Workflow n8n
Automatisation Google Drive avec n8n : gestion de documents AI
- Ce workflow n8n est conçu pour automatiser la gestion de documents dans Google Drive en intégrant des fonctionnalités d'intelligence artificielle. Il permet aux utilisateurs de charger des fichiers, d'extraire des métadonnées et de traiter des documents à l'aide de modèles de langage avancés comme Google Gemini et OpenAI. Ce type d'automatisation est particulièrement utile pour les équipes de gestion de documents, les entreprises qui manipulent de grandes quantités de données ou celles qui cherchent à améliorer leur efficacité opérationnelle.
- Le processus commence par un déclencheur manuel qui active le workflow. Ensuite, les fichiers sont chargés via le nœud 'Data Loader', suivi d'une étape de découpage de texte avec le 'Token Splitter'. Les données sont ensuite stockées dans un vecteur à l'aide de 'Qdrant Vector Store'. Le workflow continue avec la récupération des contenus de fichiers et l'extraction des métadonnées nécessaires. Les utilisateurs peuvent également interagir avec le modèle de chat Google Gemini pour obtenir des réponses basées sur le contenu des documents.
- Les bénéfices de cette automatisation n8n incluent une réduction significative du temps consacré à la gestion manuelle des documents, une amélioration de la précision des informations extraites et une intégration fluide avec Google Drive. En optimisant ces processus, les entreprises peuvent se concentrer sur des tâches à plus forte valeur ajoutée, tout en minimisant les erreurs humaines.
Tags clés :automatisationGoogle Driveintelligence artificiellen8ngestion de documents
Catégorie: Manual · Tags: automatisation, Google Drive, intelligence artificielle, n8n, gestion de documents❤ 0
Workflow n8n Google Drive, intelligence artificielle, gestion de documents : vue d'ensemble
Schéma des nœuds et connexions de ce workflow n8n, généré à partir du JSON n8n.
Workflow n8n Google Drive, intelligence artificielle, gestion de documents : détail des nœuds
Inscris-toi pour voir l'intégralité du workflow
Inscription gratuite
S'inscrire gratuitementBesoin d'aide ?{
"id": "8tusZTTtcyaiznEG",
"meta": {
"instanceId": "31e69f7f4a77bf465b805824e303232f0227212ae922d12133a0f96ffeab4fef",
"templateCredsSetupCompleted": true
},
"name": "🤖 AI Powered RAG Chatbot for Your Docs + Google Drive + Gemini + Qdrant",
"tags": [],
"nodes": [
{
"id": "7ad5796b-d1a0-4cc1-bed6-105ff499beeb",
"name": "Data Loader",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
620,
720
],
"parameters": {
"options": {
"metadata": {
"metadataValues": [
{
"name": "file_id",
"value": "={{ $json.id }}"
},
{
"name": "pubkey",
"value": "={{ $json.name }}"
},
{
"name": "=overarching_theme",
"value": "={{ $('Extract Meta Data').item.json.output.overarching_theme }}"
},
{
"name": "recurring_topics",
"value": "={{ $('Extract Meta Data').item.json.output.recurring_topics }}"
},
{
"name": "pain_points",
"value": "={{ $('Extract Meta Data').item.json.output.pain_points }}"
},
{
"name": "analytical_insights",
"value": "={{ $('Extract Meta Data').item.json.output.analytical_insights }}"
},
{
"name": "conclusion",
"value": "={{ $('Extract Meta Data').item.json.output.conclusion }}"
},
{
"name": "keywords",
"value": "={{ $('Extract Meta Data').item.json.output.keywords }}"
}
]
}
},
"dataType": "binary",
"binaryMode": "specificField"
},
"typeVersion": 1
},
{
"id": "84986ee2-4d79-49e8-8778-b8a955cf2174",
"name": "Token Splitter",
"type": "@n8n/n8n-nodes-langchain.textSplitterTokenSplitter",
"position": [
720,
860
],
"parameters": {
"chunkSize": 3000
},
"typeVersion": 1
},
{
"id": "82aa7016-f3af-4de8-a410-b1c802041213",
"name": "Qdrant Vector Store",
"type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
"onError": "continueRegularOutput",
"position": [
540,
520
],
"parameters": {
"mode": "insert",
"options": {},
"qdrantCollection": {
"__rl": true,
"mode": "id",
"value": "=nostr-damus-user-profiles"
}
},
"credentials": {
"qdrantApi": {
"id": "DJQ4hVAVdWZytjr2",
"name": "QdrantApi account"
}
},
"executeOnce": false,
"retryOnFail": true,
"typeVersion": 1
},
{
"id": "07f4d14a-1864-406b-946b-09c776e3038b",
"name": "Loop Over Items",
"type": "n8n-nodes-base.splitInBatches",
"onError": "continueRegularOutput",
"position": [
180,
-140
],
"parameters": {
"options": {}
},
"typeVersion": 3
},
{
"id": "b0f9b066-62de-41bc-afce-dcb4d20d100c",
"name": "Wait",
"type": "n8n-nodes-base.wait",
"position": [
1020,
840
],
"webhookId": "237d7f8a-aead-479a-b813-f407d1f37fa5",
"parameters": {},
"typeVersion": 1.1
},
{
"id": "2a883003-f5ec-409e-97e4-809360ca11ed",
"name": "When clicking ‘Test workflow’",
"type": "n8n-nodes-base.manualTrigger",
"position": [
-1160,
-280
],
"parameters": {},
"typeVersion": 1
},
{
"id": "cfbb6b77-142f-4689-b051-436f40ababe6",
"name": "Google Gemini Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
1120,
-20
],
"parameters": {
"options": {
"temperature": 0.4
},
"modelName": "models/gemini-2.0-flash-exp"
},
"credentials": {
"googlePalmApi": {
"id": "L9UNQHflYlyF9Ngd",
"name": "Google Gemini(PaLM) Api account"
}
},
"typeVersion": 1
},
{
"id": "c9c50387-64a3-473f-9ea7-509a301836a3",
"name": "Merge",
"type": "n8n-nodes-base.merge",
"position": [
820,
200
],
"parameters": {
"mode": "combine",
"options": {},
"combineBy": "combineAll"
},
"typeVersion": 3
},
{
"id": "ea143b9f-9bd8-4f3f-8979-5a0fd2691e9d",
"name": "Extract Meta Data",
"type": "@n8n/n8n-nodes-langchain.informationExtractor",
"position": [
1020,
-180
],
"parameters": {
"text": "={{ $json.data }}",
"options": {
"systemPromptTemplate": "You are an expert extraction algorithm.\nOnly extract relevant information from the text.\nIf you do not know the value of an attribute asked to extract, you may omit the attribute's value."
},
"attributes": {
"attributes": [
{
"name": "overarching_theme",
"description": "Summarize the main theme(s) discussed in the \"Overarching Theme\" section."
},
{
"name": "recurring_topics",
"description": "List the recurring topics mentioned in the \"Common Threads\" section as an array of strings."
},
{
"name": "pain_points",
"description": "Summarize the user's frustrations or challenges mentioned in the \"Pain Points\" section as an array of strings."
},
{
"name": "analytical_insights",
"description": "Extract a list of key analytical observations from the \"Analytical Insights\" section, including shifts in tone or behavior."
},
{
"name": "conclusion",
"description": "Summarize the conclusions drawn about the user’s threads and their overall focus."
},
{
"name": "keywords",
"description": "Generate a list of 10 keywords that capture the essence of the document (e.g., \"askNostr,\" \"decentralization,\" \"spam filtering\")."
}
]
}
},
"typeVersion": 1
},
{
"id": "2ddd778f-6676-4a4b-b592-536401831bc8",
"name": "Get File Contents",
"type": "n8n-nodes-base.extractFromFile",
"position": [
820,
-180
],
"parameters": {
"options": {},
"operation": "text"
},
"typeVersion": 1
},
{
"id": "cdbb8bbc-967c-4f01-b844-4d31328153df",
"name": "Download File From Google Drive",
"type": "n8n-nodes-base.googleDrive",
"position": [
500,
-180
],
"parameters": {
"fileId": {
"__rl": true,
"mode": "id",
"value": "={{ $json.id }}"
},
"options": {},
"operation": "download"
},
"credentials": {
"googleDriveOAuth2Api": {
"id": "UhdXGYLTAJbsa0xX",
"name": "Google Drive account"
}
},
"typeVersion": 3
},
{
"id": "399e196c-76ec-4077-aacc-f669173b0229",
"name": "Find File Ids in Google Drive Folder",
"type": "n8n-nodes-base.googleDrive",
"position": [
-620,
-160
],
"parameters": {
"filter": {
"driveId": {
"mode": "list",
"value": "My Drive"
},
"folderId": {
"__rl": true,
"mode": "id",
"value": "={{ $json.folder_id }}"
}
},
"options": {},
"resource": "fileFolder",
"returnAll": true
},
"credentials": {
"googleDriveOAuth2Api": {
"id": "UhdXGYLTAJbsa0xX",
"name": "Google Drive account"
}
},
"typeVersion": 3
},
{
"id": "3bc4f005-c6c8-4f73-816a-1573d6dfb62f",
"name": "text-embeddings-3-large",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
480,
720
],
"parameters": {
"model": "text-embedding-3-large",
"options": {}
},
"credentials": {
"openAiApi": {
"id": "jEMSvKmtYfzAkhe6",
"name": "OpenAi account"
}
},
"typeVersion": 1
},
{
"id": "5d42b34a-7156-4163-a2c4-a9cb3c984c96",
"name": "Google Folder ID",
"type": "n8n-nodes-base.set",
"position": [
-820,
-160
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "e6f6188f-c895-4c8c-b39a-0ef55b490fd6",
"name": "folder_id",
"type": "string",
"value": "[Your-Google-Folder-ID]"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "7be310c2-d30f-42a2-8f57-33c7b184e429",
"name": "gpt-4o-mini1",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
-400,
940
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"id": "jEMSvKmtYfzAkhe6",
"name": "OpenAi account"
}
},
"typeVersion": 1
},
{
"id": "18aacfd9-3f6e-4fba-9f68-d8cc95bc667b",
"name": "Delete Qdrant Points by File ID",
"type": "@n8n/n8n-nodes-langchain.code",
"position": [
-500,
800
],
"parameters": {
"code": {
"execute": {
"code": "const { QdrantVectorStore } = require(\"@langchain/qdrant\");\nconst { OpenAIEmbeddings } = require(\"@langchain/openai\");\n\n// Qdrant connection details\nconst url = \"http://localhost:6333/\";\nconst apiKey = \"\";\n\n// OpenAI API configuration\nconst openAIApiKey = \"[Your-OpenAI-API-Key]\";\n\n// Get input data\nconst items = this.getInputData()[0];\n// console.log(items)\n\nconst collectionName = items.json.qdrant_collection_name;\n// console.log(collectionName)\n\nasync function deleteDocumentsFromQdrant() {\n try {\n // Initialize OpenAI embeddings\n const embeddings = new OpenAIEmbeddings({\n model: \"text-embedding-3-large\",\n openAIApiKey: openAIApiKey\n });\n\n // Connect to existing Qdrant collection\n const vectorStore = await QdrantVectorStore.fromExistingCollection(embeddings, {\n url: url,\n apiKey: apiKey,\n collectionName: collectionName,\n });\n\n const fileIds = items.json.appended_id.map(item => item);\n\n console.log(fileIds)\n\n // Delete points by fileId\n const deletionResults = await Promise.all(fileIds.map(async (file_id) => {\n const filter = {\n must: [\n {\n key: \"metadata.file_id\",\n match: { value: file_id }\n }\n ]\n };\n\n try {\n // Access the underlying Qdrant client to perform the deletion\n await vectorStore.client.delete(collectionName, { filter });\n return { file_id, status: \"deleted\" };\n } catch (error) {\n console.error(`Error deleting documents for fileId ${file_id}:`, error);\n return { file_id, status: \"error\", message: error.message };\n }\n }));\n\n return deletionResults;\n } catch (error) {\n console.error(\"An error occurred during the deletion process:\", error);\n return error.message;\n }\n}\n\n// Execute the deletion process\ntry {\n const result = await deleteDocumentsFromQdrant();\n console.log(\"Deletion process completed:\", result);\n return [];\n} catch (error) {\n console.error(\"Failed to execute deletion process:\", error);\n return [{ json: { error } }];\n}\n\n"
}
},
"inputs": {
"input": [
{
"type": "main",
"required": true,
"maxConnections": 1
},
{
"type": "ai_languageModel",
"required": true,
"maxConnections": 1
}
]
},
"outputs": {
"output": [
{
"type": "main"
}
]
}
},
"typeVersion": 1
},
{
"id": "329cec97-aac1-4714-97ce-add5915b1078",
"name": "Qdrant Collection Name",
"type": "n8n-nodes-base.set",
"position": [
-700,
100
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "11fa71e9-6cbc-4183-9439-e3379b2b970e",
"name": "qdrant_collection_name",
"type": "string",
"value": "nostr-damus-user-profiles"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "82e98da8-530d-4a3c-97e6-5e91ad644a46",
"name": "File Id List",
"type": "n8n-nodes-base.summarize",
"position": [
-700,
280
],
"parameters": {
"options": {},
"fieldsToSummarize": {
"values": [
{
"field": "id",
"aggregation": "append"
}
]
}
},
"typeVersion": 1.1
},
{
"id": "f3def614-2709-4847-831d-d6a80c86ec1c",
"name": "Merge1",
"type": "n8n-nodes-base.merge",
"position": [
-340,
340
],
"parameters": {
"mode": "combine",
"options": {},
"combineBy": "combineByPosition"
},
"typeVersion": 3
},
{
"id": "cfe399fb-8560-4ac4-98f7-4f539ae6a52c",
"name": "Merge2",
"type": "n8n-nodes-base.merge",
"position": [
-80,
-140
],
"parameters": {},
"typeVersion": 3
},
{
"id": "1059da47-2abd-4884-b9c2-6b7d1623e31d",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1280,
560
],
"parameters": {
"color": 3,
"width": 1180,
"height": 760,
"content": "## Prepare Qdrant Vector Store"
},
"typeVersion": 1
},
{
"id": "2616e08f-070e-45b5-906f-40e832519aa2",
"name": "Confirm Qdrant Delete Points",
"type": "n8n-nodes-base.telegram",
"position": [
-1060,
760
],
"webhookId": "29aac1ac-9345-4e44-babf-ebcfae701d88",
"parameters": {
"chatId": "={{ $env.TELEGRAM_CHAT_ID }}",
"message": "=WARNING - {{ $json.appended_id.length }} Records in the Qdrant vector store collection \"{{ $json.qdrant_collection_name }}\" will be deleted. Are you sure you want to continue? This action cannot be undone!",
"options": {
"limitWaitTime": {
"values": {
"resumeUnit": "minutes",
"resumeAmount": 15
}
}
},
"operation": "sendAndWait",
"approvalOptions": {
"values": {
"approvalType": "double"
}
}
},
"credentials": {
"telegramApi": {
"id": "pAIFhguJlkO3c7aQ",
"name": "Telegram account"
}
},
"typeVersion": 1.2
},
{
"id": "9d167192-e87b-41be-87f2-d7ddf866bb8d",
"name": "If",
"type": "n8n-nodes-base.if",
"position": [
-1060,
1000
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "20f530d6-fd55-420d-b8a9-70e5303f688e",
"operator": {
"type": "boolean",
"operation": "true",
"singleValue": true
},
"leftValue": "={{ $json.data.approved }}",
"rightValue": ""
}
]
}
},
"typeVersion": 2.2
},
{
"id": "1178f8cf-ece0-4b11-942d-18dd025da366",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
320,
420
],
"parameters": {
"color": 7,
"width": 920,
"height": 640,
"content": "## Perform Qdrant Vector Store Operations"
},
"typeVersion": 1
},
{
"id": "cbf17a08-2f4c-4605-8418-5bf93ade7cf4",
"name": "Send Declined Message",
"type": "n8n-nodes-base.telegram",
"position": [
-740,
1120
],
"webhookId": "382a3b43-b83f-47b1-a276-67c6b98a441a",
"parameters": {
"text": "Qdrant vector store upsert declined",
"chatId": "={{ $env.TELEGRAM_CHAT_ID }}",
"additionalFields": {
"appendAttribution": false
}
},
"credentials": {
"telegramApi": {
"id": "pAIFhguJlkO3c7aQ",
"name": "Telegram account"
}
},
"typeVersion": 1.2
},
{
"id": "890f478a-e000-418d-8582-4fef946e44d8",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-900,
-380
],
"parameters": {
"width": 480,
"height": 840,
"content": "## 🌟Workflow Config\n\n- Google Drive Folder Id\n- Qdrant Collection Name\n- List of Google Drive File Id's"
},
"typeVersion": 1
},
{
"id": "d2bc2fed-c134-4e54-bd9d-69996be966a3",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
740,
-280
],
"parameters": {
"color": 6,
"width": 640,
"height": 420,
"content": "## Extract Metadata for Qdrant Hybrid Search"
},
"typeVersion": 1
},
{
"id": "61f3c21e-bc2a-47bc-8ab1-678b1f425ee3",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
400,
-280
],
"parameters": {
"color": 2,
"width": 300,
"height": 320,
"content": "## Google Drive"
},
"typeVersion": 1
},
{
"id": "61e608e4-ac6a-4131-9ca8-c46a5134bff9",
"name": "Sticky Note5",
"type": "n8n-nodes-base.stickyNote",
"position": [
80,
-360
],
"parameters": {
"color": 5,
"width": 1360,
"height": 1480,
"content": "## ✨ Save Documents to Qdrant Vector Store"
},
"typeVersion": 1
},
{
"id": "410681cb-e757-42c0-89de-902edbe998e3",
"name": "Sticky Note6",
"type": "n8n-nodes-base.stickyNote",
"position": [
-580,
680
],
"parameters": {
"color": 5,
"width": 420,
"height": 400,
"content": "## Delete From Qdrant Vector Store\nThis operation can not be undone!!!"
},
"typeVersion": 1
},
{
"id": "238469ce-3710-4681-b1b2-200c1b699d5e",
"name": "Sticky Note7",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1200,
640
],
"parameters": {
"color": 4,
"width": 380,
"height": 520,
"content": "## Human In The Loop\nUser must verify deletion of points from Qdrant vector store"
},
"typeVersion": 1
},
{
"id": "0b2f6ff4-dd02-4f0e-b2eb-60b1ce736cf5",
"name": "Sticky Note8",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1280,
-380
],
"parameters": {
"color": 4,
"width": 340,
"height": 460,
"content": "## 👍Start Here!"
},
"typeVersion": 1
},
{
"id": "abde545b-1a23-4b3e-8046-335b9d0fa445",
"name": "Webhook",
"type": "n8n-nodes-base.webhook",
"disabled": true,
"position": [
-1160,
-100
],
"webhookId": "3a30557f-9264-4bc8-a253-a9356677c791",
"parameters": {
"path": "upsert",
"options": {}
},
"typeVersion": 2
},
{
"id": "897d29af-719d-4fe7-93a9-44c693cc6547",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
-600,
-1200
],
"parameters": {
"text": "={{ $json.chatInput }}",
"options": {
"systemMessage": "=You are an intelligent assistant specialized in answering user questions using Nostr user profiles. Your primary goal is to provide precise, contextually relevant, and concise answers based on the tools and resources available.\n\n### TOOL\nUse the \"nostr_damus_user_profiles\" tool to:\n- perform semantic similarity searches and retrieve information from Nostr user profiles relevant to the user's query.\n- access detailed information about Nostr and/or Damus users when additional context or specifics are required.\n\n### Key Instructions\n1. **Response Guidelines**:\n - Clearly explain how the retrieved information addresses the user's query, if applicable.\n - If no relevant information is found, respond with: \"I cannot find the answer in the available resources.\"\n\n2. **Focus and Relevance**:\n - Ensure all responses are directly aligned with the user's question.\n - Avoid including extraneous details or relying solely on internal knowledge.\n"
},
"promptType": "define"
},
"typeVersion": 1.7
},
{
"id": "316b0d8d-bbc7-4c40-b6d0-d0c762554fca",
"name": "Window Buffer Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
-580,
-1000
],
"parameters": {
"contextWindowLength": 40
},
"typeVersion": 1.3
},
{
"id": "f1e342a8-d50e-48a8-9d7a-850f8be93cff",
"name": "When chat message received",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
-1160,
-1200
],
"webhookId": "5f1c0c82-0ff9-40c7-9e2e-b1a96ffe24cd",
"parameters": {
"options": {}
},
"typeVersion": 1.1
},
{
"id": "12902fa9-5bcb-4e8b-ac13-7f4cb6e7e1d0",
"name": "Google Gemini Chat Model1",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
-760,
-1000
],
"parameters": {
"options": {
"maxOutputTokens": 8192
},
"modelName": "models/gemini-2.0-flash-exp"
},
"credentials": {
"googlePalmApi": {
"id": "L9UNQHflYlyF9Ngd",
"name": "Google Gemini(PaLM) Api account"
}
},
"typeVersion": 1
},
{
"id": "1c5818d4-6251-4d14-8b4f-d1f3ddfbed38",
"name": "text-embeddings-3-large1",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
-320,
-840
],
"parameters": {
"model": "text-embedding-3-large",
"options": {}
},
"credentials": {
"openAiApi": {
"id": "jEMSvKmtYfzAkhe6",
"name": "OpenAi account"
}
},
"typeVersion": 1
},
{
"id": "80056067-5d2b-4ac7-8e69-e75bd66a1ad4",
"name": "Sticky Note9",
"type": "n8n-nodes-base.stickyNote",
"position": [
-900,
-1300
],
"parameters": {
"color": 5,
"width": 860,
"height": 680,
"content": "## 🤖Retrieve Content from Qdrant Vector Store"
},
"typeVersion": 1
},
{
"id": "b45b18e4-7773-4eec-837b-f43fc0eeb90c",
"name": "Sticky Note10",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1280,
-1300
],
"parameters": {
"color": 4,
"width": 340,
"height": 320,
"content": "## 🗣️ Chat with Your Documents"
},
"typeVersion": 1
},
{
"id": "8fe891dd-dee6-4abb-bc09-d90e6d7bf3cb",
"name": "Sticky Note11",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1360,
-480
],
"parameters": {
"color": 7,
"width": 2880,
"height": 1880,
"content": "# Step 1 - Save Documents to Qdrant Vector Store"
},
"typeVersion": 1
},
{
"id": "4a9bf716-3fc3-4ccc-b831-19a1afdb4588",
"name": "Sticky Note12",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1360,
-1420
],
"parameters": {
"color": 7,
"width": 1780,
"height": 880,
"content": "# Step 2 - Chat with Your Documents from Qdrant Vector Store"
},
"typeVersion": 1
},
{
"id": "fccedfde-c5aa-4237-9d1c-feb9ebabf4f3",
"name": "Google Drive",
"type": "n8n-nodes-base.googleDrive",
"disabled": true,
"position": [
120,
-780
],
"parameters": {
"name": "=Nostr Chatbot - Avatar - {{ $now }}",
"content": "={{ $json.output }}",
"driveId": {
"__rl": true,
"mode": "list",
"value": "My Drive"
},
"options": {},
"folderId": {
"__rl": true,
"mode": "list",
"value": "root",
"cachedResultName": "/ (Root folder)"
},
"operation": "createFromText"
},
"credentials": {
"googleDriveOAuth2Api": {
"id": "UhdXGYLTAJbsa0xX",
"name": "Google Drive account"
}
},
"typeVersion": 3
},
{
"id": "6d6813f6-4f2e-499a-9e5c-fe15624a91ef",
"name": "Respond to User",
"type": "n8n-nodes-base.set",
"position": [
120,
-960
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "cd8f88e1-19c0-4b9e-914d-e2e7ba21d9fa",
"name": "output",
"type": "string",
"value": "={{ $json.output }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "1c73bae9-2bdd-4383-a6f8-3cf43d3c15be",
"name": "Sticky Note13",
"type": "n8n-nodes-base.stickyNote",
"position": [
0,
-1300
],
"parameters": {
"color": 4,
"width": 340,
"height": 300,
"content": "## Save Chat History"
},
"typeVersion": 1
},
{
"id": "db3dcc69-d1d0-48a1-b949-37f2de802b4a",
"name": "Update Chat History",
"type": "n8n-nodes-base.googleDocs",
"position": [
120,
-1200
],
"parameters": {
"actionsUi": {
"actionFields": [
{
"text": "=\n-------------------------------\n\n{{ $now }}\n\n{{ $('When chat message received').item.json.chatInput }}\n\n{{ $json.output }}",
"action": "insert"
}
]
},
"operation": "update",
"documentURL": "1ej_qLolUFp1h4eZkrb99T3DWQ3JOwXVEMS3VUjWyVf0"
},
"credentials": {
"googleDocsOAuth2Api": {
"id": "YWEHuG28zOt532MQ",
"name": "Google Docs account"
}
},
"typeVersion": 2
},
{
"id": "2dd28eed-b71b-44fb-bb78-8cb50b0d0c93",
"name": "Qdrant Vector Store Tool",
"type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
"position": [
-420,
-1000
],
"parameters": {
"mode": "retrieve-as-tool",
"topK": 20,
"options": {},
"toolName": "nostr_damus_user_profiles",
"toolDescription": "Retrieve information about Nostr or Damus users",
"qdrantCollection": {
"__rl": true,
"mode": "list",
"value": "nostr-damus-user-profiles",
"cachedResultName": "nostr-damus-user-profiles"
}
},
"credentials": {
"qdrantApi": {
"id": "DJQ4hVAVdWZytjr2",
"name": "QdrantApi account"
}
},
"typeVersion": 1
},
{
"id": "3b130cf8-ab8e-4001-a3d0-a129194aee98",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"disabled": true,
"position": [
-760,
-820
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"id": "jEMSvKmtYfzAkhe6",
"name": "OpenAi account"
}
},
"typeVersion": 1.2
},
{
"id": "ccc64645-ad14-4b6b-a507-0b5fb0ac945f",
"name": "Send Completed Message",
"type": "n8n-nodes-base.telegram",
"position": [
500,
200
],
"webhookId": "382a3b43-b83f-47b1-a276-67c6b98a441a",
"parameters": {
"text": "Qdrant vector store upsert completed",
"chatId": "={{ $env.TELEGRAM_CHAT_ID }}",
"additionalFields": {
"appendAttribution": false
}
},
"credentials": {
"telegramApi": {
"id": "pAIFhguJlkO3c7aQ",
"name": "Telegram account"
}
},
"typeVersion": 1.2
},
{
"id": "885fef53-2246-45b1-a122-ab5b82374585",
"name": "Sticky Note14",
"type": "n8n-nodes-base.stickyNote",
"position": [
-2120,
-480
],
"parameters": {
"width": 700,
"height": 1240,
"content": "# 🤖 AI-Powered RAG Chatbot with Google Drive Integration\n\nThis workflow creates a powerful RAG (Retrieval-Augmented Generation) chatbot that can process, store, and interact with documents from Google Drive using Qdrant vector storage and Google's Gemini AI.\n\n## How It Works\n\n### Document Processing & Storage 📚\n- Retrieves documents from a specified Google Drive folder\n- Processes and splits documents into manageable chunks\n- Extracts metadata using AI for enhanced search capabilities\n- Stores document vectors in Qdrant for efficient retrieval\n\n### Intelligent Chat Interface 💬\n- Provides a conversational interface powered by Google Gemini\n- Uses RAG to retrieve relevant context from stored documents\n- Maintains chat history in Google Docs for reference\n- Delivers accurate, context-aware responses\n\n### Vector Store Management 🗄️\n- Features secure delete operations with human verification\n- Includes Telegram notifications for important operations\n- Maintains data integrity with proper version control\n- Supports batch processing of documents\n\n## Setup Steps\n\n1. Configure API Credentials:\n - Set up Google Drive & Docs access\n - Configure Gemini AI API\n - Set up Qdrant vector store connection\n - Add Telegram bot for notifications\n\n2. Configure Document Sources:\n - Set Google Drive folder ID\n - Define Qdrant collection name\n - Set up document processing parameters\n\n3. Test and Deploy:\n - Verify document processing\n - Test chat functionality\n - Confirm vector store operations\n - Check notification system\n\n\nThis workflow is ideal for organizations needing to create intelligent chatbots that can access and understand large document repositories while maintaining context and providing accurate responses through RAG technology.\n"
},
"typeVersion": 1
}
],
"active": false,
"pinData": {},
"settings": {
"timezone": "America/Vancouver",
"callerPolicy": "workflowsFromSameOwner",
"executionOrder": "v1"
},
"versionId": "0c0d90e5-02f9-4169-b477-fd90c52ce44e",
"connections": {
"If": {
"main": [
[
{
"node": "Delete Qdrant Points by File ID",
"type": "main",
"index": 0
}
],
[
{
"node": "Send Declined Message",
"type": "main",
"index": 0
}
]
]
},
"Wait": {
"main": [
[
{
"node": "Loop Over Items",
"type": "main",
"index": 0
}
]
]
},
"Merge": {
"main": [
[
{
"node": "Qdrant Vector Store",
"type": "main",
"index": 0
}
]
]
},
"Merge1": {
"main": [
[
{
"node": "Confirm Qdrant Delete Points",
"type": "main",
"index": 0
}
]
]
},
"Merge2": {
"main": [
[
{
"node": "Loop Over Items",
"type": "main",
"index": 0
}
]
]
},
"Webhook": {
"main": [
[
{
"node": "Google Folder ID",
"type": "main",
"index": 0
}
]
]
},
"AI Agent": {
"main": [
[
{
"node": "Update Chat History",
"type": "main",
"index": 0
},
{
"node": "Respond to User",
"type": "main",
"index": 0
}
]
]
},
"Data Loader": {
"ai_document": [
[
{
"node": "Qdrant Vector Store",
"type": "ai_document",
"index": 0
}
]
]
},
"File Id List": {
"main": [
[
{
"node": "Merge1",
"type": "main",
"index": 1
}
]
]
},
"gpt-4o-mini1": {
"ai_languageModel": [
[
{
"node": "Delete Qdrant Points by File ID",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Token Splitter": {
"ai_textSplitter": [
[
{
"node": "Data Loader",
"type": "ai_textSplitter",
"index": 0
}
]
]
},
"Loop Over Items": {
"main": [
[
{
"node": "Send Completed Message",
"type": "main",
"index": 0
}
],
[
{
"node": "Download File From Google Drive",
"type": "main",
"index": 0
}
]
]
},
"Respond to User": {
"main": [
[]
]
},
"Google Folder ID": {
"main": [
[
{
"node": "Find File Ids in Google Drive Folder",
"type": "main",
"index": 0
}
]
]
},
"Extract Meta Data": {
"main": [
[
{
"node": "Merge",
"type": "main",
"index": 0
}
]
]
},
"Get File Contents": {
"main": [
[
{
"node": "Extract Meta Data",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[]
]
},
"Qdrant Vector Store": {
"main": [
[
{
"node": "Wait",
"type": "main",
"index": 0
}
]
]
},
"Update Chat History": {
"main": [
[]
]
},
"Window Buffer Memory": {
"ai_memory": [
[
{
"node": "AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Qdrant Collection Name": {
"main": [
[
{
"node": "Merge1",
"type": "main",
"index": 0
}
]
]
},
"text-embeddings-3-large": {
"ai_embedding": [
[
{
"node": "Qdrant Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Google Gemini Chat Model": {
"ai_languageModel": [
[
{
"node": "Extract Meta Data",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Qdrant Vector Store Tool": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
],
"ai_vectorStore": [
[]
]
},
"text-embeddings-3-large1": {
"ai_embedding": [
[
{
"node": "Qdrant Vector Store Tool",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Google Gemini Chat Model1": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"Confirm Qdrant Delete Points": {
"main": [
[
{
"node": "If",
"type": "main",
"index": 0
}
]
]
},
"Delete Qdrant Points by File ID": {
"main": [
[
{
"node": "Merge2",
"type": "main",
"index": 1
}
]
]
},
"Download File From Google Drive": {
"main": [
[
{
"node": "Get File Contents",
"type": "main",
"index": 0
},
{
"node": "Merge",
"type": "main",
"index": 1
}
]
]
},
"When clicking ‘Test workflow’": {
"main": [
[
{
"node": "Google Folder ID",
"type": "main",
"index": 0
}
]
]
},
"Find File Ids in Google Drive Folder": {
"main": [
[
{
"node": "File Id List",
"type": "main",
"index": 0
},
{
"node": "Qdrant Collection Name",
"type": "main",
"index": 0
},
{
"node": "Merge2",
"type": "main",
"index": 0
}
]
]
}
}
}Workflow n8n Google Drive, intelligence artificielle, gestion de documents : pour qui est ce workflow ?
Ce workflow s'adresse aux entreprises et équipes qui gèrent de nombreux documents et qui souhaitent automatiser le traitement de ces fichiers. Il est particulièrement adapté aux professionnels de la gestion de données, aux équipes de marketing et aux développeurs cherchant à intégrer des solutions d'IA dans leurs processus.
Workflow n8n Google Drive, intelligence artificielle, gestion de documents : problème résolu
Ce workflow résout le problème de la gestion manuelle des documents, qui peut être chronophage et sujet à des erreurs. En automatisant le chargement, l'extraction et le traitement des fichiers, les utilisateurs gagnent du temps et améliorent la précision des informations. Cela permet également de réduire les risques liés à la manipulation manuelle des données et d'optimiser la productivité des équipes.
Workflow n8n Google Drive, intelligence artificielle, gestion de documents : étapes du workflow
Étape 1 : Le workflow est déclenché manuellement.
- Étape 1 : Les fichiers sont chargés via le nœud 'Data Loader'.
- Étape 2 : Le texte est découpé en morceaux gérables grâce au 'Token Splitter'.
- Étape 3 : Les données sont stockées dans le 'Qdrant Vector Store'.
- Étape 4 : Les contenus des fichiers sont récupérés et les métadonnées extraites.
- Étape 5 : Les utilisateurs peuvent interagir avec le modèle de chat Google Gemini pour obtenir des réponses basées sur le contenu traité.
Workflow n8n Google Drive, intelligence artificielle, gestion de documents : guide de personnalisation
Pour personnaliser ce workflow, vous pouvez modifier les paramètres du nœud 'Data Loader' pour ajuster le type de données à charger. Il est également possible de changer les modèles utilisés dans les nœuds de traitement, comme 'Google Gemini Chat Model' et 'gpt-4o-mini1', pour répondre à des besoins spécifiques. Pensez à sécuriser le flux en vérifiant les autorisations d'accès aux fichiers Google Drive et en configurant les notifications pour suivre les résultats des opérations.