{ "name": "rag_faq_extractor", "nodes": [ { "parameters": {}, "id": "b7e8c306-95d7-493a-9594-0b0549e93eeb", "name": "Manual Trigger", "type": "n8n-nodes-base.manualTrigger", "typeVersion": 1, "position": [ -1440, 80 ] }, { "parameters": { "model": "mistral-large-latest", "options": {} }, "id": "656b9cbe-b346-479f-8a27-dde776a95391", "name": "Mistral Chat Model 1", "type": "@n8n/n8n-nodes-langchain.lmChatMistralCloud", "typeVersion": 1, "position": [ -1008, 272 ], "credentials": { "mistralCloudApi": { "name": "" } } }, { "parameters": { "model": "mistral-large-latest", "options": {} }, "id": "7361d2aa-9ee4-430a-89c1-9cbfef84d0d6", "name": "Mistral Chat Model 2", "type": "@n8n/n8n-nodes-langchain.lmChatMistralCloud", "typeVersion": 1, "position": [ -272, 288 ], "credentials": { "mistralCloudApi": { "name": "" } } }, { "parameters": { "model": "mistral-large-latest", "options": {} }, "id": "e1dc4ace-daa6-48a1-ab51-2ee4aa65e6f5", "name": "Mistral Chat Model 3", "type": "@n8n/n8n-nodes-langchain.lmChatMistralCloud", "typeVersion": 1, "position": [ 608, -48 ], "credentials": { "mistralCloudApi": { "name": "" } } }, { "parameters": { "inputDataFieldName": "json_output", "name": "faq.json", "driveId": { "__rl": true, "value": "My Drive", "mode": "list", "cachedResultName": "My Drive", "cachedResultUrl": "https://drive.google.com/drive/my-drive" }, "folderId": { "__rl": true, "value": "root", "mode": "list", "cachedResultName": "/ (Root folder)", "cachedResultUrl": "https://drive.google.com/drive" }, "options": {} }, "type": "n8n-nodes-base.googleDrive", "typeVersion": 3, "position": [ 1808, -240 ], "id": "2eeeb088-b51f-4ffa-ac9e-4e0d457f0ed4", "name": "Upload file", "credentials": { "googleDriveOAuth2Api": { "name": "" } } }, { "parameters": { "url": "https://r.jina.ai/https://faq.tagheuer.com/?l=fr&c=Products:All_TAG_Heuer_Connected", "options": {} }, "id": "38daefdb-59e1-4276-83c9-f778af33a18f", "name": "Get FAQ first page", "type": "n8n-nodes-base.httpRequest", "typeVersion": 4.2, "position": [ -1216, 80 ] }, { "parameters": { "promptType": "define", "text": "=Analyse ce contenu markdown d'une page FAQ et extrait UNIQUEMENT les URLs des sous-cat\u00e9gories de la section Connected et ajoute aussi l'url : https://faq.tagheuer.com/?l=fr&c=Products:All_TAG_Heuer_Connected.\n\nContenu:\n{{ $json.data }}\n\nRetourne un JSON array avec les URLs compl\u00e8tes des sous-cat\u00e9gories. Format attendu:\n{\n \"subcategories\": [\n \"https://faq.tagheuer.com/?l=fr&c=Products:Connected:Subcategory1\",\n \"https://faq.tagheuer.com/?l=fr&c=Products:Connected:Subcategory2\"\n ]\n}\n\nRetourne UNIQUEMENT le JSON, rien d'autre." }, "id": "9b7ebca8-e46e-4dd0-89c5-b718e3b83d21", "name": "Extract categories", "type": "@n8n/n8n-nodes-langchain.chainLlm", "typeVersion": 1.4, "position": [ -1008, 80 ] }, { "parameters": { "jsCode": "// R\u00e9cup\u00e9rer la r\u00e9ponse du LLM\nconst input = $input.first().json;\nlet response = input.output || input.text || input.response || JSON.stringify(input);\n\nconsole.log('R\u00e9ponse brute du LLM:', response);\n\nlet parsed;\n\ntry {\n // Si la r\u00e9ponse est d\u00e9j\u00e0 un objet\n if (typeof response === 'object') {\n parsed = response;\n } else {\n // Nettoyer la r\u00e9ponse (enlever markdown, backticks, etc.)\n response = response.replace(/```json\\n?/g, '').replace(/```\\n?/g, '').trim();\n \n // Extraire le JSON de la r\u00e9ponse\n const jsonMatch = response.match(/\\{[\\s\\S]*\\}/);\n if (jsonMatch) {\n parsed = JSON.parse(jsonMatch[0]);\n } else {\n parsed = JSON.parse(response);\n }\n }\n} catch (e) {\n console.error('Erreur de parsing:', e.message);\n console.error('R\u00e9ponse qui a caus\u00e9 l\\'erreur:', response);\n return [{ error: 'Parsing failed', rawResponse: response }];\n}\n\nconsole.log('JSON pars\u00e9:', parsed);\n\nconst urls = parsed.subcategories || [];\n\nif (urls.length === 0) {\n console.warn('Aucune sous-cat\u00e9gorie trouv\u00e9e');\n return [{ warning: 'No subcategories found', parsed: parsed }];\n}\n\nreturn urls.map(url => ({ url: url }));" }, "id": "f86956ae-a0bc-40dc-860f-908107b0034a", "name": "Parser categories", "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ -688, 80 ] }, { "parameters": { "url": "=https://r.jina.ai/{{ $json.url }}", "options": {} }, "id": "884ea90d-9e69-42c2-85e8-89c805977aa2", "name": "Get questions / answers url by category", "type": "n8n-nodes-base.httpRequest", "typeVersion": 4.2, "position": [ -464, 80 ] }, { "parameters": { "promptType": "define", "text": "=Analyse ce contenu markdown d'une page FAQ et extrait TOUTES les questions avec leurs liens vers les r\u00e9ponses.\n\nContenu:\n{{ $json.data }}\n\nRetourne un JSON array avec les questions et URLs. Format attendu:\n{\n \"questions\": [\n {\n \"question\": \"Texte de la question\",\n \"url\": \"https://faq.tagheuer.com/...\"\n }\n ]\n}\n\nRetourne UNIQUEMENT le JSON, rien d'autre." }, "id": "20e8df4b-f238-4f8a-951b-d01d32e2b1ff", "name": "Extract questions / answers", "type": "@n8n/n8n-nodes-langchain.chainLlm", "typeVersion": 1.4, "position": [ -272, 80 ] }, { "parameters": { "language": "pythonNative", "pythonCode": "import json\nimport re\n\nresults = []\n\nfor item in _items:\n response = item[\"json\"][\"text\"]\n\n response = re.sub(r'```json\\n?', '', response, flags=re.IGNORECASE)\n response = re.sub(r'```\\n?', '', response).strip()\n\n results.extend(json.loads(response)[\"questions\"])\n\nreturn results\n" }, "id": "a1ff0f1e-8060-49ab-9183-d9584dd7cbfa", "name": "Parser questions / answers", "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 80, 80 ] }, { "parameters": { "url": "=https://r.jina.ai/{{ $('Loop Over Questions').item.json.url }}", "options": {} }, "id": "53b629bc-f4e9-4305-984e-cf7ce31fe9be", "name": "Get answer", "type": "n8n-nodes-base.httpRequest", "typeVersion": 4.2, "position": [ 1184, 112 ] }, { "parameters": { "options": {} }, "type": "n8n-nodes-base.splitInBatches", "typeVersion": 3, "position": [ 336, 80 ], "id": "86854aa5-cb4f-488e-9b99-8de90ddf7bbe", "name": "Loop Over Questions" }, { "parameters": { "amount": 10 }, "type": "n8n-nodes-base.wait", "typeVersion": 1.1, "position": [ 960, 112 ], "id": "db4ea897-23f1-4221-b0f0-70c578046da8", "name": "Wait" }, { "parameters": { "promptType": "define", "text": "=Extrait la r\u00e9ponse compl\u00e8te de cette page FAQ.\n\nContenu:\n{{ $json.data }}\n\nRetourne un JSON avec la r\u00e9ponse. Format attendu:\n{\n \"answer\": \"Texte complet de la r\u00e9ponse\"\n}\n\nRetourne UNIQUEMENT le JSON, rien d'autre." }, "id": "7574e42f-f75f-44bd-a634-4e264d5f4f32", "name": "Extract answer", "type": "@n8n/n8n-nodes-langchain.chainLlm", "typeVersion": 1.4, "position": [ 608, -256 ] }, { "parameters": { "language": "pythonNative", "pythonCode": "import json\nimport re\n\nresults = []\n\nfor item in _items:\n response = item[\"json\"][\"text\"]\n\n response = re.sub(r'```json\\n?', '', response, flags=re.IGNORECASE)\n response = re.sub(r'```\\n?', '', response).strip()\n\n results.append(json.loads(response))\n\nreturn results" }, "id": "e55b2a2b-244e-40b8-aedc-1eac9130348e", "name": "Parse answer", "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 928, -256 ] }, { "parameters": { "mode": "combine", "combineBy": "combineByPosition", "options": {} }, "type": "n8n-nodes-base.merge", "typeVersion": 3.2, "position": [ 1184, -240 ], "id": "04110840-9a2f-4e71-8ed9-4a850f744cf9", "name": "Merge1" }, { "parameters": { "language": "pythonNative", "pythonCode": "import json\nimport base64\n\noutput_items = []\nall_data = []\n\n# Collecte toutes les donn\u00e9es JSON entrantes (items)\nfor item in _items:\n all_data.append(item['json'])\n\n# Convertit le tableau d'objets JSON en une cha\u00eene JSON format\u00e9e\n# s'assurer qu'on encode en UTF-8 pour la compatibilit\u00e9\njson_string = json.dumps(all_data, indent=2, ensure_ascii=False)\njson_bytes = json_string.encode('utf8')\n\n# Cr\u00e9e les donn\u00e9es binaires au format attendu par n8n (base64)\n# Le nom du champ binaire doit \u00eatre unique, ex: 'json_output'\nbinary_data = {\n 'json_output': {\n # Encode en base64 pour le transfert\n 'data': base64.b64encode(json_bytes).decode('utf8'), \n 'mimeType': 'application/json',\n 'fileName': 'faq_complete_rag_source.json',\n 'fileSize': len(json_bytes)\n }\n}\n\n# Cr\u00e9e l'objet de sortie avec les donn\u00e9es binaires\noutput_items.append({\n 'json': {'success': True, 'message': 'JSON converti en binaire'},\n 'binary': binary_data\n})\n\nreturn output_items" }, "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 1616, -240 ], "id": "288e023a-bd03-4fec-ac93-87c3ef8cd082", "name": "Create file context" }, { "parameters": { "dataTableId": { "__rl": true, "value": "6bJjcVcg9rJne4UJ", "mode": "list", "cachedResultName": "faq", "cachedResultUrl": "/projects/yJGMCjVHH04zJMly/datatables/6bJjcVcg9rJne4UJ" }, "columns": { "mappingMode": "defineBelow", "value": { "question": "={{ $json.question }}", "answer": "={{ $json.data }}" }, "matchingColumns": [], "schema": [ { "id": "question", "displayName": "question", "required": false, "defaultMatch": false, "display": true, "type": "string", "readOnly": false, "removed": false }, { "id": "answer", "displayName": "answer", "required": false, "defaultMatch": false, "display": true, "type": "string", "readOnly": false, "removed": false } ], "attemptToConvertTypes": false, "convertFieldsToString": false }, "options": {} }, "type": "n8n-nodes-base.dataTable", "typeVersion": 1.1, "position": [ 1584, 112 ], "id": "df4335ba-af06-4fc2-b9aa-57fd845979fd", "name": "Save question / answer" }, { "parameters": { "operation": "get", "dataTableId": { "__rl": true, "value": "6bJjcVcg9rJne4UJ", "mode": "list", "cachedResultName": "faq", "cachedResultUrl": "/projects/yJGMCjVHH04zJMly/datatables/6bJjcVcg9rJne4UJ" }, "matchType": "allConditions", "filters": { "conditions": [ { "keyName": "question", "keyValue": "={{ $json.question }}" } ] } }, "type": "n8n-nodes-base.dataTable", "typeVersion": 1.1, "position": [ 544, 96 ], "id": "99f7a78b-62f6-498d-9373-0741d97e96e8", "name": "Get row(s)", "alwaysOutputData": true }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "strict", "version": 3 }, "conditions": [ { "id": "56a3c12e-911b-4144-88ea-571b5f0d699b", "leftValue": "={{ $json.id }}", "rightValue": "", "operator": { "type": "number", "operation": "notEmpty", "singleValue": true } } ], "combinator": "and" }, "options": {} }, "type": "n8n-nodes-base.if", "typeVersion": 2.3, "position": [ 752, 96 ], "id": "199a10fe-26ae-471f-95ed-2b4e981577df", "name": "If question exists" }, { "parameters": { "assignments": { "assignments": [ { "id": "3de5c651-80a8-44bc-9221-8dd3549c7a26", "name": "data", "value": "={{ $json.data }}", "type": "string" }, { "id": "3a8ef59f-b67e-474d-af62-8865f47894b4", "name": "question", "value": "={{ $('Loop Over Questions').item.json.question }}", "type": "string" } ] }, "options": {} }, "type": "n8n-nodes-base.set", "typeVersion": 3.4, "position": [ 1392, 112 ], "id": "4d36a9ed-865b-4199-ab73-07161cd60a62", "name": "Rebuild data" }, { "parameters": { "assignments": { "assignments": [ { "id": "4baf92a0-091c-427e-a50f-aae3324001d8", "name": "data", "value": "={{ $('Rebuild data').item.json.data }}", "type": "string" }, { "id": "0c04d064-da0f-41bd-b98e-058f9c761062", "name": "question", "value": "={{ $('Rebuild data').item.json.question }}", "type": "string" } ] }, "options": {} }, "type": "n8n-nodes-base.set", "typeVersion": 3.4, "position": [ 1792, 112 ], "id": "7e06d6c9-7aa9-488d-84e9-4331865062e9", "name": "Build response" }, { "parameters": { "assignments": { "assignments": [ { "id": "d3518942-62c5-4452-a9b9-5823608764df", "name": "answer", "value": "={{ $json.answer }}", "type": "string" }, { "id": "6f05e761-a887-49a4-aced-c3241005c436", "name": "question", "value": "={{ $json.question }}", "type": "string" } ] }, "options": {} }, "type": "n8n-nodes-base.set", "typeVersion": 3.4, "position": [ 1408, -240 ], "id": "9e520a50-3b69-4efd-abb7-5dd107e90fdc", "name": "Edit Fields" } ], "connections": { "Manual Trigger": { "main": [ [ { "node": "Get FAQ first page", "type": "main", "index": 0 } ] ] }, "Mistral Chat Model 1": { "ai_languageModel": [ [ { "node": "Extract categories", "type": "ai_languageModel", "index": 0 } ] ] }, "Mistral Chat Model 2": { "ai_languageModel": [ [ { "node": "Extract questions / answers", "type": "ai_languageModel", "index": 0 } ] ] }, "Mistral Chat Model 3": { "ai_languageModel": [ [ { "node": "Extract answer", "type": "ai_languageModel", "index": 0 } ] ] }, "Get FAQ first page": { "main": [ [ { "node": "Extract categories", "type": "main", "index": 0 } ] ] }, "Extract categories": { "main": [ [ { "node": "Parser categories", "type": "main", "index": 0 } ] ] }, "Parser categories": { "main": [ [ { "node": "Get questions / answers url by category", "type": "main", "index": 0 } ] ] }, "Get questions / answers url by category": { "main": [ [ { "node": "Extract questions / answers", "type": "main", "index": 0 } ] ] }, "Extract questions / answers": { "main": [ [ { "node": "Parser questions / answers", "type": "main", "index": 0 } ] ] }, "Parser questions / answers": { "main": [ [ { "node": "Loop Over Questions", "type": "main", "index": 0 } ] ] }, "Get answer": { "main": [ [ { "node": "Rebuild data", "type": "main", "index": 0 } ] ] }, "Loop Over Questions": { "main": [ [ { "node": "Extract answer", "type": "main", "index": 0 }, { "node": "Merge1", "type": "main", "index": 1 } ], [ { "node": "Get row(s)", "type": "main", "index": 0 } ] ] }, "Wait": { "main": [ [ { "node": "Get answer", "type": "main", "index": 0 } ] ] }, "Extract answer": { "main": [ [ { "node": "Parse answer", "type": "main", "index": 0 } ] ] }, "Parse answer": { "main": [ [ { "node": "Merge1", "type": "main", "index": 0 } ] ] }, "Merge1": { "main": [ [ { "node": "Edit Fields", "type": "main", "index": 0 } ] ] }, "Create file context": { "main": [ [ { "node": "Upload file", "type": "main", "index": 0 } ] ] }, "Save question / answer": { "main": [ [ { "node": "Build response", "type": "main", "index": 0 } ] ] }, "Get row(s)": { "main": [ [ { "node": "If question exists", "type": "main", "index": 0 } ] ] }, "If question exists": { "main": [ [ { "node": "Loop Over Questions", "type": "main", "index": 0 } ], [ { "node": "Wait", "type": "main", "index": 0 } ] ] }, "Rebuild data": { "main": [ [ { "node": "Save question / answer", "type": "main", "index": 0 } ] ] }, "Build response": { "main": [ [ { "node": "Loop Over Questions", "type": "main", "index": 0 } ] ] }, "Edit Fields": { "main": [ [ { "node": "Create file context", "type": "main", "index": 0 } ] ] } }, "active": false, "settings": { "executionOrder": "v1", "availableInMCP": false }, "versionId": "93ba1de9-f9e7-438a-aee7-446203760439", "meta": { "templateCredsSetupCompleted": true }, "id": "9u8lhjFWHBTpcyR6", "tags": [] }