Exemple de métrique d'évaluation : Vérifier si un outil est appelé

Name: Exemple de métrique d'évaluation : Vérifier si un outil est appelé
Rating: 4.5 (10 reviews)
Author: David Roberts

Intermédiaire

Ceci est unEngineering, AIworkflow d'automatisation du domainecontenant 15 nœuds.Utilise principalement des nœuds comme Set, Evaluation, Agent, HttpRequestTool, EvaluationTrigger, combinant la technologie d'intelligence artificielle pour une automatisation intelligente. Exemple d'indicateur d'évaluation : Vérifier si un outil est appelé

Prérequis

•Peut nécessiter les informations d'identification d'authentification de l'API cible
•Clé API OpenAI

Nœuds utilisés (15)

Catégorie

Ingénierie

Intelligence Artificielle

Aperçu du workflow

Visualisation des connexions entre les nœuds, avec support du zoom et du déplacement

Agent IA

OpenAI Modèle de chat

Calculatrice

Vérifier si l'outil est appelé

Récupérer une page web

Quand un message de chat est reçu

Correspondre au format de chat

Retourner une réponse de chat

Quand une ligne de jeu de données est récupérée

Évaluation

Évaluation en cours ?

React Flow

Exporter le workflow

Copiez la configuration JSON suivante dans n8n pour importer et utiliser ce workflow

{
  "meta": {
    "instanceId": "bf40384a063e00f3b983f4f9bada22b57a8231a04c0fb48d363e26d7b0f2b7e7",
    "templateCredsSetupCompleted": true
  },
  "nodes": [
    {
      "id": "ffd0cca6-4a60-4058-b3fb-c92d949ea864",
      "name": "Agent IA",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        -960,
        -120
      ],
      "parameters": {
        "options": {
          "returnIntermediateSteps": true
        }
      },
      "typeVersion": 1.9
    },
    {
      "id": "73055399-e667-45cb-8a32-accb83dd74f8",
      "name": "OpenAI Modèle de chat",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        -1000,
        140
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4o-mini"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "Ag9qPAsY7lpIGkvC",
          "name": "JPs n8n openAI key"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "54ffa0e9-dbf7-4406-9952-485ca46d1172",
      "name": "Calculatrice",
      "type": "@n8n/n8n-nodes-langchain.toolCalculator",
      "position": [
        -840,
        140
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "09dcce53-ce33-4263-b903-655db12d13dd",
      "name": "Vérifier si l'outil est appelé",
      "type": "n8n-nodes-base.set",
      "position": [
        -340,
        -240
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "58c48e6f-4a12-4bf6-94ae-705244273a84",
              "name": "tool_called",
              "type": "boolean",
              "value": "={{ $json.intermediateSteps.filter(x => x.action.tool == $('When fetching a dataset row').item.json.tool_to_call).length > 0 }}"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "62fb0980-6c8e-4ab6-b914-59339b4b385f",
      "name": "Récupérer une page web",
      "type": "n8n-nodes-base.httpRequestTool",
      "position": [
        -700,
        140
      ],
      "parameters": {
        "url": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('URL', ``, 'string') }}",
        "options": {}
      },
      "typeVersion": 4.2
    },
    {
      "id": "ec4c82df-8804-49f2-a8ba-348f29b97cd6",
      "name": "Note adhésive",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -980,
        -200
      ],
      "parameters": {
        "color": 7,
        "width": 300,
        "height": 220,
        "content": "Make sure to enable 'Return intermediate steps' in the agent, to get the list of executed tools"
      },
      "typeVersion": 1
    },
    {
      "id": "f6fa8aef-4362-4691-85fc-2612eb1dee63",
      "name": "Quand un message de chat est reçu",
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "position": [
        -1440,
        -240
      ],
      "webhookId": "c4dc43bf-4625-4821-bd9d-ca22a2f34170",
      "parameters": {
        "options": {}
      },
      "typeVersion": 1.1
    },
    {
      "id": "d1274230-aa4d-4456-93ea-8123e263df7d",
      "name": "Correspondre au format de chat",
      "type": "n8n-nodes-base.set",
      "position": [
        -1220,
        40
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "e6e064bb-ac06-40ca-97bf-42f682b30065",
              "name": "chatInput",
              "type": "string",
              "value": "={{ $json.question }}"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "474a2321-7a4c-41be-a8fa-718f5a093171",
      "name": "Note adhésive1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -380,
        -320
      ],
      "parameters": {
        "color": 7,
        "width": 180,
        "height": 240,
        "content": "Check whether the list of executed tools contains the target tool"
      },
      "typeVersion": 1
    },
    {
      "id": "3351706d-e7e9-4701-9224-b4c873167c0d",
      "name": "Retourner une réponse de chat",
      "type": "n8n-nodes-base.noOp",
      "position": [
        -340,
        40
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "e7beb2d8-f864-4aea-84f2-0d82987f52f8",
      "name": "Note adhésive3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1740,
        -280
      ],
      "parameters": {
        "width": 200,
        "height": 500,
        "content": "## How it works\nThis template shows how to calculate a workflow evaluation metric: **whether a specific tool was called** by an agent.\n\nYou can find more information on workflow evaluation [here](https://docs.n8n.io/advanced-ai/evaluations/overview), and other metric examples [here](https://docs.n8n.io/advanced-ai/evaluations/metric-based-evaluations/#2-calculate-metrics)."
      },
      "typeVersion": 1
    },
    {
      "id": "a990cca2-7ea5-4d43-9cc2-b6257299bcc1",
      "name": "Note adhésive4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1500,
        -60
      ],
      "parameters": {
        "color": 7,
        "width": 220,
        "height": 260,
        "content": "Read in [this test dataset](https://docs.google.com/spreadsheets/d/1uuPS5cHtSNZ6HNLOi75A2m8nVWZrdBZ_Ivf58osDAS8/edit?gid=969651976#gid=969651976) of questions and the tools that should be called when answering them"
      },
      "typeVersion": 1
    },
    {
      "id": "f0f7e18c-029f-4e0a-ac2f-168e10b5f51f",
      "name": "Quand une ligne de jeu de données est récupérée",
      "type": "n8n-nodes-base.evaluationTrigger",
      "position": [
        -1440,
        40
      ],
      "parameters": {
        "sheetName": {
          "__rl": true,
          "mode": "url",
          "value": "https://docs.google.com/spreadsheets/d/1uuPS5cHtSNZ6HNLOi75A2m8nVWZrdBZ_Ivf58osDAS8/edit?gid=969651976#gid=969651976"
        },
        "documentId": {
          "__rl": true,
          "mode": "url",
          "value": "https://docs.google.com/spreadsheets/d/1uuPS5cHtSNZ6HNLOi75A2m8nVWZrdBZ_Ivf58osDAS8/edit?gid=969651976#gid=969651976"
        }
      },
      "credentials": {
        "googleSheetsOAuth2Api": {
          "id": "bpr2LoSELMlxpwnN",
          "name": "Google Sheets account David"
        }
      },
      "typeVersion": 4.6
    },
    {
      "id": "e0c49dc5-a06b-4552-b53c-e5dfc51017e0",
      "name": "Évaluation",
      "type": "n8n-nodes-base.evaluation",
      "position": [
        -120,
        -240
      ],
      "parameters": {
        "metrics": {
          "assignments": [
            {
              "id": "66ed21d5-a10a-47a3-993d-459aa4a4fbba",
              "name": "tool_called",
              "type": "number",
              "value": "={{ $json.tool_called.toNumber() }}"
            }
          ]
        },
        "operation": "setMetrics"
      },
      "typeVersion": 4.6
    },
    {
      "id": "5b14c47b-2dae-4ca7-882c-d0ec722eadab",
      "name": "Évaluation en cours ?",
      "type": "n8n-nodes-base.evaluation",
      "position": [
        -580,
        -120
      ],
      "parameters": {
        "operation": "checkIfEvaluating"
      },
      "typeVersion": 4.6
    }
  ],
  "pinData": {},
  "connections": {
    "ffd0cca6-4a60-4058-b3fb-c92d949ea864": {
      "main": [
        [
          {
            "node": "5b14c47b-2dae-4ca7-882c-d0ec722eadab",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "54ffa0e9-dbf7-4406-9952-485ca46d1172": {
      "ai_tool": [
        [
          {
            "node": "ffd0cca6-4a60-4058-b3fb-c92d949ea864",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "5b14c47b-2dae-4ca7-882c-d0ec722eadab": {
      "main": [
        [
          {
            "node": "09dcce53-ce33-4263-b903-655db12d13dd",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "3351706d-e7e9-4701-9224-b4c873167c0d",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "62fb0980-6c8e-4ab6-b914-59339b4b385f": {
      "ai_tool": [
        [
          {
            "node": "ffd0cca6-4a60-4058-b3fb-c92d949ea864",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "d1274230-aa4d-4456-93ea-8123e263df7d": {
      "main": [
        [
          {
            "node": "ffd0cca6-4a60-4058-b3fb-c92d949ea864",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "73055399-e667-45cb-8a32-accb83dd74f8": {
      "ai_languageModel": [
        [
          {
            "node": "ffd0cca6-4a60-4058-b3fb-c92d949ea864",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "09dcce53-ce33-4263-b903-655db12d13dd": {
      "main": [
        [
          {
            "node": "e0c49dc5-a06b-4552-b53c-e5dfc51017e0",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "f6fa8aef-4362-4691-85fc-2612eb1dee63": {
      "main": [
        [
          {
            "node": "ffd0cca6-4a60-4058-b3fb-c92d949ea864",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "f0f7e18c-029f-4e0a-ac2f-168e10b5f51f": {
      "main": [
        [
          {
            "node": "d1274230-aa4d-4456-93ea-8123e263df7d",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}

Foire aux questions

Comment utiliser ce workflow ?

Copiez le code de configuration JSON ci-dessus, créez un nouveau workflow dans votre instance n8n et sélectionnez "Importer depuis le JSON", collez la configuration et modifiez les paramètres d'authentification selon vos besoins.

Dans quelles scénarios ce workflow est-il adapté ?

Intermédiaire - Ingénierie, Intelligence Artificielle

Est-ce payant ?

Ce workflow est entièrement gratuit et peut être utilisé directement. Veuillez noter que les services tiers utilisés dans le workflow (comme l'API OpenAI) peuvent nécessiter un paiement de votre part.