Construire un pipeline RAG pour la base de connaissances GLPI avec Google Gemini et PostgreSQL
Ceci est unInternal Wiki, Multimodal AIworkflow d'automatisation du domainecontenant 9 nœuds.Utilise principalement des nœuds comme Agent, ChatTrigger, LmChatGoogleGemini, MemoryBufferWindow, VectorStorePGVector. Construire un pipeline RAG pour la base de connaissances GLPI avec Google Gemini et PostgreSQL
- •Clé API Google Gemini
Nœuds utilisés (9)
Catégorie
{
"meta": {
"instanceId": "98986c4dc0b4b2af9fd0666d254f8b80e6e6b2044e2f3f3eedc76242999f4b5e",
"templateCredsSetupCompleted": true
},
"nodes": [
{
"id": "faa18c92-30d0-481f-b073-0b5efa68fbdf",
"name": "Agent IA",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
3824,
992
],
"parameters": {},
"typeVersion": 1.8
},
{
"id": "dd67e0b2-9986-4506-813e-d9d79b0b9f7b",
"name": "Modèle de chat Google Gemini",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
3392,
1232
],
"parameters": {},
"typeVersion": 1
},
{
"id": "0667b08a-42f9-4c74-9560-75f196147468",
"name": "À la réception du message",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
3488,
992
],
"webhookId": "8850cfe1-5a35-4bc9-9c02-91ccf4b82c58",
"parameters": {},
"typeVersion": 1.1
},
{
"id": "e828b8eb-b88f-425b-aaca-7081a0145c08",
"name": "Incorporations Google Gemini1",
"type": "@n8n/n8n-nodes-langchain.embeddingsGoogleGemini",
"position": [
4192,
1440
],
"parameters": {},
"typeVersion": 1
},
{
"id": "6f220ede-5bbf-48b7-a5b1-48052fb1dd87",
"name": "Note adhésive",
"type": "n8n-nodes-base.stickyNote",
"position": [
3488,
800
],
"parameters": {
"content": ""
},
"typeVersion": 1
},
{
"id": "761568e7-36aa-4dd2-8dc1-a037b0c27218",
"name": "Incorporations Google Gemini3",
"type": "@n8n/n8n-nodes-langchain.embeddingsGoogleGemini",
"position": [
3904,
1424
],
"parameters": {},
"typeVersion": 1
},
{
"id": "e25c8e1e-a871-491e-ad86-fd9575700f96",
"name": "CONHECIMENTO_TI_GLPI",
"type": "@n8n/n8n-nodes-langchain.vectorStorePGVector",
"position": [
4208,
1280
],
"parameters": {},
"typeVersion": 1.1
},
{
"id": "19487e55-30d4-4570-a9e2-6ff9ce92c615",
"name": "CONFLUENCE_TI_CONFLUENCE_SGU_GPL",
"type": "@n8n/n8n-nodes-langchain.vectorStorePGVector",
"position": [
3824,
1264
],
"parameters": {},
"typeVersion": 1.1
},
{
"id": "2fe1ca70-36ee-4593-bf7d-33bc1d4ea9f9",
"name": "Simple Mémoire",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
3648,
1248
],
"parameters": {},
"typeVersion": 1.3
}
],
"pinData": {},
"connections": {
"AI Agent": {
"main": [
[]
]
},
"Simple Memory": {
"ai_memory": [
[
{
"node": "AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"e25c8e1e-a871-491e-ad86-fd9575700f96": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Google Gemini Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Embeddings Google Gemini1": {
"ai_embedding": [
[
{
"node": "e25c8e1e-a871-491e-ad86-fd9575700f96",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Embeddings Google Gemini3": {
"ai_embedding": [
[
{
"node": "19487e55-30d4-4570-a9e2-6ff9ce92c615",
"type": "ai_embedding",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"19487e55-30d4-4570-a9e2-6ff9ce92c615": {
"ai_tool": [
[]
]
}
}
}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 ?
Intermédiaire - Wiki interne, IA Multimodale
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
Thiago Vazzoler Loureiro
@thiagovazzolerBuilding Custom Automations with n8n | Node.js Developer | Integration Specialist | Open Source Contributor If you need help with n8n workflows, API integrations, or custom nodes, feel free to connect on LinkedIn: http://linkedin.com/in/thiago-vazzoler-loureiro-24056227
Partager ce workflow