AutomationFlowsAI & RAG › Auto-generate Faq Answers in Vtiger CRM with Deepseek LLM and Langchain

Auto-generate Faq Answers in Vtiger CRM with Deepseek LLM and Langchain

ByAhmed Saadawi @ahmedsaadawi on n8n.io

This workflow contains community nodes that are only compatible with the self-hosted version of n8n.

Cron / scheduled trigger★★★★☆ complexityAI-powered8 nodesN8N Nodes Vtiger CrmAgentLm Chat Deep SeekMemory Buffer Window
AI & RAG Trigger: Cron / scheduled Nodes: 8 Complexity: ★★★★☆ AI nodes: yes Added:

This workflow corresponds to n8n.io template #6308 — we link there as the canonical source.

This workflow follows the Agent → Lmchatdeepseek recipe pattern — see all workflows that pair these two integrations.

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 →

Download .json
{
  "id": "chYsh0pJpFivekfQ",
  "meta": {
    "templateCredsSetupCompleted": true
  },
  "name": "Vtiger CRM answer FAQ by DeepSeek LLM",
  "tags": [],
  "nodes": [
    {
      "id": "4cf51b80-921d-4b76-b368-cb52e4c5b1ae",
      "name": "Vtiger",
      "type": "n8n-nodes-vtiger-crm.vtigerNode",
      "position": [
        -688,
        -224
      ],
      "parameters": {
        "query_field": "select * from Faq where faqstatus='Draft' order by id desc limit 1;"
      },
      "credentials": {
        "vtigerApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "56e98463-5a93-438d-acd6-8a47d9e5a03d",
      "name": "Vtiger1",
      "type": "n8n-nodes-vtiger-crm.vtigerNode",
      "position": [
        144,
        -240
      ],
      "parameters": {
        "operation": "update",
        "element_field": "={\n  \"faq_answer\": {{ JSON.stringify($json.output) }},\n\"faqstatus\": \"Published\"\n}",
        "webservice_id_field": "={{ $('Vtiger').item.json.result[0].id }}"
      },
      "credentials": {
        "vtigerApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "79457836-4a32-42b8-a21e-a015eb1398b2",
      "name": "If",
      "type": "n8n-nodes-base.if",
      "position": [
        -528,
        -224
      ],
      "parameters": {
        "options": {},
        "conditions": {
          "options": {
            "version": 2,
            "leftValue": "",
            "caseSensitive": true,
            "typeValidation": "strict"
          },
          "combinator": "and",
          "conditions": [
            {
              "id": "1a4121a1-3315-48c6-b319-be947242e291",
              "operator": {
                "type": "string",
                "operation": "notEmpty",
                "singleValue": true
              },
              "leftValue": "={{ $json.result[0].id }}",
              "rightValue": ""
            }
          ]
        }
      },
      "typeVersion": 2.2
    },
    {
      "id": "75eae6a3-c2f4-4e2e-ae8f-25dfcd836efa",
      "name": "AI Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        -256,
        -240
      ],
      "parameters": {
        "text": "=Output as plain text, {{ $json.result[0].question }}",
        "options": {},
        "promptType": "define"
      },
      "typeVersion": 2.1
    },
    {
      "id": "c74887f0-da3d-4c7c-a87f-84087d37c320",
      "name": "DeepSeek Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatDeepSeek",
      "position": [
        -256,
        -32
      ],
      "parameters": {
        "options": {}
      },
      "credentials": {
        "deepSeekApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "784b3e33-e62d-4ef6-80ac-b4d8a02a0b19",
      "name": "Simple Memory",
      "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
      "position": [
        -128,
        -32
      ],
      "parameters": {
        "sessionKey": "={{ $json.result[0].question }}",
        "sessionIdType": "customKey"
      },
      "typeVersion": 1.3
    },
    {
      "id": "b2693d93-4f03-4692-8c5f-16e472b98b33",
      "name": "Schedule Trigger Every n Minutes",
      "type": "n8n-nodes-base.scheduleTrigger",
      "position": [
        -944,
        -224
      ],
      "parameters": {
        "rule": {
          "interval": [
            {
              "field": "minutes",
              "minutesInterval": 1
            }
          ]
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "f3987ade-529e-493c-a3a9-e22b2ba10fe8",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -736,
        -656
      ],
      "parameters": {
        "width": 816,
        "height": 384,
        "content": "### \ud83e\udde0 Auto-Answer FAQ Drafts with AI  \n**(Vtiger CRM + DeepSeek + LangChain)**\n\nThis workflow runs **every 1 minute** to:\n- \ud83d\udce5 Fetch the latest `Draft` FAQ from Vtiger CRM\n- \ud83e\udd16 Use **DeepSeek LLM** via **LangChain** to generate a plain-text answer\n- \ud83d\udce4 Automatically update the FAQ with the answer and mark it as `Published`\n---\n> \ud83d\udca1 **Note:**  \n> This workflow uses a custom **Vtiger CRM** node from the **Community Nodes** registry.  \n> To install it in your self-hosted n8n:\n> 1. Go to `Settings` \u2192 `Community Nodes`\n> 2. Click **Install Node** then enter:  \n> ```bash\n> n8n-nodes-vtiger-crm\n> ```\n---\n> \u2705 Perfect for teams that want to auto-fill answers and speed up knowledge base publishing!"
      },
      "typeVersion": 1
    }
  ],
  "active": true,
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "bf3f1f93-3711-494c-9544-2f39f6e45ee8",
  "connections": {
    "If": {
      "main": [
        [
          {
            "node": "AI Agent",
            "type": "main",
            "index": 0
          }
        ],
        []
      ]
    },
    "Vtiger": {
      "main": [
        [
          {
            "node": "If",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Vtiger1": {
      "main": [
        []
      ]
    },
    "AI Agent": {
      "main": [
        [
          {
            "node": "Vtiger1",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Simple Memory": {
      "ai_memory": [
        [
          {
            "node": "AI Agent",
            "type": "ai_memory",
            "index": 0
          }
        ]
      ]
    },
    "DeepSeek Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Schedule Trigger Every n Minutes": {
      "main": [
        [
          {
            "node": "Vtiger",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}

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.

Pro

For the full experience including quality scoring and batch install features for each workflow upgrade to Pro

About this workflow

This workflow contains community nodes that are only compatible with the self-hosted version of n8n.

Source: https://n8n.io/workflows/6308/ — 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.

AI & RAG

This workflow is for beauty salons who want consistent, high‑quality social media content without writing every post manually. It also suits agencies and automation builders who manage multiple beauty

Telegram, Google Sheets Trigger, Agent +26
AI & RAG

This workflow contains community nodes that are only compatible with the self-hosted version of n8n.

Mailgun, OpenAI, OpenAI Chat +8
AI & RAG

⚠️ DISCLAIMER: This workflow uses the AnySite LinkedIn community node, which is only available on self-hosted n8n instances. It will not work on n8n.cloud.

OpenAI Chat, Output Parser Structured, Google Sheets +6
AI & RAG

BoomerBobBot.TP. Uses agent, telegramTrigger, telegram, memoryBufferWindow. Event-driven trigger; 95 nodes.

Agent, Telegram Trigger, Telegram +10
AI & RAG

What this workflow does

OpenAI Chat, Memory Buffer Window, Output Parser Structured +4