Conversational RAG

The workflow JSON

Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →

{
  "name": "Conversational RAG",
  "nodes": [
    {
      "parameters": {
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
      "typeVersion": 1.2,
      "position": [
        -1720,
        440
      ],
      "id": "9a5673f1-0e60-402b-80e3-96e87ea48926",
      "name": "Embeddings OpenAI",
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "typeVersion": 1.4,
      "position": [
        -2288,
        0
      ],
      "id": "21323550-71c0-4694-bd5e-6a8b063cbef2",
      "name": "[Trigger] Chat Input"
    },
    {
      "parameters": {
        "promptType": "define",
        "text": "=You are a helpful and strictly factual AI assistant. \nYour primary task is to answer the user's question based ONLY on the provided documents from the Vector Store.\n\nRULES:\n1. If the answer is not explicitly stated in the provided documents, you MUST say: \"\u0628\u0627 \u062a\u0648\u062c\u0647 \u0628\u0647 \u0627\u0633\u0646\u0627\u062f \u0627\u0631\u0627\u0626\u0647\u200c\u0634\u062f\u0647\u060c \u0627\u0637\u0644\u0627\u0639\u0627\u062a\u06cc \u062f\u0631 \u0627\u06cc\u0646 \u0645\u0648\u0631\u062f \u0648\u062c\u0648\u062f \u0646\u062f\u0627\u0631\u062f.\" (Do NOT make up information or use your pre-trained knowledge).\n2. Always cite the title of the document you are using to answer.\n3. Be concise and direct.\n4. If the user asks about multiple items, ensure you check all provided context chunks before answering.\n\nuser massage :{{ $json.chatInput }}",
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.agent",
      "typeVersion": 3.1,
      "position": [
        -2000,
        0
      ],
      "id": "444ba438-16a2-4f8f-b536-9d5b4dc5861c",
      "name": "[Agent] RAG Assistant"
    },
    {
      "parameters": {
        "model": {
          "__rl": true,
          "value": "gpt-4o-mini",
          "mode": "list",
          "cachedResultName": "gpt-4o-mini"
        },
        "builtInTools": {},
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "typeVersion": 1.3,
      "position": [
        -2096,
        224
      ],
      "id": "dda52b9f-daf3-4249-ae3e-96601518a23e",
      "name": "[model] gpt-4o-mini",
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "contextWindowLength": 10
      },
      "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
      "typeVersion": 1.4,
      "position": [
        -1928,
        232
      ],
      "id": "86e2f822-0340-4d7e-91c7-0d1ef5c4ba68",
      "name": "[Memory] 10-Msg Buffer"
    },
    {
      "parameters": {
        "mode": "retrieve-as-tool",
        "toolDescription": "work with my data\n",
        "qdrantCollection": {
          "__rl": true,
          "value": "my_rag",
          "mode": "list",
          "cachedResultName": "my_rag"
        },
        "topK": 6,
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
      "typeVersion": 1.3,
      "position": [
        -1800,
        232
      ],
      "id": "9db77231-c4be-476b-b839-3af125da2c2e",
      "name": "[Tool] Qdrant Retriever",
      "credentials": {
        "qdrantApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "respondWith": "json",
        "options": {}
      },
      "type": "n8n-nodes-base.respondToWebhook",
      "typeVersion": 1.5,
      "position": [
        -1552,
        0
      ],
      "id": "f9794e6d-0f3d-4db9-bfa5-0491635187b3",
      "name": "[Output] Send Chat Response"
    }
  ],
  "connections": {
    "Embeddings OpenAI": {
      "ai_embedding": [
        [
          {
            "node": "[Tool] Qdrant Retriever",
            "type": "ai_embedding",
            "index": 0
          }
        ]
      ]
    },
    "[Trigger] Chat Input": {
      "main": [
        [
          {
            "node": "[Agent] RAG Assistant",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "[Agent] RAG Assistant": {
      "main": [
        [
          {
            "node": "[Output] Send Chat Response",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "[model] gpt-4o-mini": {
      "ai_languageModel": [
        [
          {
            "node": "[Agent] RAG Assistant",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "[Memory] 10-Msg Buffer": {
      "ai_memory": [
        [
          {
            "node": "[Agent] RAG Assistant",
            "type": "ai_memory",
            "index": 0
          }
        ]
      ]
    },
    "[Tool] Qdrant Retriever": {
      "ai_tool": [
        [
          {
            "node": "[Agent] RAG Assistant",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    }
  },
  "active": false,
  "settings": {
    "executionOrder": "v1",
    "binaryMode": "separate",
    "availableInMCP": false
  },
  "meta": {
    "templateCredsSetupCompleted": false
  },
  "nodeGroups": [],
  "tags": []
}

Credentials you'll need

Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.

• openAiApi
• qdrantApi

About this workflow

Conversational RAG. Uses embeddingsOpenAi, chatTrigger, agent, lmChatOpenAi. Chat trigger; 7 nodes.

Source: https://github.com/mryusefi/rag-chatbot-qdrant/blob/main/conversational-rag.json — original creator credit. Request a take-down →

More AI & RAG workflows → · Browse all categories →

Related workflows

Workflows that share integrations, category, or trigger type with this one. All free to copy and import.