Agente RAG Final

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": "Agente_RAG_final",
  "nodes": [
    {
      "parameters": {
        "inputSource": "passthrough"
      },
      "id": "c055762a-8fe7-4141-a639-df2372f30060",
      "typeVersion": 1.1,
      "name": "When_Executed_by_Main_Workflow",
      "type": "n8n-nodes-base.executeWorkflowTrigger",
      "position": [
        272,
        352
      ]
    },
    {
      "parameters": {
        "method": "POST",
        "url": "https://openrouter.ai/api/v1/embeddings",
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
            {
              "name": "Authorization",
              "value": "Bearer YOUR_API_KEY"
            },
            {
              "name": "Content-Type",
              "value": "application/json"
            }
          ]
        },
        "sendBody": true,
        "bodyParameters": {
          "parameters": [
            {
              "name": "model",
              "value": "text-embedding-3-small"
            },
            {
              "name": "input",
              "value": "={{ $json.mensaje_actual }}"
            }
          ]
        },
        "options": {}
      },
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.4,
      "position": [
        496,
        352
      ],
      "id": "9cab4f9b-a774-42b9-ae51-82928d5bdf1f",
      "name": "Embeddings_Openrouter"
    },
    {
      "parameters": {
        "jsCode": "const embedding = $input.first().json.data[0].embedding;\nconst datos = $('When_Executed_by_Main_Workflow').first().json;\n\nreturn [{\n  json: {\n    ...datos,\n    embedding: JSON.stringify(embedding)\n  }\n}];"
      },
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        704,
        352
      ],
      "id": "9c24bbe8-af20-48f3-a980-85f197c646db",
      "name": "Parsear_embedding_mensaje"
    },
    {
      "parameters": {
        "operation": "executeQuery",
        "query": "SELECT contenido, metadata, similarity\nFROM buscar_documentos(\n  '{{ $json.embedding }}'::vector,\n  5,\n  0.5\n);",
        "options": {}
      },
      "type": "n8n-nodes-base.postgres",
      "typeVersion": 2.6,
      "position": [
        912,
        352
      ],
      "id": "b1588b8f-bd22-42a4-aff6-9f7983021728",
      "name": "Buscar_documentos",
      "alwaysOutputData": true,
      "credentials": {
        "postgres": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "jsCode": "const docs = $input.all();\nconst datos = $('When_Executed_by_Main_Workflow').first().json;\n\nlet contexto = '';\nif (docs.length === 0 || !docs[0].json.contenido) {\n  contexto = 'No se encontr\u00f3 informaci\u00f3n relevante en los documentos.';\n} else {\n  contexto = docs.map((d, i) => \n    `[Fuente ${i+1}] (similitud: ${(d.json.similarity * 100).toFixed(1)}%):\\n${d.json.contenido}`\n  ).join('\\n\\n');\n}\n\nreturn [{\n  json: {\n    ...datos,\n    contexto\n  }\n}];"
      },
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        1120,
        352
      ],
      "id": "490bc121-3126-4b3a-8693-1ff6eba3484b",
      "name": "Formatear_contexto"
    },
    {
      "parameters": {
        "promptType": "define",
        "text": "={{ $json.mensaje_actual }}",
        "needsFallback": true,
        "messages": {
          "messageValues": [
            {
              "type": "HumanMessagePromptTemplate",
              "message": "=Historial previo:\n{{ $json.historial_texto }}\n\nInformaci\u00f3n disponible:\n{{ $json.contexto }}\n\nPregunta del cliente: {{ $json.mensaje_actual }}"
            },
            {
              "message": "Eres un asistente virtual de Inmobiliaria CBBA, Cochabamba, Bolivia. Respondes preguntas de clientes usando \u00daNICAMENTE la informaci\u00f3n del contexto proporcionado.  Reglas importantes: - Responde SOLO con informaci\u00f3n del contexto - Si el contexto no tiene la informaci\u00f3n, di: \"No tengo esa informaci\u00f3n disponible, te recomiendo contactarnos directamente\" - Menciona siempre la fuente (Fuente 1, Fuente 2, etc.) - S\u00e9 amable, conciso y profesional - Responde en espa\u00f1ol - No inventes precios, direcciones ni datos que no est\u00e9n en el contexto"
            }
          ]
        },
        "batching": {}
      },
      "type": "@n8n/n8n-nodes-langchain.chainLlm",
      "typeVersion": 1.9,
      "position": [
        1344,
        352
      ],
      "id": "ea966399-33e7-440b-94cd-e84eb04e581f",
      "name": "Basic LLM Chain"
    },
    {
      "parameters": {
        "model": "llama-3.1-8b-instant",
        "options": {
          "temperature": 0.2
        }
      },
      "type": "@n8n/n8n-nodes-langchain.lmChatGroq",
      "typeVersion": 1,
      "position": [
        1296,
        624
      ],
      "id": "38b63ac0-d402-4498-97fa-853b6fcc7925",
      "name": "Groq Chat Model",
      "credentials": {
        "groqApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "options": {
          "temperature": 0.2
        }
      },
      "type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
      "typeVersion": 1,
      "position": [
        1488,
        624
      ],
      "id": "f8829f3f-8685-40e0-8e02-7201ebf7b23d",
      "name": "Google Gemini Chat Model",
      "credentials": {
        "googlePalmApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "jsCode": "const respuesta = $input.first().json.text;\nconst datos = $('When_Executed_by_Main_Workflow').first().json;\n\nreturn [{\n  json: {\n    ...datos,\n    respuesta: respuesta,\n    agente_usado: 'RAG'\n  }\n}];"
      },
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        1696,
        352
      ],
      "id": "32ecf915-da2b-464a-be7b-a61dbf1f5b58",
      "name": "Formatear_respuesta_RAG"
    }
  ],
  "connections": {
    "When_Executed_by_Main_Workflow": {
      "main": [
        [
          {
            "node": "Embeddings_Openrouter",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Embeddings_Openrouter": {
      "main": [
        [
          {
            "node": "Parsear_embedding_mensaje",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Parsear_embedding_mensaje": {
      "main": [
        [
          {
            "node": "Buscar_documentos",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Buscar_documentos": {
      "main": [
        [
          {
            "node": "Formatear_contexto",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Groq Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "Basic LLM Chain",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Google Gemini Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "Basic LLM Chain",
            "type": "ai_languageModel",
            "index": 1
          }
        ]
      ]
    },
    "Formatear_contexto": {
      "main": [
        [
          {
            "node": "Basic LLM Chain",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Basic LLM Chain": {
      "main": [
        [
          {
            "node": "Formatear_respuesta_RAG",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "active": false,
  "settings": {
    "executionOrder": "v1",
    "availableInMCP": false,
    "timeSavedMode": "fixed",
    "errorWorkflow": "Lg4ma3dxwZeqgxOJDE0ew",
    "callerPolicy": "workflowsFromSameOwner",
    "binaryMode": "separate"
  },
  "versionId": "77f0058a-6210-411d-896e-4b947678bbf1",
  "meta": {
    "templateCredsSetupCompleted": true
  },
  "id": "6UBqCSPwybMxiOQ0",
  "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.

• googlePalmApi
• groqApi
• postgres

About this workflow

Agente_RAG_final. Uses executeWorkflowTrigger, httpRequest, postgres, chainLlm. Event-driven trigger; 9 nodes.

Source: https://github.com/sergioRancibia/n8n-automation-ai-agents-portfolio/blob/main/n8n-ai-automation-system/workflows/agente-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.