ...],\n  \"content\": \"<string>\",\n  \"metaTitle\": \"<string>\",\n  \"metaDescription\": \"<string>\",\n  \"readingTime\": \"<number or string>\",\n  \"difficulty\": \"<string>\"\n}\n\nYour task:\n1. Produce a complete article in the above format, or revise the existing article if provided.\n2. Make sure the text is clear, specific, and helpful to the reader.\n3. Return valid JSON only – do not include extra commentary or fields beyond the above structure.\n4. If any information is missing from the user instructions, make reasonable assumptions.\n"
        },
        "promptType": "define"
      },
      "typeVersion": 1.7
    },
    {
      "id": "bc62facb-c5cb-465d-89b1-a65a893c3ce1",
      "name": "AI Editor Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        2280,
        380
      ],
      "parameters": {
        "text": "={{ $json }}",
        "options": {
          "maxIterations": 5,
          "systemMessage": "=You are an editorial AI assistant. Your role is to review and evaluate a draft article represented as a JSON object.\n\nCategory IDs:\n- \"getting-started\"\n- \"learning-paths\"\n- \"certifications\"\n- \"programming\"\n- \"applications\"\n- \"career\"\n\nInput Format:\n\n{\n  \"title\": \"<string>\",\n  \"slug\": \"<string>\",\n  \"category\": { \"id\": \"<string>\" },\n  \"description\": \"<string>\",\n  \"keywords\": [\"<string>\", \"...\"],\n  \"content\": \"<string>\",\n  \"metaTitle\": \"<string>\",\n  \"metaDescription\": \"<string>\",\n  \"readingTime\": \"<string | number>\",\n  \"difficulty\": \"<string>\"\n}\n\nYour Tasks:\n\n1. Evaluate the quality of the article — especially the title, description, content, and metadata.\n2. Comment on clarity, specificity, usefulness, and overall quality.\n3. If improvements are needed, add an \"improvements\" field describing exactly what to fix.\n4. Set the \"action\" field:\n- \"rewrite\" if improvements are needed.\n- \"submit\" if the article is high quality.\n5. Include all fields from the original input in your output.\n6. If \"action\" is \"submit\", set \"improvements\" to null.\n7. Avoid repeating feedback across iterations.\n8. After 2 iterations, automatically call the accept-and-publish tool and set the \"action\" to \"submit\".\n9. VERY IMPORTANT: Do NOT modify any of the input fields\n10. VERY IMPORTANT: Do NOT truncate the sources or modify the content field in any way\n\n✅ Output Format:\n\n{\n  \"title\": \"...\",\n  \"action\": \"rewrite | submit\",\n  \"improvements\": \"... | null\",\n  \"slug\": \"...\",\n  \"category\": {\n    \"id\": \"...\"\n  },\n  \"description\": \"...\",\n  \"keywords\": [\"...\"],\n  \"content\": \"...\",\n  \"metaTitle\": \"...\",\n  \"metaDescription\": \"...\",\n  \"readingTime\": \"...\",\n  \"difficulty\": \"...\"\n}\n\nTone: Be concise, direct, and constructive. Focus on maximizing clarity, usefulness, and readability for the end reader."
        },
        "promptType": "define",
        "hasOutputParser": true
      },
      "retryOnFail": true,
      "typeVersion": 1.7
    },
    {
      "id": "8c08d67a-b916-4cfd-89cd-16b34250bcb2",
      "name": "OpenAI Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        680,
        640
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-3.5-turbo",
          "cachedResultName": "gpt-3.5-turbo"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "KLN8ZfDzv8mW6pyu",
          "name": "OpenAi account"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "97bb1374-f502-4152-a5a3-bc5d46a18171",
      "name": "OpenAI Chat Model1",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        2200,
        660
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4.5-preview",
          "cachedResultName": "gpt-4.5-preview"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "KLN8ZfDzv8mW6pyu",
          "name": "OpenAi account"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "1c422e76-5b1a-4615-b379-ab39d4bd13b4",
      "name": "Accept and Publish",
      "type": "@n8n/n8n-nodes-langchain.toolWorkflow",
      "position": [
        2500,
        680
      ],
      "parameters": {
        "name": "submit",
        "workflowId": {
          "__rl": true,
          "mode": "list",
          "value": "uIREtTV8TRuF3lru",
          "cachedResultName": "Publish to Contentful"
        },
        "description": "Call this tool when the article quality is above the threshold we need",
        "workflowInputs": {
          "value": {
            "slug": "=  {{ $json.slug }}",
            "title": "={{ $('Format').item.json.title }}",
            "content": "={{ $json.content }}",
            "category": "={{ $json.category }}",
            "keywords": "={{ $json.keywords }}",
            "metaTitle": "={{ $json.metaTitle }}",
            "difficulty": "={{ $json.difficulty }}",
            "description": "={{ $json.description }}",
            "readingTime": "={{ $json.readingTime }}",
            "metaDescription": "={{ $json.metaDescription }}"
          },
          "schema": [
            {
              "id": "title",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "title",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "action",
              "type": "string",
              "display": true,
              "removed": true,
              "required": false,
              "displayName": "action",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "improvements",
              "type": "string",
              "display": true,
              "removed": true,
              "required": false,
              "displayName": "improvements",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "slug",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "slug",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "category",
              "type": "object",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "category",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "description",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "description",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "keywords",
              "type": "array",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "keywords",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "content",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "content",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "metaTitle",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "metaTitle",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "metaDescription",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "metaDescription",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "readingTime",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "readingTime",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "difficulty",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "difficulty",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            }
          ],
          "mappingMode": "defineBelow",
          "matchingColumns": [],
          "attemptToConvertTypes": false,
          "convertFieldsToString": false
        }
      },
      "typeVersion": 2
    },
    {
      "id": "b6807e84-900a-48fc-a869-862824c62ba1",
      "name": "When chat message received",
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "position": [
        -60,
        660
      ],
      "webhookId": "7ed20abc-d8bc-4426-95f1-b9778c075ddf",
      "parameters": {
        "public": true,
        "options": {},
        "initialMessages": "What topics should I write about?"
      },
      "typeVersion": 1.1
    },
    {
      "id": "e3021ac4-9444-4689-af0c-a4bbd4729c35",
      "name": "JSON.parse1",
      "type": "n8n-nodes-base.code",
      "position": [
        1320,
        120
      ],
      "parameters": {
        "mode": "runOnceForEachItem",
        "jsCode": "const outputText = $json.output;\n\n// Parse JSON from ChatGPT response\nconst parsedOutput = JSON.parse(outputText);\n\n// Return parsed object for next nodes\nreturn parsedOutput;"
      },
      "typeVersion": 2
    },
    {
      "id": "d6a5eccd-c8e3-4ee0-beb0-7b8fc8428b91",
      "name": "Merge",
      "type": "n8n-nodes-base.merge",
      "position": [
        1840,
        380
      ],
      "parameters": {
        "numberInputs": 3
      },
      "typeVersion": 3
    },
    {
      "id": "8461a1a0-a984-4ec1-bc93-3a1a312caf55",
      "name": "Format",
      "type": "n8n-nodes-base.code",
      "position": [
        2060,
        380
      ],
      "parameters": {
        "jsCode": "// Get all items passed into this node as an array\nconst items = $input.all();\n\n// If you always have at least two items:\nconst firstItem = items[0].json;\nconst secondItem = items[1].json;\nconst thirdItem = items[2].json;\n\n// Overwrite the first item’s “content” with the second item’s “content”\nfirstItem.content = secondItem.content;\nfirstItem.iterationCount = thirdItem.iterationCount\n\n// Return a single new item containing the merged result\nreturn [\n  {\n    json: firstItem\n  }\n];"
      },
      "typeVersion": 2
    },
    {
      "id": "9b9a82fb-990c-4be0-aee9-ed80f0631c28",
      "name": "JSON.parse",
      "type": "n8n-nodes-base.code",
      "position": [
        3300,
        840
      ],
      "parameters": {
        "mode": "runOnceForEachItem",
        "jsCode": "const outputText = $json.output;\n\n// Parse JSON from ChatGPT response\nconst parsedOutput = JSON.parse(outputText);\n\n// Return parsed object for next nodes\nreturn parsedOutput;"
      },
      "typeVersion": 2
    },
    {
      "id": "066dfd10-e97a-44a8-89e0-5b2b5c4a6244",
      "name": "Format Perplexity Output & Add Citations",
      "type": "n8n-nodes-base.code",
      "position": [
        1480,
        380
      ],
      "parameters": {
        "mode": "runOnceForEachItem",
        "jsCode": "const data = { ...$json };\n\n// Clean out <think> block if present\ndata.content = $json.choices[0].message.content.replace(/<think>[\\s\\S]*?<\\/think>/g, '').trim();\n\n// Convert citations array to markdown link list\nconst citations = $json.citations\n  .map((url, i) => `- [${i + 1}](${url})`)\n  .join('\\n');\n\ndata.content += `\\n\\n---\\n\\n### Sources\\n${citations}`;\n\nreturn data;"
      },
      "typeVersion": 2
    },
    {
      "id": "fc9d9e93-568a-41af-a295-8736617b157e",
      "name": "Initialize Count",
      "type": "n8n-nodes-base.set",
      "position": [
        340,
        660
      ],
      "parameters": {
        "values": {
          "number": [
            {
              "name": "iterationCount"
            }
          ]
        },
        "options": {}
      },
      "typeVersion": 1
    },
    {
      "id": "b0e636dd-f572-4ee2-832f-4bb4167b011b",
      "name": "Increment Count",
      "type": "n8n-nodes-base.function",
      "position": [
        1400,
        740
      ],
      "parameters": {
        "functionCode": "const current = $json.iterationCount || 0;\n\nreturn [{ iterationCount: current + 1 }];"
      },
      "typeVersion": 1
    },
    {
      "id": "86689f0e-9607-4eda-bcd6-36241d0cbe63",
      "name": "Check Limit",
      "type": "n8n-nodes-base.if",
      "position": [
        2660,
        380
      ],
      "parameters": {
        "conditions": {
          "number": [
            {
              "value1": "={{ $json.iterationCount }}",
              "value2": 3,
              "operation": "largerEqual"
            }
          ]
        }
      },
      "typeVersion": 1
    },
    {
      "id": "0f42b0f3-0b96-40df-9c06-2a6d31e142d9",
      "name": "Stop Here",
      "type": "n8n-nodes-base.noOp",
      "position": [
        2980,
        300
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "1e61b3ba-e9bd-43c7-8217-d4a22f707318",
      "name": "Execute Workflow",
      "type": "n8n-nodes-base.executeWorkflow",
      "position": [
        3740,
        300
      ],
      "parameters": {
        "options": {},
        "workflowId": {
          "__rl": true,
          "mode": "list",
          "value": "uIREtTV8TRuF3lru",
          "cachedResultName": "Publish to Contentful"
        },
        "workflowInputs": {
          "value": {
            "slug": "={{ $json.slug }}",
            "title": "={{ $json.title }}",
            "content": "={{ $json.content }}",
            "category": "={{ $json.category }}",
            "keywords": "={{ $json.keywords }}",
            "metaTitle": "={{ $json.metaTitle }}",
            "difficulty": "={{ $json.difficulty }}",
            "description": "={{ $json.description }}",
            "readingTime": "={{ $json.readingTime }}",
            "metaDescription": "={{ $json.metaDescription }}"
          },
          "schema": [
            {
              "id": "title",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "title",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "slug",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "slug",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "category",
              "type": "object",
              "display": true,
              "required": false,
              "displayName": "category",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "description",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "description",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "keywords",
              "type": "array",
              "display": true,
              "required": false,
              "displayName": "keywords",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "content",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "content",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "metaTitle",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "metaTitle",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "metaDescription",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "metaDescription",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "readingTime",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "readingTime",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "difficulty",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "difficulty",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            }
          ],
          "mappingMode": "defineBelow",
          "matchingColumns": [],
          "attemptToConvertTypes": false,
          "convertFieldsToString": true
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "04526224-e48c-4032-9c92-475c6bf9cd0a",
      "name": "JSON.parse3",
      "type": "n8n-nodes-base.code",
      "position": [
        3280,
        300
      ],
      "parameters": {
        "mode": "runOnceForEachItem",
        "jsCode": "const outputText = $json.output;\n\n// Parse JSON from ChatGPT response\nconst parsedOutput = JSON.parse(outputText);\n\n// Return parsed object for next nodes\nreturn parsedOutput;"
      },
      "typeVersion": 2
    },
    {
      "id": "0303ab91-b788-4074-a15d-239565528dec",
      "name": "should submit",
      "type": "n8n-nodes-base.if",
      "position": [
        2980,
        680
      ],
      "parameters": {
        "options": {},
        "conditions": {
          "options": {
            "version": 2,
            "leftValue": "",
            "caseSensitive": true,
            "typeValidation": "strict"
          },
          "combinator": "and",
          "conditions": [
            {
              "id": "3c1f6cb2-a556-4c74-885e-05e4f757997b",
              "operator": {
                "name": "filter.operator.equals",
                "type": "string",
                "operation": "equals"
              },
              "leftValue": "submit",
              "rightValue": "={{ $json.output.parseJson().action }}"
            }
          ]
        }
      },
      "typeVersion": 2.2
    },
    {
      "id": "4f68e1ad-0b7c-41ca-a9cc-d220017cc1bd",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        540,
        80
      ],
      "parameters": {
        "color": 6,
        "width": 940,
        "height": 680,
        "content": "## Writer Agent\n\n- Focuses on writing for all the fields in contentful\n- Has a specified format for input and output\n- Handles implementing feedback from editor agent"
      },
      "typeVersion": 1
    },
    {
      "id": "f5e9968a-0681-4b72-9bb3-98750f55565e",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        2620,
        120
      ],
      "parameters": {
        "color": 3,
        "width": 860,
        "height": 880,
        "content": "## Count Incrementer\n\n- Tracks a variable count to ensure the flow hits a max number of feedback iterations.\n- This is critical for feedback to avoid hitting an infinite loop."
      },
      "typeVersion": 1
    },
    {
      "id": "462e6c9a-162a-4f66-b846-14b29517454c",
      "name": "Sticky Note2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        2140,
        160
      ],
      "parameters": {
        "width": 460,
        "height": 640,
        "content": "## Editor Agent\n\n- Sole purpose is to look at the quality of output for the previous combo of perplexity & openAI Agent.\n- Determines if it is publishable or not."
      },
      "typeVersion": 1
    },
    {
      "id": "27149a0a-ab95-4f73-a20c-34167ac56d2a",
      "name": "Sticky Note3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        3580,
        60
      ],
      "parameters": {
        "color": 4,
        "width": 460,
        "height": 480,
        "content": "## Publish To Contentful\n\n- Publishes to Contentful by converting the fields to the appropriate fields for the contentful POST create content API.\n- Converts the article to Rich Text formatting specifically for Contentful by using another AI formatter trained on it's specs.\n\nemail us if you want that flow too: christian@varritech.com"
      },
      "typeVersion": 1
    }
  ],
  "active": true,
  "pinData": {},
  "settings": {
    "callerPolicy": "workflowsFromSameOwner",
    "errorWorkflow": "AKus9UvKRJfvTZBA",
    "executionOrder": "v1",
    "executionTimeout": 1800
  },
  "versionId": "69ce37b2-0909-4d9e-af89-992e22888bd8",
  "connections": {
    "Merge": {
      "main": [
        [
          {
            "node": "Format",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Format": {
      "main": [
        [
          {
            "node": "AI Editor Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Stop Here": {
      "main": [
        [
          {
            "node": "JSON.parse3",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "JSON.parse": {
      "main": [
        [
          {
            "node": "AI Writer Agent",
            "type": "main",
            "index": 0
          },
          {
            "node": "Increment Count",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Check Limit": {
      "main": [
        [
          {
            "node": "Stop Here",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "should submit",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "JSON.parse1": {
      "main": [
        [
          {
            "node": "Merge",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "JSON.parse3": {
      "main": [
        [
          {
            "node": "Execute Workflow",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "should submit": {
      "main": [
        [
          {
            "node": "JSON.parse3",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "JSON.parse",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "AI Editor Agent": {
      "main": [
        [
          {
            "node": "Check Limit",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "AI Writer Agent": {
      "main": [
        [
          {
            "node": "Create Perplexity Content",
            "type": "main",
            "index": 0
          },
          {
            "node": "JSON.parse1",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Increment Count": {
      "main": [
        [
          {
            "node": "Merge",
            "type": "main",
            "index": 2
          }
        ]
      ]
    },
    "Initialize Count": {
      "main": [
        [
          {
            "node": "AI Writer Agent",
            "type": "main",
            "index": 0
          },
          {
            "node": "Increment Count",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "AI Writer Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Accept and Publish": {
      "ai_tool": [
        [
          {
            "node": "AI Editor Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model1": {
      "ai_languageModel": [
        [
          {
            "node": "AI Editor Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Create Perplexity Content": {
      "main": [
        [
          {
            "node": "Format Perplexity Output & Add Citations",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "When chat message received": {
      "main": [
        [
          {
            "node": "Initialize Count",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Format Perplexity Output & Add Citations": {
      "main": [
        [
          {
            "node": "Merge",
            "type": "main",
            "index": 1
          }
        ]
      ]
    }
  }
}

Workflow n8n génération de contenu, base de connaissances : pour qui est ce workflow ?

Ce workflow s'adresse aux équipes de support client, aux rédacteurs techniques et aux responsables de la documentation au sein des entreprises de taille moyenne à grande. Il est conçu pour des utilisateurs ayant un niveau technique intermédiaire, souhaitant automatiser la création de contenu pour améliorer l'efficacité de leurs processus.

Workflow n8n génération de contenu, base de connaissances : problème résolu

Ce workflow résout le problème de la création manuelle d'articles de base de connaissances, qui peut être long et laborieux. En automatisant ce processus, il élimine les frustrations liées à la rédaction répétitive et permet de réduire le temps consacré à la création de contenu. Les utilisateurs bénéficient d'une production rapide d'articles de qualité, ce qui améliore l'accès à l'information et la satisfaction des utilisateurs finaux.

Workflow n8n génération de contenu, base de connaissances : étapes du workflow

Étape 1 : Le workflow est déclenché par la réception d'un message de chat.

  • Étape 1 : Le contenu est généré à l'aide du nœud 'Create Perplexity Content'.
  • Étape 2 : Le texte généré est ensuite traité par l'agent d'écriture AI pour affiner le contenu.
  • Étape 3 : Un second agent d'édition AI améliore encore le texte.
  • Étape 4 : Les modèles de chat OpenAI sont utilisés pour enrichir le contenu avec des réponses contextuelles.
  • Étape 5 : Le contenu final est formaté et préparé pour publication.
  • Étape 6 : Le workflow publie automatiquement l'article dans la base de connaissances, assurant ainsi une mise à jour rapide et efficace.

Workflow n8n génération de contenu, base de connaissances : guide de personnalisation

Pour personnaliser ce workflow, vous pouvez modifier l'URL du webhook pour l'adapter à votre système de messagerie. Vous pouvez également ajuster les paramètres des nœuds AI pour affiner le style et le ton du contenu généré. Pensez à changer les modèles de chat OpenAI en fonction de vos besoins spécifiques. Pour une meilleure intégration, vous pouvez connecter d'autres outils de gestion de contenu ou de documentation. Assurez-vous de sécuriser le flux en vérifiant les permissions d'accès aux données sensibles.