AI RAG Code Assistant Chat

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": "RAG Code Assistant",
  "nodes": [
    {
      "parameters": {},
      "id": "chat-trigger",
      "name": "When chat message received",
      "type": "n8n-nodes-base.chatTrigger",
      "typeVersion": 1,
      "position": [
        0,
        0
      ]
    },
    {
      "parameters": {
        "options": {
          "systemMessage": "You are a helpful Code Assistant. You have access to a RAG system to search code, explain symbols, and index the codebase.\n\nAlways use the 'search_code' tool to find relevant code before answering questions about the codebase.\nIf the user asks to index a folder, use 'index_code'."
        }
      },
      "id": "ai-agent",
      "name": "AI Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "typeVersion": 1.6,
      "position": [
        220,
        0
      ]
    },
    {
      "parameters": {
        "model": "gpt-4o-mini",
        "options": {
          "temperature": 0.3
        }
      },
      "id": "openai-model",
      "name": "OpenAI Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "typeVersion": 1,
      "position": [
        220,
        220
      ],
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "method": "POST",
        "url": "http://localhost:8000/query",
        "authentication": "none",
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
            {
              "name": "Content-Type",
              "value": "application/json"
            }
          ]
        },
        "sendBody": true,
        "bodyParameters": {
          "parameters": [
            {
              "name": "query",
              "value": "={{ $fromAI(\"query\") }}"
            },
            {
              "name": "k",
              "value": "5"
            }
          ]
        },
        "toolDescription": "Search the codebase for code snippets relevant to the query.",
        "toolName": "search_code"
      },
      "id": "tool-search",
      "name": "Search Code",
      "type": "@n8n/n8n-nodes-langchain.toolHttpRequest",
      "typeVersion": 1,
      "position": [
        500,
        -100
      ]
    },
    {
      "parameters": {
        "method": "POST",
        "url": "http://localhost:8000/index",
        "authentication": "none",
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
            {
              "name": "Content-Type",
              "value": "application/json"
            }
          ]
        },
        "sendBody": true,
        "bodyParameters": {
          "parameters": [
            {
              "name": "path",
              "value": "={{ $fromAI(\"path\") }}"
            },
            {
              "name": "force",
              "value": false
            }
          ]
        },
        "toolDescription": "Index the codebase at a specific path. Use this when the user asks to index or update the code.",
        "toolName": "index_code"
      },
      "id": "tool-index",
      "name": "Index Code",
      "type": "@n8n/n8n-nodes-langchain.toolHttpRequest",
      "typeVersion": 1,
      "position": [
        660,
        -100
      ]
    },
    {
      "parameters": {
        "method": "POST",
        "url": "http://localhost:8000/mcp",
        "authentication": "none",
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
            {
              "name": "Content-Type",
              "value": "application/json"
            }
          ]
        },
        "sendBody": true,
        "bodyParameters": {
          "parameters": [
            {
              "name": "method",
              "value": "rag.explain"
            },
            {
              "name": "params",
              "value": "={{ { \"symbol\": $fromAI(\"symbol\") } }}"
            },
            {
              "name": "id",
              "value": 1
            }
          ]
        },
        "toolDescription": "Get an explanation for a specific code symbol or concept.",
        "toolName": "explain_symbol"
      },
      "id": "tool-explain",
      "name": "Explain Symbol",
      "type": "@n8n/n8n-nodes-langchain.toolHttpRequest",
      "typeVersion": 1,
      "position": [
        820,
        -100
      ]
    }
  ],
  "connections": {
    "When chat message received": {
      "main": [
        [
          {
            "node": "AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Search Code": {
      "ai_tool": [
        [
          {
            "node": "AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "Index Code": {
      "ai_tool": [
        [
          {
            "node": "AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "Explain Symbol": {
      "ai_tool": [
        [
          {
            "node": "AI Agent",
            "type": "ai_tool",
            "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.

• openAiApi

About this workflow

RAG Code Assistant. Uses chatTrigger, agent, lmChatOpenAi, toolHttpRequest. Chat trigger; 6 nodes.

Source: https://github.com/dthompsonfl/jules_rag/blob/8e82a4d651bfd0385b8860b013b9452da7b5dcda/n8n/rag_workflow.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.