Frage-Antwort-KI-Agent bauen

Name: Frage-Antwort-KI-Agent bauen
Rating: 4.5 (10 reviews)
Author: Thomas Janssen

Fortgeschritten

Dies ist ein Engineering, AI RAG-Bereich Automatisierungsworkflow mit 12 Nodes. Hauptsächlich werden FormTrigger, McpClientTool, McpTrigger, EmbeddingsOllama, VectorStoreQdrant und andere Nodes verwendet. Frage-Antwort-KI-Agent mit Llama, RAG und Google Suche bauen

Voraussetzungen

•Qdrant-Serververbindungsdaten

Verwendete Nodes (12)

DocumentDefaultDataLoader

TextSplitterRecursiveCharacterTextSplitter

Kategorie

Engineering

KI RAG

Workflow-Vorschau

Visualisierung der Node-Verbindungen, mit Zoom und Pan

MCP Server Trigger

Qdrant Vektorspeicher

Einbettungen Ollama

MCP Client

MCP Client1

On form submission

Qdrant Vektorspeicher1

Einbettungen Ollama1

Default Data Loader

Recursive Character Text Splitter

React Flow

Workflow exportieren

Kopieren Sie die folgende JSON-Konfiguration und importieren Sie sie in n8n

{
  "meta": {
    "instanceId": "558d88703fb65b2d0e44613bc35916258b0f0bf983c5d4730c00c424b77ca36a",
    "templateCredsSetupCompleted": true
  },
  "nodes": [
    {
      "id": "95fbf42b-4efb-4301-8e8f-34859156534c",
      "name": "MCP Server Trigger",
      "type": "@n8n/n8n-nodes-langchain.mcpTrigger",
      "position": [
        0,
        0
      ],
      "webhookId": "8d7910ab-f0db-4042-9da9-f580647a8a8e",
      "parameters": {
        "path": "8d7910ab-f0db-4042-9da9-f580647a8a8e"
      },
      "typeVersion": 2
    },
    {
      "id": "0d2f7b7c-a2e2-43ec-baf1-d0e507977bab",
      "name": "Qdrant Vektorspeicher",
      "type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
      "position": [
        440,
        140
      ],
      "parameters": {
        "mode": "retrieve-as-tool",
        "options": {},
        "toolDescription": "Use this tool to retrieve data from a database",
        "qdrantCollection": {
          "__rl": true,
          "mode": "id",
          "value": "mcp_rag"
        }
      },
      "credentials": {
        "qdrantApi": {
          "id": "sFfERYppMeBnFNeA",
          "name": "Local QdrantApi database"
        }
      },
      "typeVersion": 1.3
    },
    {
      "id": "6c0a4301-66d6-40a6-b133-d809de367e0e",
      "name": "Einbettungen Ollama",
      "type": "@n8n/n8n-nodes-langchain.embeddingsOllama",
      "position": [
        620,
        320
      ],
      "parameters": {
        "model": "mxbai-embed-large:latest"
      },
      "credentials": {
        "ollamaApi": {
          "id": "xHuYe0MDGOs9IpBW",
          "name": "Local Ollama service"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "a0c04dfe-aa62-4dae-b0e2-b7882c1c06fd",
      "name": "MCP Client",
      "type": "n8n-nodes-mcp.mcpClientTool",
      "position": [
        -20,
        280
      ],
      "parameters": {},
      "credentials": {
        "mcpClientApi": {
          "id": "gtICJ1VBUVNpQahr",
          "name": "MCP Client (STDIO) account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "6b2e162e-3431-41e3-839e-5b4a206de768",
      "name": "MCP Client1",
      "type": "n8n-nodes-mcp.mcpClientTool",
      "position": [
        200,
        280
      ],
      "parameters": {
        "toolName": "execute_tool",
        "operation": "executeTool"
      },
      "credentials": {
        "mcpClientApi": {
          "id": "gtICJ1VBUVNpQahr",
          "name": "MCP Client (STDIO) account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "2989e6de-fe14-4215-ab7e-350b52faa011",
      "name": "Haftnotiz",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -80,
        -100
      ],
      "parameters": {
        "color": 5,
        "width": 880,
        "height": 620,
        "content": "## MCP Server\n**Will be triggered by the MCP Client"
      },
      "typeVersion": 1
    },
    {
      "id": "fb2c49d7-fa34-4ac9-b2e8-1d5dd9a73b3c",
      "name": "Haftnotiz1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        860,
        -100
      ],
      "parameters": {
        "color": 4,
        "width": 880,
        "height": 620,
        "content": "## RAG Ingestion Pipeline\n**Only run once to upload your documents"
      },
      "typeVersion": 1
    },
    {
      "id": "34e2aafe-c627-4af8-a673-16526802fbd5",
      "name": "On form submission",
      "type": "n8n-nodes-base.formTrigger",
      "position": [
        960,
        40
      ],
      "webhookId": "7d7ae610-42c0-4fbf-a286-df5c6b62a510",
      "parameters": {
        "options": {},
        "formTitle": "Ingest PDF Files in semantic database",
        "formFields": {
          "values": [
            {
              "fieldType": "file",
              "fieldLabel": "Upload a file",
              "acceptFileTypes": ".pdf"
            }
          ]
        }
      },
      "typeVersion": 2.2
    },
    {
      "id": "efb5839e-104c-4920-b932-34d9177a5c70",
      "name": "Qdrant Vektorspeicher1",
      "type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
      "position": [
        1180,
        40
      ],
      "parameters": {
        "mode": "insert",
        "options": {},
        "qdrantCollection": {
          "__rl": true,
          "mode": "id",
          "value": "mcp_rag"
        }
      },
      "credentials": {
        "qdrantApi": {
          "id": "sFfERYppMeBnFNeA",
          "name": "Local QdrantApi database"
        }
      },
      "typeVersion": 1.3
    },
    {
      "id": "92f0f26c-5af6-4943-bdbf-45777267598d",
      "name": "Einbettungen Ollama1",
      "type": "@n8n/n8n-nodes-langchain.embeddingsOllama",
      "position": [
        1100,
        300
      ],
      "parameters": {
        "model": "mxbai-embed-large:latest"
      },
      "credentials": {
        "ollamaApi": {
          "id": "xHuYe0MDGOs9IpBW",
          "name": "Local Ollama service"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "950a0544-43c4-4423-982e-b04408e46a97",
      "name": "Default Data Loader",
      "type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
      "position": [
        1400,
        220
      ],
      "parameters": {
        "options": {},
        "dataType": "binary",
        "textSplittingMode": "custom"
      },
      "typeVersion": 1.1
    },
    {
      "id": "7cd3a5f4-ffb1-4f93-9a7d-a40aea4aa64a",
      "name": "Recursive Character Text Splitter",
      "type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
      "position": [
        1300,
        360
      ],
      "parameters": {
        "options": {},
        "chunkSize": 400,
        "chunkOverlap": 100
      },
      "typeVersion": 1
    }
  ],
  "pinData": {},
  "connections": {
    "a0c04dfe-aa62-4dae-b0e2-b7882c1c06fd": {
      "ai_tool": [
        [
          {
            "node": "95fbf42b-4efb-4301-8e8f-34859156534c",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "6b2e162e-3431-41e3-839e-5b4a206de768": {
      "ai_tool": [
        [
          {
            "node": "95fbf42b-4efb-4301-8e8f-34859156534c",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "Embeddings Ollama": {
      "ai_embedding": [
        [
          {
            "node": "Qdrant Vector Store",
            "type": "ai_embedding",
            "index": 0
          }
        ]
      ]
    },
    "Embeddings Ollama1": {
      "ai_embedding": [
        [
          {
            "node": "Qdrant Vector Store1",
            "type": "ai_embedding",
            "index": 0
          }
        ]
      ]
    },
    "34e2aafe-c627-4af8-a673-16526802fbd5": {
      "main": [
        [
          {
            "node": "Qdrant Vector Store1",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "950a0544-43c4-4423-982e-b04408e46a97": {
      "ai_document": [
        [
          {
            "node": "Qdrant Vector Store1",
            "type": "ai_document",
            "index": 0
          }
        ]
      ]
    },
    "Qdrant Vector Store": {
      "ai_tool": [
        [
          {
            "node": "95fbf42b-4efb-4301-8e8f-34859156534c",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "7cd3a5f4-ffb1-4f93-9a7d-a40aea4aa64a": {
      "ai_textSplitter": [
        [
          {
            "node": "950a0544-43c4-4423-982e-b04408e46a97",
            "type": "ai_textSplitter",
            "index": 0
          }
        ]
      ]
    }
  }
}

Häufig gestellte Fragen

Wie verwende ich diesen Workflow?

Kopieren Sie den obigen JSON-Code, erstellen Sie einen neuen Workflow in Ihrer n8n-Instanz und wählen Sie "Aus JSON importieren". Fügen Sie die Konfiguration ein und passen Sie die Anmeldedaten nach Bedarf an.

Für welche Szenarien ist dieser Workflow geeignet?

Fortgeschritten - Engineering, KI RAG

Ist es kostenpflichtig?

Dieser Workflow ist völlig kostenlos. Beachten Sie jedoch, dass Drittanbieterdienste (wie OpenAI API), die im Workflow verwendet werden, möglicherweise kostenpflichtig sind.