Modèle RAG d'agent IA local n8n
Ceci est unInternal Wiki, AI RAGworkflow d'automatisation du domainecontenant 41 nœuds.Utilise principalement des nœuds comme Set, Switch, Webhook, Postgres, Aggregate. Système de questions-réponses sur des documents locaux utilisant Ollama AI, un agent RAG intelligent et PGVector
- •Point de terminaison HTTP Webhook (généré automatiquement par n8n)
- •Informations de connexion à la base de données PostgreSQL
- •Clé API OpenAI
Nœuds utilisés (41)
Catégorie
{
"id": "dlA7uMt2f1hTW3xd",
"meta": {
"instanceId": "8cf060ebda3ec45b5ebb6a30779eaf0c03dfba83865feab3f32adb31b82caa08"
},
"name": "n8n Local AI Agentic RAG Template",
"tags": [],
"nodes": [
{
"id": "397d00eb-8034-49e5-a8f6-0a0fd9b97d5b",
"name": "Chargeur de données par défaut",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
3312,
1280
],
"parameters": {
"options": {
"metadata": {
"metadataValues": [
{
"name": "=file_id",
"value": "={{ $('Set File ID').first().json.file_id }}"
},
{
"name": "file_title",
"value": "={{ $('Set File ID').first().json.file_title }}"
}
]
}
},
"jsonData": "={{ $json.data || $json.text || $json.concatenated_data }}",
"jsonMode": "expressionData"
},
"typeVersion": 1
},
{
"id": "e57065a2-9087-48e9-839e-d9c5c5fb477f",
"name": "Note adhésive",
"type": "n8n-nodes-base.stickyNote",
"position": [
2304,
144
],
"parameters": {
"color": 4,
"width": 583.4552380860637,
"height": 528.85546469693,
"content": "## Agent Tools for RAG"
},
"typeVersion": 1
},
{
"id": "f7efaf27-78fb-4429-beba-74ffcc700342",
"name": "Note adhésive 1",
"type": "n8n-nodes-base.stickyNote",
"position": [
560,
688
],
"parameters": {
"color": 5,
"width": 3073,
"height": 867,
"content": "## Tool to Add a Google Drive File to Vector DB"
},
"typeVersion": 1
},
{
"id": "a137d00b-fb01-408c-9963-645e2beb44d9",
"name": "Extraire le texte du document",
"type": "n8n-nodes-base.extractFromFile",
"position": [
2512,
1280
],
"parameters": {
"options": {},
"operation": "text"
},
"typeVersion": 1,
"alwaysOutputData": true
},
{
"id": "1aec304d-7264-4e65-8654-cb9294c96c82",
"name": "Mémoire de chat Postgres",
"type": "@n8n/n8n-nodes-langchain.memoryPostgresChat",
"position": [
1712,
512
],
"parameters": {},
"notesInFlow": false,
"typeVersion": 1
},
{
"id": "9c407f2b-4f6a-46d6-a607-225c1c628ae5",
"name": "Définir l'ID du fichier",
"type": "n8n-nodes-base.set",
"position": [
992,
960
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "10646eae-ae46-4327-a4dc-9987c2d76173",
"name": "file_id",
"type": "string",
"value": "={{ $json.path }}"
},
{
"id": "f4536df5-d0b1-4392-bf17-b8137fb31a44",
"name": "file_type",
"type": "string",
"value": "={{ $json.path.split(/[\\\\/]/).pop().split('.').pop(); }}"
},
{
"id": "77d782de-169d-4a46-8a8e-a3831c04d90f",
"name": "file_title",
"type": "string",
"value": "={{ $json.path.split(/[\\\\/]/).pop().split('.').slice(0, -1).join('.'); }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "bc93aa94-10ec-4670-99f4-3bcec36be1ce",
"name": "Note adhésive 2",
"type": "n8n-nodes-base.stickyNote",
"position": [
1264,
208
],
"parameters": {
"width": 1035.6381264595484,
"height": 464.8027193303974,
"content": "## RAG AI Agent with Chat Interface"
},
"typeVersion": 1
},
{
"id": "8ccc451e-2fac-49b0-8700-085476add599",
"name": "Répondre à Webhook",
"type": "n8n-nodes-base.respondToWebhook",
"position": [
2128,
288
],
"parameters": {
"options": {}
},
"typeVersion": 1.1
},
{
"id": "55abb8ac-7988-430a-ae41-5155471228a2",
"name": "Modifier les champs",
"type": "n8n-nodes-base.set",
"position": [
1568,
288
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "9a9a245e-f1a1-4282-bb02-a81ffe629f0f",
"name": "chatInput",
"type": "string",
"value": "={{ $json?.chatInput || $json.body.chatInput }}"
},
{
"id": "b80831d8-c653-4203-8706-adedfdb98f77",
"name": "sessionId",
"type": "string",
"value": "={{ $json?.sessionId || $json.body.sessionId}}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "78b3fd17-23e9-4693-b782-918a5a8e5aed",
"name": "À la réception d'un message de chat",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
1312,
288
],
"webhookId": "e104e40e-6134-4825-a6f0-8a646d882662",
"parameters": {
"public": true,
"options": {}
},
"typeVersion": 1.1
},
{
"id": "06e362d1-d20c-407a-a75a-ed175c07439d",
"name": "Webhook",
"type": "n8n-nodes-base.webhook",
"position": [
1312,
480
],
"webhookId": "bf4dd093-bb02-472c-9454-7ab9af97bd1d",
"parameters": {
"path": "bf4dd093-bb02-472c-9454-7ab9af97bd1d",
"options": {},
"httpMethod": "POST",
"responseMode": "responseNode"
},
"typeVersion": 2
},
{
"id": "e8ba5c17-3426-4d76-b69b-ff91dff7958f",
"name": "Extraire le texte PDF",
"type": "n8n-nodes-base.extractFromFile",
"position": [
2512,
720
],
"parameters": {
"options": {},
"operation": "pdf"
},
"typeVersion": 1
},
{
"id": "b40eb123-d7fc-4799-b248-4b9516aee49e",
"name": "Agréger",
"type": "n8n-nodes-base.aggregate",
"position": [
2544,
912
],
"parameters": {
"options": {},
"aggregate": "aggregateAllItemData"
},
"typeVersion": 1
},
{
"id": "0e3755e8-9532-447f-9137-f65d542c247e",
"name": "Résumer",
"type": "n8n-nodes-base.summarize",
"position": [
2752,
992
],
"parameters": {
"options": {},
"fieldsToSummarize": {
"values": [
{
"field": "data",
"aggregation": "concatenate"
}
]
}
},
"typeVersion": 1
},
{
"id": "b185f2be-06bf-4a14-8d58-4b411a709f18",
"name": "Agent IA RAG",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
1792,
288
],
"parameters": {
"text": "={{ $json.chatInput }}",
"options": {
"systemMessage": "You are a personal assistant who helps answer questions from a corpus of documents. The documents are either text based (Txt, docs, extracted PDFs, etc.) or tabular data (CSVs or Excel documents).\n\nYou are given tools to perform RAG in the 'documents' table, look up the documents available in your knowledge base in the 'document_metadata' table, extract all the text from a given document, and query the tabular files with SQL in the 'document_rows' table.\n\nAlways start by performing RAG unless the users asks you to check a document or the question requires a SQL query for tabular data (fetching a sum, finding a max, something a RAG lookup would be unreliable for). If RAG doesn't help, then look at the documents that are available to you, find a few that you think would contain the answer, and then analyze those.\n\nAlways tell the user if you didn't find the answer. Don't make something up just to please them."
},
"promptType": "define"
},
"typeVersion": 1.6
},
{
"id": "2ee45951-3553-49b7-9f79-3cef3d065e8a",
"name": "Commutateur",
"type": "n8n-nodes-base.switch",
"position": [
1840,
944
],
"parameters": {
"rules": {
"values": [
{
"conditions": {
"options": {
"version": 1,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"operator": {
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $('Set File ID').item.json.file_type }}",
"rightValue": "pdf"
}
]
}
},
{
"conditions": {
"options": {
"version": 1,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "2ae7faa7-a936-4621-a680-60c512163034",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $('Set File ID').item.json.file_type }}",
"rightValue": "xlsx"
}
]
}
},
{
"conditions": {
"options": {
"version": 1,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "fc193b06-363b-4699-a97d-e5a850138b0e",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $('Set File ID').item.json.file_type }}",
"rightValue": "=csv"
}
]
}
},
{
"conditions": {
"options": {
"version": 1,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "b69f5605-0179-4b02-9a32-e34bb085f82d",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $('Set File ID').item.json.file_type }}",
"rightValue": "txt"
}
]
}
}
]
},
"options": {
"fallbackOutput": 3
}
},
"typeVersion": 3
},
{
"id": "20bf7dde-e073-4288-a9d6-34df3973b5c3",
"name": "Extraire d'Excel",
"type": "n8n-nodes-base.extractFromFile",
"position": [
2320,
912
],
"parameters": {
"options": {},
"operation": "xlsx"
},
"typeVersion": 1
},
{
"id": "f1840995-3f1c-4f4e-9d78-bc9225ecbe2b",
"name": "Définir le schéma",
"type": "n8n-nodes-base.set",
"position": [
3184,
848
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "f422e2e0-381c-46ea-8f38-3f58c501d8b9",
"name": "schema",
"type": "string",
"value": "={{ $('Extract from Excel').isExecuted ? $('Extract from Excel').first().json.keys().toJsonString() : $('Extract from CSV').first().json.keys().toJsonString() }}"
},
{
"id": "bb07c71e-5b60-4795-864c-cc3845b6bc46",
"name": "data",
"type": "string",
"value": "={{ $json.concatenated_data }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "b79ceb0b-f370-4ffb-9953-14b411acb5d9",
"name": "Extraire de CSV",
"type": "n8n-nodes-base.extractFromFile",
"position": [
2320,
1088
],
"parameters": {
"options": {}
},
"typeVersion": 1
},
{
"id": "7067874e-4123-4a6c-a94d-89e4d1878309",
"name": "Note adhésive 3",
"type": "n8n-nodes-base.stickyNote",
"position": [
560,
368
],
"parameters": {
"color": 3,
"width": 680,
"height": 300,
"content": "## Run Each Node Once to Set Up Database Tables"
},
"typeVersion": 1
},
{
"id": "130c53e8-d507-4b6f-b1cf-f79dbc571c46",
"name": "Créer une table de métadonnées de document",
"type": "n8n-nodes-base.postgres",
"position": [
688,
464
],
"parameters": {
"query": "CREATE TABLE document_metadata (\n id TEXT PRIMARY KEY,\n title TEXT,\n created_at TIMESTAMP DEFAULT NOW(),\n schema TEXT\n);",
"options": {},
"operation": "executeQuery"
},
"typeVersion": 2.5
},
{
"id": "421d2123-b68a-4c51-a482-db5bdffd3f76",
"name": "Créer une table de lignes de document (pour données tabulaires)",
"type": "n8n-nodes-base.postgres",
"position": [
992,
464
],
"parameters": {
"query": "CREATE TABLE document_rows (\n id SERIAL PRIMARY KEY,\n dataset_id TEXT REFERENCES document_metadata(id),\n row_data JSONB -- Store the actual row data\n);",
"options": {},
"operation": "executeQuery"
},
"typeVersion": 2.5
},
{
"id": "55ff6535-bedb-479f-b3da-eb45e1127e77",
"name": "Lister les documents",
"type": "n8n-nodes-base.postgresTool",
"position": [
1840,
512
],
"parameters": {
"table": {
"__rl": true,
"mode": "list",
"value": "document_metadata",
"cachedResultName": "document_metadata"
},
"schema": {
"__rl": true,
"mode": "list",
"value": "public"
},
"options": {},
"operation": "select",
"returnAll": true,
"descriptionType": "manual",
"toolDescription": "Use this tool to fetch all available documents, including the table schema if the file is a CSV or Excel file."
},
"typeVersion": 2.5
},
{
"id": "ffcb630b-5119-4ff6-b85a-d77eeb8d5713",
"name": "Obtenir le contenu du fichier",
"type": "n8n-nodes-base.postgresTool",
"position": [
1984,
512
],
"parameters": {
"query": "SELECT \n string_agg(text, ' ') as document_text\nFROM documents_pg\n WHERE metadata->>'file_id' = $1\nGROUP BY metadata->>'file_id';",
"options": {
"queryReplacement": "={{ $fromAI('file_id') }}"
},
"operation": "executeQuery",
"descriptionType": "manual",
"toolDescription": "Given a file ID, fetches the text from the document."
},
"typeVersion": 2.5
},
{
"id": "f504b2f4-ffb5-4ef7-ba93-753151b77d9e",
"name": "Interroger les lignes de document",
"type": "n8n-nodes-base.postgresTool",
"position": [
2144,
512
],
"parameters": {
"query": "{{ $fromAI('sql_query') }}",
"options": {},
"operation": "executeQuery",
"descriptionType": "manual",
"toolDescription": "Run a SQL query - use this to query from the document_rows table once you know the file ID (which is the file path) you are querying. dataset_id is the file_id (file path) and you are always using the row_data for filtering, which is a jsonb field that has all the keys from the file schema given in the document_metadata table.\n\nExample query:\n\nSELECT AVG((row_data->>'revenue')::numeric)\nFROM document_rows\nWHERE dataset_id = '/data/shared/document.csv';\n\nExample query 2:\n\nSELECT \n row_data->>'category' as category,\n SUM((row_data->>'sales')::numeric) as total_sales\nFROM dataset_rows\nWHERE dataset_id = '/data/shared/document2.csv'\nGROUP BY row_data->>'category';"
},
"typeVersion": 2.5
},
{
"id": "4abe03ca-297c-4509-b0db-7bed4338a158",
"name": "Boucler sur les éléments",
"type": "n8n-nodes-base.splitInBatches",
"position": [
800,
800
],
"parameters": {
"options": {
"reset": false
}
},
"typeVersion": 3
},
{
"id": "e382d750-85ba-492d-9d3e-eb839af0bfc1",
"name": "Insérer les métadonnées du document",
"type": "n8n-nodes-base.postgres",
"position": [
1488,
832
],
"parameters": {
"table": {
"__rl": true,
"mode": "list",
"value": "document_metadata",
"cachedResultName": "document_metadata"
},
"schema": {
"__rl": true,
"mode": "list",
"value": "public"
},
"columns": {
"value": {
"id": "={{ $('Set File ID').item.json.file_id }}",
"title": "={{ $('Set File ID').item.json.file_title }}"
},
"schema": [
{
"id": "id",
"type": "string",
"display": true,
"removed": false,
"required": true,
"displayName": "id",
"defaultMatch": true,
"canBeUsedToMatch": true
},
{
"id": "title",
"type": "string",
"display": true,
"required": false,
"displayName": "title",
"defaultMatch": false,
"canBeUsedToMatch": false
},
{
"id": "url",
"type": "string",
"display": true,
"removed": true,
"required": false,
"displayName": "url",
"defaultMatch": false,
"canBeUsedToMatch": false
},
{
"id": "created_at",
"type": "dateTime",
"display": true,
"required": false,
"displayName": "created_at",
"defaultMatch": false,
"canBeUsedToMatch": false
},
{
"id": "schema",
"type": "string",
"display": true,
"removed": true,
"required": false,
"displayName": "schema",
"defaultMatch": false,
"canBeUsedToMatch": false
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"id"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {},
"operation": "upsert"
},
"executeOnce": true,
"typeVersion": 2.5
},
{
"id": "bbf6f704-b4a2-4ff2-ac09-27626526b35f",
"name": "Insérer les lignes du tableau",
"type": "n8n-nodes-base.postgres",
"position": [
2544,
1088
],
"parameters": {
"table": {
"__rl": true,
"mode": "list",
"value": "document_rows",
"cachedResultName": "document_rows"
},
"schema": {
"__rl": true,
"mode": "list",
"value": "public"
},
"columns": {
"value": {
"row_data": "={{ $json.toJsonString().replaceAll(/'/g, \"''\") }}",
"dataset_id": "={{ $('Set File ID').item.json.file_id }}"
},
"schema": [
{
"id": "id",
"type": "number",
"display": true,
"removed": true,
"required": false,
"displayName": "id",
"defaultMatch": true,
"canBeUsedToMatch": true
},
{
"id": "dataset_id",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "dataset_id",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "row_data",
"type": "object",
"display": true,
"removed": false,
"required": false,
"displayName": "row_data",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"id"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {}
},
"typeVersion": 2.5
},
{
"id": "3265a7df-dd40-421e-b1fb-53293a7460f8",
"name": "Mettre à jour le schéma pour les métadonnées du document",
"type": "n8n-nodes-base.postgres",
"position": [
3408,
848
],
"parameters": {
"table": {
"__rl": true,
"mode": "list",
"value": "document_metadata",
"cachedResultName": "document_metadata"
},
"schema": {
"__rl": true,
"mode": "list",
"value": "public"
},
"columns": {
"value": {
"id": "={{ $('Set File ID').item.json.file_id }}",
"schema": "={{ $json.schema }}"
},
"schema": [
{
"id": "id",
"type": "string",
"display": true,
"removed": false,
"required": true,
"displayName": "id",
"defaultMatch": true,
"canBeUsedToMatch": true
},
{
"id": "title",
"type": "string",
"display": true,
"removed": true,
"required": false,
"displayName": "title",
"defaultMatch": false,
"canBeUsedToMatch": false
},
{
"id": "url",
"type": "string",
"display": true,
"removed": true,
"required": false,
"displayName": "url",
"defaultMatch": false,
"canBeUsedToMatch": false
},
{
"id": "created_at",
"type": "dateTime",
"display": true,
"required": false,
"displayName": "created_at",
"defaultMatch": false,
"canBeUsedToMatch": false
},
{
"id": "schema",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "schema",
"defaultMatch": false,
"canBeUsedToMatch": false
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"id"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {},
"operation": "upsert"
},
"typeVersion": 2.5
},
{
"id": "53f9f045-bb08-4b22-a11e-dfd2c964b687",
"name": "Note adhésive 9",
"type": "n8n-nodes-base.stickyNote",
"position": [
0,
0
],
"parameters": {
"color": 6,
"width": 540,
"height": 1320,
"content": "## 🚀 n8n Local AI Agentic RAG Template\n\n**Author:** [Jadai kongolo](https://my.jadaikongolo.tech)\n\n## What is this?\nThis template provides an entirely local implementation of an **Agentic RAG (Retrieval Augmented Generation)** system in n8n that can be extended easily for your specific use case and knowledge base. Unlike standard RAG which only performs simple lookups, this agent can reason about your knowledge base, self-improve retrieval, and dynamically switch between different tools based on the specific question. \n\n## Why Agentic RAG?\nStandard RAG has significant limitations:\n- Poor analysis of numerical/tabular data\n- Missing context due to document chunking\n- Inability to connect information across documents\n- No dynamic tool selection based on question type\n\n## What makes this template powerful:\n- **Intelligent tool selection**: Switches between RAG lookups, SQL queries, or full document retrieval based on the question\n- **Complete document context**: Accesses entire documents when needed instead of just chunks\n- **Accurate numerical analysis**: Uses SQL for precise calculations on spreadsheet/tabular data\n- **Cross-document insights**: Connects information across your entire knowledge base\n- **Multi-file processing**: Handles multiple documents in a single workflow loop\n- **Efficient storage**: Uses JSONB in Supabase to store tabular data without creating new tables for each CSV\n\n## Getting Started\n1. Run the table creation nodes first to set up your database tables in Supabase\n2. Upload your documents to the folder on your computer that is mounted to /data/shared in the n8n container. This folder by default is the \"shared\" folder in the local AI package.\n3. The agent will process them automatically (chunking text, storing tabular data in Supabase)\n4. Start asking questions that leverage the agent's multiple reasoning approaches\n\n## Customization\nThis template provides a solid foundation that you can extend by:\n- Tuning the system prompt for your specific use case\n- Adding document metadata like summaries\n- Implementing more advanced RAG techniques\n- Optimizing for larger knowledge bases\n\n---\n\nThe non-local (\"cloud\") version of this Agentic RAG agent can be [found here](https://kongolo.gumroad.com/l/anxwv)."
},
"typeVersion": 1
},
{
"id": "cdee87fe-e154-47ab-9330-32dee5c213d3",
"name": "Déclencheur de fichier local",
"type": "n8n-nodes-base.localFileTrigger",
"position": [
608,
800
],
"parameters": {
"path": "/data/shared",
"events": [
"add",
"change"
],
"options": {
"usePolling": true,
"followSymlinks": true
},
"triggerOn": "folder"
},
"typeVersion": 1
},
{
"id": "67311475-7928-4ddc-957a-79817c98d26d",
"name": "Lire/Écrire des fichiers depuis le disque",
"type": "n8n-nodes-base.readWriteFile",
"position": [
1648,
960
],
"parameters": {
"options": {
"dataPropertyName": "=data"
},
"fileSelector": "={{ $('Set File ID').item.json.file_id }}"
},
"typeVersion": 1
},
{
"id": "366e800a-9bd7-4822-a11c-f555800bbba6",
"name": "Embeddings Ollama",
"type": "@n8n/n8n-nodes-langchain.embeddingsOllama",
"position": [
3072,
1280
],
"parameters": {
"model": "nomic-embed-text:latest"
},
"typeVersion": 1
},
{
"id": "be37cfb9-ea40-4244-87d7-b562be315573",
"name": "Embeddings Ollama 1",
"type": "@n8n/n8n-nodes-langchain.embeddingsOllama",
"position": [
2560,
480
],
"parameters": {
"model": "nomic-embed-text:latest"
},
"typeVersion": 1
},
{
"id": "1306b972-2b24-4c62-846e-f1c5b3d0482c",
"name": "Séparateur de texte récursif",
"type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
"position": [
3200,
1408
],
"parameters": {
"options": {},
"chunkSize": 400
},
"typeVersion": 1
},
{
"id": "677ad468-8118-4f8f-9a47-f5429cdc7582",
"name": "Ollama (Changer l'URL de base)",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
1568,
512
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "qwen2.5:14b-8k",
"cachedResultName": "qwen2.5:14b-8k"
},
"options": {}
},
"typeVersion": 1.2
},
{
"id": "b3e23401-8868-4b3c-a3fe-37fda44419d5",
"name": "Note adhésive 4",
"type": "n8n-nodes-base.stickyNote",
"position": [
0,
1344
],
"parameters": {
"color": 6,
"width": 540,
"height": 200,
"content": "## NOTE\n\nThe Ollama chat model node doesn't work with the RAG nodes - known issue with n8n.\n\nSo for now, we are using the OpenAI chat model but changing the base URL to Ollama when creating the credentials (i.e. http://ollama:11434/v1). The API key can be set to whatever, it isn't used for local LLMs."
},
"typeVersion": 1
},
{
"id": "987a6081-cdfd-457e-a2e5-4fa93fa018f4",
"name": "Supprimer les anciens enregistrements de document",
"type": "n8n-nodes-base.postgres",
"position": [
1168,
832
],
"parameters": {
"query": "DO $$\nBEGIN\n IF EXISTS (SELECT 1 FROM information_schema.tables WHERE table_name = 'documents_pg') THEN\n EXECUTE 'DELETE FROM documents_pg WHERE metadata->>''file_id'' LIKE ''%' || $1 || '%''';\n END IF;\nEND\n$$;",
"options": {
"queryReplacement": "={{ $json.file_id }}"
},
"operation": "executeQuery"
},
"typeVersion": 2.5
},
{
"id": "619a8a54-5fb8-4d8f-9cac-5a1c2a58f44b",
"name": "Supprimer les anciens enregistrements de données",
"type": "n8n-nodes-base.postgres",
"position": [
1328,
960
],
"parameters": {
"query": "DELETE FROM document_rows\nWHERE dataset_id LIKE '%' || $1 || '%';",
"options": {
"queryReplacement": "={{ $('Set File ID').item.json.file_id }}"
},
"operation": "executeQuery"
},
"typeVersion": 2.5
},
{
"id": "c975f943-3c05-45eb-9b11-4bd254845fbc",
"name": "Magasin Postgres PGVector",
"type": "@n8n/n8n-nodes-langchain.vectorStorePGVector",
"position": [
3184,
1072
],
"parameters": {
"mode": "insert",
"options": {},
"tableName": "documents_pg"
},
"typeVersion": 1
},
{
"id": "9bba5830-ad14-454c-b653-48baf03844bb",
"name": "Magasin Postgres PGVector 1",
"type": "@n8n/n8n-nodes-langchain.vectorStorePGVector",
"position": [
2464,
288
],
"parameters": {
"mode": "retrieve-as-tool",
"options": {},
"toolName": "documents",
"tableName": "documents_pg",
"toolDescription": "Use RAG to look up information in the knowledgebase."
},
"typeVersion": 1
}
],
"active": false,
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"versionId": "43f092c7-957d-42d3-8ea5-26108c4cd991",
"connections": {
"2ee45951-3553-49b7-9f79-3cef3d065e8a": {
"main": [
[
{
"node": "e8ba5c17-3426-4d76-b69b-ff91dff7958f",
"type": "main",
"index": 0
}
],
[
{
"node": "20bf7dde-e073-4288-a9d6-34df3973b5c3",
"type": "main",
"index": 0
}
],
[
{
"node": "b79ceb0b-f370-4ffb-9953-14b411acb5d9",
"type": "main",
"index": 0
}
],
[
{
"node": "a137d00b-fb01-408c-9963-645e2beb44d9",
"type": "main",
"index": 0
}
]
]
},
"06e362d1-d20c-407a-a75a-ed175c07439d": {
"main": [
[
{
"node": "55abb8ac-7988-430a-ae41-5155471228a2",
"type": "main",
"index": 0
}
]
]
},
"b40eb123-d7fc-4799-b248-4b9516aee49e": {
"main": [
[
{
"node": "0e3755e8-9532-447f-9137-f65d542c247e",
"type": "main",
"index": 0
}
]
]
},
"0e3755e8-9532-447f-9137-f65d542c247e": {
"main": [
[
{
"node": "f1840995-3f1c-4f4e-9d78-bc9225ecbe2b",
"type": "main",
"index": 0
},
{
"node": "c975f943-3c05-45eb-9b11-4bd254845fbc",
"type": "main",
"index": 0
}
]
]
},
"f1840995-3f1c-4f4e-9d78-bc9225ecbe2b": {
"main": [
[
{
"node": "3265a7df-dd40-421e-b1fb-53293a7460f8",
"type": "main",
"index": 0
}
]
]
},
"55abb8ac-7988-430a-ae41-5155471228a2": {
"main": [
[
{
"node": "b185f2be-06bf-4a14-8d58-4b411a709f18",
"type": "main",
"index": 0
}
]
]
},
"9c407f2b-4f6a-46d6-a607-225c1c628ae5": {
"main": [
[
{
"node": "987a6081-cdfd-457e-a2e5-4fa93fa018f4",
"type": "main",
"index": 0
}
]
]
},
"b185f2be-06bf-4a14-8d58-4b411a709f18": {
"main": [
[
{
"node": "8ccc451e-2fac-49b0-8700-085476add599",
"type": "main",
"index": 0
}
]
]
},
"55ff6535-bedb-479f-b3da-eb45e1127e77": {
"ai_tool": [
[
{
"node": "b185f2be-06bf-4a14-8d58-4b411a709f18",
"type": "ai_tool",
"index": 0
}
]
]
},
"4abe03ca-297c-4509-b0db-7bed4338a158": {
"main": [
[],
[
{
"node": "9c407f2b-4f6a-46d6-a607-225c1c628ae5",
"type": "main",
"index": 0
}
]
]
},
"e8ba5c17-3426-4d76-b69b-ff91dff7958f": {
"main": [
[
{
"node": "c975f943-3c05-45eb-9b11-4bd254845fbc",
"type": "main",
"index": 0
}
]
]
},
"b79ceb0b-f370-4ffb-9953-14b411acb5d9": {
"main": [
[
{
"node": "b40eb123-d7fc-4799-b248-4b9516aee49e",
"type": "main",
"index": 0
},
{
"node": "bbf6f704-b4a2-4ff2-ac09-27626526b35f",
"type": "main",
"index": 0
}
]
]
},
"366e800a-9bd7-4822-a11c-f555800bbba6": {
"ai_embedding": [
[
{
"node": "c975f943-3c05-45eb-9b11-4bd254845fbc",
"type": "ai_embedding",
"index": 0
}
]
]
},
"ffcb630b-5119-4ff6-b85a-d77eeb8d5713": {
"ai_tool": [
[
{
"node": "b185f2be-06bf-4a14-8d58-4b411a709f18",
"type": "ai_tool",
"index": 0
}
]
]
},
"be37cfb9-ea40-4244-87d7-b562be315573": {
"ai_embedding": [
[
{
"node": "9bba5830-ad14-454c-b653-48baf03844bb",
"type": "ai_embedding",
"index": 0
}
]
]
},
"20bf7dde-e073-4288-a9d6-34df3973b5c3": {
"main": [
[
{
"node": "b40eb123-d7fc-4799-b248-4b9516aee49e",
"type": "main",
"index": 0
},
{
"node": "bbf6f704-b4a2-4ff2-ac09-27626526b35f",
"type": "main",
"index": 0
}
]
]
},
"cdee87fe-e154-47ab-9330-32dee5c213d3": {
"main": [
[
{
"node": "4abe03ca-297c-4509-b0db-7bed4338a158",
"type": "main",
"index": 0
}
]
]
},
"397d00eb-8034-49e5-a8f6-0a0fd9b97d5b": {
"ai_document": [
[
{
"node": "c975f943-3c05-45eb-9b11-4bd254845fbc",
"type": "ai_document",
"index": 0
}
]
]
},
"f504b2f4-ffb5-4ef7-ba93-753151b77d9e": {
"ai_tool": [
[
{
"node": "b185f2be-06bf-4a14-8d58-4b411a709f18",
"type": "ai_tool",
"index": 0
}
]
]
},
"1aec304d-7264-4e65-8654-cb9294c96c82": {
"ai_memory": [
[
{
"node": "b185f2be-06bf-4a14-8d58-4b411a709f18",
"type": "ai_memory",
"index": 0
}
]
]
},
"a137d00b-fb01-408c-9963-645e2beb44d9": {
"main": [
[
{
"node": "c975f943-3c05-45eb-9b11-4bd254845fbc",
"type": "main",
"index": 0
}
]
]
},
"987a6081-cdfd-457e-a2e5-4fa93fa018f4": {
"main": [
[
{
"node": "619a8a54-5fb8-4d8f-9cac-5a1c2a58f44b",
"type": "main",
"index": 0
}
]
]
},
"619a8a54-5fb8-4d8f-9cac-5a1c2a58f44b": {
"main": [
[
{
"node": "e382d750-85ba-492d-9d3e-eb839af0bfc1",
"type": "main",
"index": 0
}
]
]
},
"c975f943-3c05-45eb-9b11-4bd254845fbc": {
"main": [
[
{
"node": "4abe03ca-297c-4509-b0db-7bed4338a158",
"type": "main",
"index": 0
}
]
]
},
"e382d750-85ba-492d-9d3e-eb839af0bfc1": {
"main": [
[
{
"node": "67311475-7928-4ddc-957a-79817c98d26d",
"type": "main",
"index": 0
}
]
]
},
"677ad468-8118-4f8f-9a47-f5429cdc7582": {
"ai_languageModel": [
[
{
"node": "b185f2be-06bf-4a14-8d58-4b411a709f18",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"9bba5830-ad14-454c-b653-48baf03844bb": {
"ai_tool": [
[
{
"node": "b185f2be-06bf-4a14-8d58-4b411a709f18",
"type": "ai_tool",
"index": 0
}
]
]
},
"67311475-7928-4ddc-957a-79817c98d26d": {
"main": [
[
{
"node": "2ee45951-3553-49b7-9f79-3cef3d065e8a",
"type": "main",
"index": 0
}
]
]
},
"78b3fd17-23e9-4693-b782-918a5a8e5aed": {
"main": [
[
{
"node": "55abb8ac-7988-430a-ae41-5155471228a2",
"type": "main",
"index": 0
}
]
]
},
"1306b972-2b24-4c62-846e-f1c5b3d0482c": {
"ai_textSplitter": [
[
{
"node": "397d00eb-8034-49e5-a8f6-0a0fd9b97d5b",
"type": "ai_textSplitter",
"index": 0
}
]
]
}
}
}Comment utiliser ce workflow ?
Copiez le code de configuration JSON ci-dessus, créez un nouveau workflow dans votre instance n8n et sélectionnez "Importer depuis le JSON", collez la configuration et modifiez les paramètres d'authentification selon vos besoins.
Dans quelles scénarios ce workflow est-il adapté ?
Avancé - Wiki interne, RAG IA
Est-ce payant ?
Ce workflow est entièrement gratuit et peut être utilisé directement. Veuillez noter que les services tiers utilisés dans le workflow (comme l'API OpenAI) peuvent nécessiter un paiement de votre part.
Workflows recommandés
Jadai kongolo
@jadai-ai-automationHi 👋 I'm Jadai kongolo. As an AI Automation Expert, I’m passionate about simplifying tech and empowering small businesses and young coders through AI automation. With my AI agency, Oki, I create efficient, n8n-powered workflows that save time, streamline operations, and boost growth for SMBs.
Partager ce workflow