Insérer et récupérer des documents
Avancé
Ceci est unAIworkflow d'automatisation du domainecontenant 25 nœuds.Utilise principalement des nœuds comme Set, Code, Html, Limit, SplitOut, combinant la technologie d'intelligence artificielle pour une automatisation intelligente. Construire un système de questions-réponses RAG avec citations en utilisant Paul Essays, Milvus et OpenAI
Prérequis
- •Peut nécessiter les informations d'identification d'authentification de l'API cible
- •Clé API OpenAI
Nœuds utilisés (25)
Catégorie
Aperçu du workflow
Visualisation des connexions entre les nœuds, avec support du zoom et du déplacement
Exporter le workflow
Copiez la configuration JSON suivante dans n8n pour importer et utiliser ce workflow
{
"id": "Hjyv9FkH5Oh6Yxw4",
"meta": {
"instanceId": "2c4c1e23e7b067270c08aab616bada21d0c384d16f212b23cf1143c6baa09219"
},
"name": "Insert and retrieve documents",
"tags": [
{
"id": "msnDWKHQmwMDxWQH",
"name": "Milvus",
"createdAt": "2025-04-16T12:48:14.539Z",
"updatedAt": "2025-04-16T12:48:14.539Z"
},
{
"id": "tnCpo8hq8uKrdASK",
"name": "AI",
"createdAt": "2025-04-16T12:47:57.976Z",
"updatedAt": "2025-04-16T12:47:57.976Z"
}
],
"nodes": [
{
"id": "52044ccd-4e0d-4353-b612-cf8db1b55331",
"name": "Lors du clic sur 'Exécuter le workflow'",
"type": "n8n-nodes-base.manualTrigger",
"position": [
-500,
-100
],
"parameters": {},
"typeVersion": 1
},
{
"id": "b6993775-d21b-4ae8-a59c-43aef2b7002b",
"name": "Récupérer la liste des essais",
"type": "n8n-nodes-base.httpRequest",
"position": [
-220,
-100
],
"parameters": {
"url": "http://www.paulgraham.com/articles.html",
"options": {}
},
"typeVersion": 4.2
},
{
"id": "cbaeb236-5c93-4b34-a06b-ff0e5de8525f",
"name": "Extraire les noms des essais",
"type": "n8n-nodes-base.html",
"position": [
-20,
-100
],
"parameters": {
"options": {},
"operation": "extractHtmlContent",
"extractionValues": {
"values": [
{
"key": "essay",
"attribute": "href",
"cssSelector": "table table a",
"returnArray": true,
"returnValue": "attribute"
}
]
}
},
"typeVersion": 1.2
},
{
"id": "d92b6692-4a02-4519-b113-8a9172c71de9",
"name": "Diviser en éléments",
"type": "n8n-nodes-base.splitOut",
"position": [
180,
-100
],
"parameters": {
"options": {},
"fieldToSplitOut": "essay"
},
"typeVersion": 1
},
{
"id": "d16ba71b-10fc-454f-8bfc-a6826280a4e7",
"name": "Récupérer les textes des essais",
"type": "n8n-nodes-base.httpRequest",
"position": [
580,
-100
],
"parameters": {
"url": "=http://www.paulgraham.com/{{ $json.essay }}",
"options": {}
},
"typeVersion": 4.2
},
{
"id": "c4fa74ea-6af5-410c-bf5c-9d8d3decf31b",
"name": "Limiter aux 3 premiers",
"type": "n8n-nodes-base.limit",
"position": [
380,
-100
],
"parameters": {
"maxItems": 3
},
"typeVersion": 1
},
{
"id": "3da8495b-62df-475d-b99d-e0f3c64266e3",
"name": "Extraire uniquement le texte",
"type": "n8n-nodes-base.html",
"position": [
900,
-100
],
"parameters": {
"options": {},
"operation": "extractHtmlContent",
"extractionValues": {
"values": [
{
"key": "data",
"cssSelector": "body",
"skipSelectors": "img,nav"
}
]
}
},
"typeVersion": 1.2
},
{
"id": "4a9b5d5d-fc94-40b7-af0c-13d992bc1eb9",
"name": "Note adhésive 3",
"type": "n8n-nodes-base.stickyNote",
"position": [
-300,
-220
],
"parameters": {
"width": 1071.752021563343,
"height": 285.66037735849045,
"content": "## Scrape latest Paul Graham essays"
},
"typeVersion": 1
},
{
"id": "b8a7a288-186f-4444-b0de-33ed90009c0a",
"name": "Note adhésive 5",
"type": "n8n-nodes-base.stickyNote",
"position": [
820,
-220
],
"parameters": {
"width": 625,
"height": 607,
"content": "## Load into Milvus vector store"
},
"typeVersion": 1
},
{
"id": "c9e7b166-cc65-47e2-a437-9c00017b492a",
"name": "Séparateur de texte récursif par caractères 1",
"type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
"position": [
1240,
240
],
"parameters": {
"options": {},
"chunkSize": 6000
},
"typeVersion": 1
},
{
"id": "e1a75f27-7c8c-4d0d-9b0f-33fe9ec96fc6",
"name": "Générer une réponse",
"type": "n8n-nodes-base.set",
"position": [
1240,
560
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "11396286-0378-4c3a-86e1-c9ef51afbfc7",
"name": "text",
"type": "string",
"value": "={{ $json.answer }} {{ $if(!$json.citations.isEmpty(), \"\\n\" + $json.citations.join(\"\"), '') }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "8b3497ad-5bc8-44b3-bdf4-3a028fe265ce",
"name": "Composer les citations",
"type": "n8n-nodes-base.set",
"position": [
1040,
560
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "ace6185e-8b3d-4f89-ae36-dfe0c391a0a9",
"name": "citations",
"type": "array",
"value": "={{ $json.citations.map(i => '[' + $('Get top chunks matching query').all()[$json.citations].json.document.metadata.file_name + ', lines ' + $('Get top chunks matching query').all()[$json.citations].json.document.metadata['loc.lines.from'] + '-' + $('Get top chunks matching query').all()[$json.citations].json.document.metadata['loc.lines.to'] + ']') }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "0452cf15-145c-49dd-8803-4c8b8a7adbea",
"name": "Répondre à la requête basée sur les segments",
"type": "@n8n/n8n-nodes-langchain.informationExtractor",
"position": [
680,
560
],
"parameters": {
"text": "={{ $json.context }}\n\nQuestion: {{ $('When chat message received').first().json.chatInput }}\nHelpful Answer:",
"options": {
"systemPromptTemplate": "=Use the following pieces of context to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer. Important: In your response, also include the the indexes of the chunks you used to generate the answer."
},
"schemaType": "manual",
"inputSchema": "{\n \"type\": \"object\",\n \"required\": [\"answer\", \"citations\"],\n \"properties\": {\n \"answer\": {\n \"type\": \"string\"\n },\n \"citations\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"number\"\n }\n }\n }\n}"
},
"typeVersion": 1
},
{
"id": "d385ac35-6f94-4101-99de-5ce1991f40c4",
"name": "Préparer les segments",
"type": "n8n-nodes-base.code",
"position": [
480,
560
],
"parameters": {
"jsCode": "let out = \"\"\nfor (const i in $input.all()) {\n let itemText = \"--- CHUNK \" + i + \" ---\\n\"\n itemText += $input.all()[i].json.document.pageContent + \"\\n\"\n itemText += \"\\n\"\n out += itemText\n}\n\nreturn {\n 'context': out\n};"
},
"typeVersion": 2
},
{
"id": "379837f2-4f96-43ff-8e87-722cbe6d652f",
"name": "Définir le nombre maximal de segments à envoyer au modèle",
"type": "n8n-nodes-base.set",
"position": [
-300,
560
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "33f4addf-72f3-4618-a6ba-5b762257d723",
"name": "chunks",
"type": "number",
"value": 4
}
]
},
"includeOtherFields": true
},
"typeVersion": 3.4
},
{
"id": "9bc391bb-df47-41df-b170-9df47a6b5e87",
"name": "Embeddings OpenAI 2",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
-100,
780
],
"parameters": {
"model": "text-embedding-ada-002",
"options": {}
},
"credentials": {
"openAiApi": {
"id": "hH2PTDH4fbS7fdPv",
"name": "OpenAi account"
}
},
"typeVersion": 1.2
},
{
"id": "efb030f4-445b-4ba0-b5c9-95e4e5893664",
"name": "Lors de la réception d'un message de chat",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
-540,
560
],
"webhookId": "cd2703a7-f912-46fe-8787-3fb83ea116ab",
"parameters": {
"options": {}
},
"typeVersion": 1.1
},
{
"id": "c74943be-0008-4d4c-9dea-598a648a97a2",
"name": "Note adhésive 1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-380,
440
],
"parameters": {
"color": 7,
"width": 1594,
"height": 529,
"content": ""
},
"typeVersion": 1
},
{
"id": "2e27f3d8-e8a2-4647-80dd-f2643b224cb5",
"name": "Magasin de vecteurs Milvus en récupération",
"type": "@n8n/n8n-nodes-langchain.vectorStoreMilvus",
"position": [
0,
560
],
"parameters": {
"mode": "load",
"topK": 2,
"prompt": "answer the question",
"milvusCollection": {
"__rl": true,
"mode": "list",
"value": "my_collection",
"cachedResultName": "my_collection"
}
},
"credentials": {
"milvusApi": {
"id": "8tMHHoLiWXIAXa7S",
"name": "Milvus account"
}
},
"typeVersion": 1.1
},
{
"id": "a3cf7e0e-f681-4880-9ccf-5c42d5457c0f",
"name": "Magasin de vecteurs Milvus",
"type": "@n8n/n8n-nodes-langchain.vectorStoreMilvus",
"position": [
1120,
-100
],
"parameters": {
"mode": "insert",
"options": {
"clearCollection": true
},
"milvusCollection": {
"__rl": true,
"mode": "list",
"value": "my_collection",
"cachedResultName": "my_collection"
}
},
"credentials": {
"milvusApi": {
"id": "8tMHHoLiWXIAXa7S",
"name": "Milvus account"
}
},
"typeVersion": 1.1
},
{
"id": "4c4cc5a5-e880-466f-a298-4af53a2acbec",
"name": "Note adhésive",
"type": "n8n-nodes-base.stickyNote",
"position": [
-700,
-260
],
"parameters": {
"width": 280,
"height": 180,
"content": "## Step 1\n1. Set up a Milvus server based on [this guide](https://milvus.io/docs/install_standalone-docker-compose.md). And then create a collection named `my_collection`.\n2. Click this workflow to load scrape and load Paul Graham essays to Milvus collection.\n"
},
"typeVersion": 1
},
{
"id": "18f42da4-42ea-4eb0-9c43-ef8bd31ab7ff",
"name": "Note adhésive 2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-680,
460
],
"parameters": {
"height": 120,
"content": "## Step 2\nChat and get citations in response"
},
"typeVersion": 1
},
{
"id": "0af427ed-d901-4192-9fdc-986a63fd585b",
"name": "Embeddings OpenAI",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
1020,
140
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"id": "hH2PTDH4fbS7fdPv",
"name": "OpenAi account"
}
},
"typeVersion": 1.2
},
{
"id": "3603852a-bf12-4289-9733-dcd29d12a4f6",
"name": "Chargeur de données par défaut",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
1160,
120
],
"parameters": {
"options": {},
"jsonData": "={{ $('Extract Text Only').item.json.data }}",
"jsonMode": "expressionData"
},
"typeVersion": 1
},
{
"id": "b49eb3ae-82cb-4d87-8f22-0789b3a14d83",
"name": "Modèle de chat OpenAI",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
680,
780
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"id": "hH2PTDH4fbS7fdPv",
"name": "OpenAi account"
}
},
"typeVersion": 1.2
}
],
"active": false,
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"versionId": "5dc48a1d-aaf0-4052-9666-28f9e76d198c",
"connections": {
"d385ac35-6f94-4101-99de-5ce1991f40c4": {
"main": [
[
{
"node": "0452cf15-145c-49dd-8803-4c8b8a7adbea",
"type": "main",
"index": 0
}
]
]
},
"b6993775-d21b-4ae8-a59c-43aef2b7002b": {
"main": [
[
{
"node": "cbaeb236-5c93-4b34-a06b-ff0e5de8525f",
"type": "main",
"index": 0
}
]
]
},
"c4fa74ea-6af5-410c-bf5c-9d8d3decf31b": {
"main": [
[
{
"node": "d16ba71b-10fc-454f-8bfc-a6826280a4e7",
"type": "main",
"index": 0
}
]
]
},
"8b3497ad-5bc8-44b3-bdf4-3a028fe265ce": {
"main": [
[
{
"node": "e1a75f27-7c8c-4d0d-9b0f-33fe9ec96fc6",
"type": "main",
"index": 0
}
]
]
},
"0af427ed-d901-4192-9fdc-986a63fd585b": {
"ai_embedding": [
[
{
"node": "a3cf7e0e-f681-4880-9ccf-5c42d5457c0f",
"type": "ai_embedding",
"index": 0
}
]
]
},
"3da8495b-62df-475d-b99d-e0f3c64266e3": {
"main": [
[
{
"node": "a3cf7e0e-f681-4880-9ccf-5c42d5457c0f",
"type": "main",
"index": 0
}
]
]
},
"d16ba71b-10fc-454f-8bfc-a6826280a4e7": {
"main": [
[
{
"node": "3da8495b-62df-475d-b99d-e0f3c64266e3",
"type": "main",
"index": 0
}
]
]
},
"b49eb3ae-82cb-4d87-8f22-0789b3a14d83": {
"ai_languageModel": [
[
{
"node": "0452cf15-145c-49dd-8803-4c8b8a7adbea",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"9bc391bb-df47-41df-b170-9df47a6b5e87": {
"ai_embedding": [
[
{
"node": "2e27f3d8-e8a2-4647-80dd-f2643b224cb5",
"type": "ai_embedding",
"index": 0
}
]
]
},
"3603852a-bf12-4289-9733-dcd29d12a4f6": {
"ai_document": [
[
{
"node": "a3cf7e0e-f681-4880-9ccf-5c42d5457c0f",
"type": "ai_document",
"index": 0
}
]
]
},
"cbaeb236-5c93-4b34-a06b-ff0e5de8525f": {
"main": [
[
{
"node": "d92b6692-4a02-4519-b113-8a9172c71de9",
"type": "main",
"index": 0
}
]
]
},
"d92b6692-4a02-4519-b113-8a9172c71de9": {
"main": [
[
{
"node": "c4fa74ea-6af5-410c-bf5c-9d8d3decf31b",
"type": "main",
"index": 0
}
]
]
},
"379837f2-4f96-43ff-8e87-722cbe6d652f": {
"main": [
[
{
"node": "2e27f3d8-e8a2-4647-80dd-f2643b224cb5",
"type": "main",
"index": 0
}
]
]
},
"0452cf15-145c-49dd-8803-4c8b8a7adbea": {
"main": [
[
{
"node": "8b3497ad-5bc8-44b3-bdf4-3a028fe265ce",
"type": "main",
"index": 0
}
]
]
},
"2e27f3d8-e8a2-4647-80dd-f2643b224cb5": {
"main": [
[
{
"node": "d385ac35-6f94-4101-99de-5ce1991f40c4",
"type": "main",
"index": 0
}
]
]
},
"52044ccd-4e0d-4353-b612-cf8db1b55331": {
"main": [
[
{
"node": "b6993775-d21b-4ae8-a59c-43aef2b7002b",
"type": "main",
"index": 0
}
]
]
},
"c9e7b166-cc65-47e2-a437-9c00017b492a": {
"ai_textSplitter": [
[
{
"node": "3603852a-bf12-4289-9733-dcd29d12a4f6",
"type": "ai_textSplitter",
"index": 0
}
]
]
}
}
}Foire aux questions
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 - Intelligence Artificielle
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
Créer un système de questions-réponses pour les articles de Paul Graham avec OpenAI et la base de données vectorielle Milvus
Utiliser OpenAI et la base de données vectorielle Milvus pour créer un système de question-réponse sur les articles de Paul Graham
Html
Limit
Split Out
+
Html
Limit
Split Out
22 NœudsCheney Zhang
Intelligence Artificielle
Explorer les nœuds n8n dans la bibliothèque de références visuelles
Explorer les nœuds n8n dans la base de références visuelles
If
Ftp
Set
+
If
Ftp
Set
113 NœudsI versus AI
Autres
Chatbot d'entreprise B2BHR IA pour les politiques et avantages des employés
Chatbot d'entreprise piloté par l'IA pour les politiques et avantages BambooHR
Set
Filter
Bamboo Hr
+
Set
Filter
Bamboo Hr
50 NœudsLudwig
Ressources Humaines
[Modèle] AI Pet Shop v8
🐶 Assistant de magasin de pets IA - Intégration de GPT-4o, Google Calendar et WhatsApp/Instagram/Facebook
If
N8n
Set
+
If
N8n
Set
244 NœudsAmanda Benks
Ventes
Agent IA restaurant [Modèle]
🤖 Assistant IA pour WhatsApp, Instagram et Messenger
If
N8n
Set
+
If
N8n
Set
239 NœudsAmanda Benks
Autres
contenugénérateur v3
AI驱动blogautomatisation：utilisationGPT-4génération并publicationSEOarticle至WordPressetTwitter
If
Set
Code
+
If
Set
Code
144 NœudsJay Emp0
Création de contenu
Informations sur le workflow
Niveau de difficulté
Avancé
Nombre de nœuds25
Catégorie1
Types de nœuds15
Description de la difficulté
Auteur
Cheney Zhang
@zc277584121Algorithm engineer at Zilliz, dedicating to the application of vector databases in the AI ecosystem.
Liens externes
Voir sur n8n.io →
Partager ce workflow