RAG simple

Name: RAG simple
Rating: 4.5 (10 reviews)
Author: Aji Prakoso

Intermédiaire

Ceci est unInternal Wiki, AI RAGworkflow d'automatisation du domainecontenant 14 nœuds.Utilise principalement des nœuds comme FormTrigger, Agent, ChatTrigger, LmChatOpenAi, RerankerCohere. Construire un système RAG basé sur PDF avec OpenAI, Pinecone et le ré-arrangement Cohere

Prérequis

•Clé API OpenAI
•Clé API Pinecone

Nœuds utilisés (14)

DocumentDefaultDataLoader

TextSplitterRecursiveCharacterTextSplitter

Catégorie

Wiki interne

RAG IA

Aperçu du workflow

Visualisation des connexions entre les nœuds, avec support du zoom et du déplacement

À la soumission du formulaire

Pinecone Vector Store

Embeddings OpenAI

Chargeur de données par défaut

Séparateur de texte récursif

Agent IA

À la réception d'un message de chat

OpenAI Chat Model

Mémoire simple

VectorDB

Reranker Cohere

React Flow

Exporter le workflow

Copiez la configuration JSON suivante dans n8n pour importer et utiliser ce workflow

{
  "id": "pDhufDfHS9qRgtLf",
  "meta": {
    "instanceId": "fa52a98dd39f67760c7540fff8a0dd5306d89f766551eb7a7c84b5f43eb33d4c",
    "templateCredsSetupCompleted": true
  },
  "name": "Simple RAG",
  "tags": [],
  "nodes": [
    {
      "id": "93cd13c5-12ad-4c9c-aac7-1886a1d24470",
      "name": "À la soumission du formulaire",
      "type": "n8n-nodes-base.formTrigger",
      "position": [
        0,
        0
      ],
      "webhookId": "cab3dda4-3b49-4f05-a2c1-915ae4c62017",
      "parameters": {
        "options": {},
        "formTitle": "Upload RAG PDF",
        "formFields": {
          "values": [
            {
              "fieldType": "file",
              "fieldLabel": "File",
              "multipleFiles": false,
              "requiredField": true,
              "acceptFileTypes": ".pdf"
            }
          ]
        },
        "formDescription": "Upload RAG PDF"
      },
      "typeVersion": 2.2
    },
    {
      "id": "13fe2ba5-a24d-4198-8509-882eb4c08e1a",
      "name": "Pinecone Vector Store",
      "type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
      "position": [
        320,
        0
      ],
      "parameters": {
        "mode": "insert",
        "options": {},
        "pineconeIndex": {
          "__rl": true,
          "mode": "list",
          "value": "n8n",
          "cachedResultName": "n8n"
        }
      },
      "credentials": {
        "pineconeApi": {
          "id": "VP5fhue9NYRkdlCj",
          "name": "PineconeApi account"
        }
      },
      "typeVersion": 1.3
    },
    {
      "id": "aa3d1481-3da7-4ae1-9857-c64a71e28443",
      "name": "Embeddings OpenAI",
      "type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
      "position": [
        920,
        460
      ],
      "parameters": {
        "options": {
          "dimensions": 1024
        }
      },
      "credentials": {
        "openAiApi": {
          "id": "y8sLJ2LzZL2c7SGi",
          "name": "OpenAI Webinar"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "17350e15-5b99-493d-acd2-9f44fd661b09",
      "name": "Chargeur de données par défaut",
      "type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
      "position": [
        440,
        220
      ],
      "parameters": {
        "options": {},
        "dataType": "binary",
        "textSplittingMode": "custom"
      },
      "typeVersion": 1.1
    },
    {
      "id": "8199713d-cad8-4d17-937c-1b3b604b95ea",
      "name": "Séparateur de texte récursif",
      "type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
      "position": [
        520,
        440
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 1
    },
    {
      "id": "fcaf5178-4694-4e20-ac62-8da3c1c8279e",
      "name": "Note autocollante",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -60,
        -80
      ],
      "parameters": {
        "width": 880,
        "height": 680,
        "content": "## Insert Data to Pinecone"
      },
      "typeVersion": 1
    },
    {
      "id": "e094ded2-c2e9-4139-b6d0-df086f2e2049",
      "name": "Agent IA",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        1440,
        80
      ],
      "parameters": {
        "options": {
          "systemMessage": "Hanya jawab berdasarkan data yang ada di tools \"VectorDB\". Kalau data disitu gak ada, jawab saja kamu tidak tahu."
        }
      },
      "typeVersion": 2
    },
    {
      "id": "015d2a82-3c3d-4604-bbbf-7df57dd24269",
      "name": "À la réception d'un message de chat",
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "position": [
        1200,
        80
      ],
      "webhookId": "c1f8d15b-e096-47f8-922e-a7484ebbc25c",
      "parameters": {
        "options": {}
      },
      "typeVersion": 1.1
    },
    {
      "id": "a1b26946-9a3f-4aa2-a723-f91e196943cf",
      "name": "OpenAI Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        1280,
        300
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4.1",
          "cachedResultName": "gpt-4.1"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "y8sLJ2LzZL2c7SGi",
          "name": "OpenAI Webinar"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "6beecd5e-a8fc-4e69-8fbc-a0e0e90c4aa6",
      "name": "Mémoire simple",
      "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
      "position": [
        1480,
        300
      ],
      "parameters": {},
      "typeVersion": 1.3
    },
    {
      "id": "02b1aa4f-a291-4f2c-b6d9-0290d6b563ae",
      "name": "VectorDB",
      "type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
      "position": [
        1640,
        300
      ],
      "parameters": {
        "mode": "retrieve-as-tool",
        "topK": 20,
        "options": {},
        "useReranker": true,
        "pineconeIndex": {
          "__rl": true,
          "mode": "list",
          "value": "n8n",
          "cachedResultName": "n8n"
        },
        "toolDescription": "Ambil data dari vector database untuk knowledgebase"
      },
      "credentials": {
        "pineconeApi": {
          "id": "VP5fhue9NYRkdlCj",
          "name": "PineconeApi account"
        }
      },
      "typeVersion": 1.3
    },
    {
      "id": "bada58fc-73f4-431f-9702-e742a75ce2c3",
      "name": "Note autocollante1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1100,
        -80
      ],
      "parameters": {
        "color": 5,
        "width": 860,
        "height": 680,
        "content": "## Chat AI Agent"
      },
      "typeVersion": 1
    },
    {
      "id": "2e572866-dcf7-492f-aebe-35b12bc6b27d",
      "name": "Note autocollante2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        840,
        300
      ],
      "parameters": {
        "color": 4,
        "height": 300,
        "content": "## Embedding Model"
      },
      "typeVersion": 1
    },
    {
      "id": "6dcbbf3a-3acd-4170-9f79-c2441da18979",
      "name": "Reranker Cohere",
      "type": "@n8n/n8n-nodes-langchain.rerankerCohere",
      "position": [
        1740,
        480
      ],
      "parameters": {},
      "credentials": {
        "cohereApi": {
          "id": "yDA2nh2ZZXkR9tcq",
          "name": "Cohere API Trial"
        }
      },
      "typeVersion": 1
    }
  ],
  "active": false,
  "pinData": {},
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "6b1d46bd-ed09-4a25-a95e-fa5a3e2950f7",
  "connections": {
    "02b1aa4f-a291-4f2c-b6d9-0290d6b563ae": {
      "ai_tool": [
        [
          {
            "node": "e094ded2-c2e9-4139-b6d0-df086f2e2049",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "6beecd5e-a8fc-4e69-8fbc-a0e0e90c4aa6": {
      "ai_memory": [
        [
          {
            "node": "e094ded2-c2e9-4139-b6d0-df086f2e2049",
            "type": "ai_memory",
            "index": 0
          }
        ]
      ]
    },
    "6dcbbf3a-3acd-4170-9f79-c2441da18979": {
      "ai_reranker": [
        [
          {
            "node": "02b1aa4f-a291-4f2c-b6d9-0290d6b563ae",
            "type": "ai_reranker",
            "index": 0
          }
        ]
      ]
    },
    "aa3d1481-3da7-4ae1-9857-c64a71e28443": {
      "ai_embedding": [
        [
          {
            "node": "13fe2ba5-a24d-4198-8509-882eb4c08e1a",
            "type": "ai_embedding",
            "index": 0
          },
          {
            "node": "02b1aa4f-a291-4f2c-b6d9-0290d6b563ae",
            "type": "ai_embedding",
            "index": 0
          }
        ]
      ]
    },
    "a1b26946-9a3f-4aa2-a723-f91e196943cf": {
      "ai_languageModel": [
        [
          {
            "node": "e094ded2-c2e9-4139-b6d0-df086f2e2049",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "93cd13c5-12ad-4c9c-aac7-1886a1d24470": {
      "main": [
        [
          {
            "node": "13fe2ba5-a24d-4198-8509-882eb4c08e1a",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "17350e15-5b99-493d-acd2-9f44fd661b09": {
      "ai_document": [
        [
          {
            "node": "13fe2ba5-a24d-4198-8509-882eb4c08e1a",
            "type": "ai_document",
            "index": 0
          }
        ]
      ]
    },
    "13fe2ba5-a24d-4198-8509-882eb4c08e1a": {
      "main": [
        []
      ]
    },
    "015d2a82-3c3d-4604-bbbf-7df57dd24269": {
      "main": [
        [
          {
            "node": "e094ded2-c2e9-4139-b6d0-df086f2e2049",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "8199713d-cad8-4d17-937c-1b3b604b95ea": {
      "ai_textSplitter": [
        [
          {
            "node": "17350e15-5b99-493d-acd2-9f44fd661b09",
            "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 ?

Intermédiaire - 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.