Génération de rapports de chronologie de machines virtuelles Azure avec l'assistant de chat Google Gemini AI

Intermédiaire

Ceci est unDevOps, AIworkflow d'automatisation du domainecontenant 11 nœuds.Utilise principalement des nœuds comme Set, Agent, ToolCode, ChatTrigger, ToolHttpRequest, combinant la technologie d'intelligence artificielle pour une automatisation intelligente. Utiliser l'assistant de chat Google Gemini AI pour générer un rapport de chronologie pour les machines virtuelles Azure

Prérequis
  • Peut nécessiter les informations d'identification d'authentification de l'API cible
  • Clé API Google Gemini
Aperçu du workflow
Visualisation des connexions entre les nœuds, avec support du zoom et du déplacement
Exporter le workflow
Copiez la configuration JSON suivante dans n8n pour importer et utiliser ce workflow
{
  "meta": {
    "instanceId": "dc70be25ab3de91313745487daa53ea6b35f677ae326eae305310e197f986f71",
    "templateCredsSetupCompleted": true
  },
  "nodes": [
    {
      "id": "214c1831-bd0d-431a-b811-bc29122f5bf1",
      "name": "Agent IA",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        1092,
        -780
      ],
      "parameters": {
        "text": "={{ $('When chat message received').item.json.chatInput }}",
        "options": {
          "systemMessage": "=You are an assistant that queries the user's Azure subscription for various Azure virtual machine information.\n\nThrough your tools, you have the ability to query information in Azure such as resource groups and virtual machines.\n\nYour task is to carefully analyze all information about one or more VMs and provide a timeline report to the user including VM state changes, CPU, network, disk activity, etc. The report will be broken down by VM and provide a historical timeline of what happened to a VM during that time.\n\nDo not ask the user questions unless absolutely necessary. He relies on you to make your own decisions.\n\nBy default, the user needs all events starting 90 days ago and newer but can override that with a request.\n\n"
        },
        "promptType": "define"
      },
      "typeVersion": 1.8
    },
    {
      "id": "1c5bee5e-bbd8-4a0c-bcdf-817540cf5b0f",
      "name": "Définir les variables communes",
      "type": "n8n-nodes-base.set",
      "position": [
        720,
        -780
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "942ba480-59b8-4a77-a36d-6f198b2b76b4",
              "name": "azure_subscription_id",
              "type": "string",
              "value": "<your azure subscription id here>"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "f2bc18f2-aa40-43b5-8738-0faa64aa5beb",
      "name": "Obtenir les statistiques de performance de la VM",
      "type": "@n8n/n8n-nodes-langchain.toolHttpRequest",
      "position": [
        1060,
        -500
      ],
      "parameters": {
        "url": "=https://management.azure.com/subscriptions/{{ $json.azure_subscription_id }}/resourceGroups/{azure_resource_group_name}/providers/Microsoft.Compute/virtualMachines/{vm_name}/providers/microsoft.insights/metrics",
        "sendQuery": true,
        "authentication": "predefinedCredentialType",
        "parametersQuery": {
          "values": [
            {
              "name": "api-version",
              "value": "2018-01-01",
              "valueProvider": "fieldValue"
            },
            {
              "name": "metricnames",
              "value": "Percentage CPU,Network In,Network Out,Disk Read Bytes,Disk Write Bytes",
              "valueProvider": "fieldValue"
            },
            {
              "name": "timespan",
              "value": "{from_time}/{to_time}&interval={interval}",
              "valueProvider": "fieldValue"
            },
            {
              "name": "aggregation",
              "value": "average,maximum",
              "valueProvider": "fieldValue"
            }
          ]
        },
        "toolDescription": "This tool returns performance metrics for a specific virtual machine (VM) in Azure. These metrics come from Azure Monitor and provide time-series data that helps you understand how the VM is performing over time. This includes key metrics like CPU usage (Percentage CPU), disk I/O, network in/out, and available memory, depending on what’s enabled for monitoring.\n\nYou can use query parameters (e.g., metricnames, timespan, interval, aggregation) to control which metrics are returned, over what time period, and at what granularity. The response includes metadata like the unit of measurement, timestamps, and aggregated values (e.g., average, minimum, maximum). This endpoint is commonly used for monitoring, alerting, and troubleshooting VM performance.",
        "nodeCredentialType": "microsoftAzureMonitorOAuth2Api",
        "placeholderDefinitions": {
          "values": [
            {
              "name": "azure_resource_group_name",
              "type": "string"
            },
            {
              "name": "vm_name",
              "type": "string"
            },
            {
              "name": "from_time",
              "type": "string",
              "description": "2025-05-18T20:01:52Z"
            },
            {
              "name": "to_time",
              "type": "string"
            },
            {
              "name": "interval",
              "description": " ISO 8601 duration format Options: PT1M (1min), PT5M (5min), PT15M (15min), PT30M (30min), PT1H (1hr), PT6H (6hr), PT12H (12hr), P1D (1day)"
            }
          ]
        }
      },
      "credentials": {
        "microsoftAzureMonitorOAuth2Api": {
          "id": "jUzjMChitb3DNqcr",
          "name": "Microsoft Azure Monitor"
        }
      },
      "typeVersion": 1.1
    },
    {
      "id": "58093475-6b4a-44b7-8a94-783de4c662f4",
      "name": "À la réception d'un message de chat",
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "position": [
        500,
        -780
      ],
      "webhookId": "def18753-6744-4666-8062-9cc37938ff3c",
      "parameters": {
        "options": {}
      },
      "typeVersion": 1.1
    },
    {
      "id": "006eb130-f4e6-4f6b-af5a-0f045eef9426",
      "name": "Modèle de chat Google Gemini",
      "type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
      "position": [
        600,
        -520
      ],
      "parameters": {
        "options": {},
        "modelName": "models/gemini-2.5-pro-preview-05-06"
      },
      "credentials": {
        "googlePalmApi": {
          "id": "MeEjlKe69mU8qQ3w",
          "name": "Google Gemini(PaLM) Api account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "838e66a3-0b0e-441d-aa02-d9dda32e3ce7",
      "name": "Mémoire simple",
      "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
      "position": [
        820,
        -460
      ],
      "parameters": {
        "sessionKey": "={{ $('When chat message received').item.json.sessionId }}",
        "sessionIdType": "customKey"
      },
      "typeVersion": 1.3
    },
    {
      "id": "30acbfb9-6938-475c-a97c-c8e9f93d8034",
      "name": "Obtenir les groupes de ressources Azure",
      "type": "@n8n/n8n-nodes-langchain.toolHttpRequest",
      "position": [
        1280,
        -520
      ],
      "parameters": {
        "url": "=https://management.azure.com/subscriptions/{{ $json.azure_subscription_id }}/resourcegroups?api-version=2021-04-01",
        "fields": "name, type",
        "dataField": "value",
        "authentication": "predefinedCredentialType",
        "fieldsToInclude": "selected",
        "toolDescription": "This tool returns a list of resource groups within the specified Azure subscription. A resource group is a container that holds related Azure resources like virtual machines, storage accounts, and databases. This API is useful for inventory, organization, and automation tasks.\n\nEach resource group object in the response includes basic metadata such as the name, location (region), id, and properties.provisioningState. It may also contain tags if they are defined. This endpoint is typically used to get an overview of how resources are grouped and managed across a subscription, and it’s often the first step in workflows that involve resource discovery or filtering by location or naming convention.",
        "optimizeResponse": true,
        "nodeCredentialType": "microsoftAzureMonitorOAuth2Api"
      },
      "credentials": {
        "microsoftAzureMonitorOAuth2Api": {
          "id": "jUzjMChitb3DNqcr",
          "name": "Microsoft Azure Monitor"
        }
      },
      "typeVersion": 1.1
    },
    {
      "id": "b5cd2f51-dde8-410f-a622-78d87bca9883",
      "name": "Obtenir les informations de la VM",
      "type": "@n8n/n8n-nodes-langchain.toolHttpRequest",
      "position": [
        1680,
        -680
      ],
      "parameters": {
        "url": "=https://management.azure.com/subscriptions/{{ $json.azure_subscription_id}}/resourceGroups/{azure_resource_group_name}/providers/Microsoft.Compute/virtualMachines",
        "fields": "name,location,tags,properties.hardwareProfile.vmSize",
        "dataField": "value",
        "sendQuery": true,
        "authentication": "predefinedCredentialType",
        "fieldsToInclude": "selected",
        "parametersQuery": {
          "values": [
            {
              "name": "api-version",
              "value": "2023-03-01",
              "valueProvider": "fieldValue"
            }
          ]
        },
        "toolDescription": "This tool returns a list of all virtual machines (VMs) within a specific resource group under a given subscription. The response is a JSON object that includes metadata for each VM, such as the VM name, location (Azure region), provisioning state, VM size (e.g., Standard_D2s_v3), OS type, and associated resources like network interfaces and storage profiles. Each VM entry may also include tags, availability zone info, and reference links to related resources like disks, NICs, or the OS image used.\n\nThis endpoint does not include live runtime data like power state or metrics (e.g., CPU usage). To get those, you’d need to call separate endpoints such as instance view (/virtualMachines/{vmName}/instanceView). The primary use case for this endpoint is inventory management—enumerating and describing all VMs in a group for configuration or auditing purposes.",
        "optimizeResponse": true,
        "nodeCredentialType": "microsoftAzureMonitorOAuth2Api",
        "placeholderDefinitions": {
          "values": [
            {
              "name": "azure_resource_group_name",
              "type": "string"
            }
          ]
        }
      },
      "credentials": {
        "microsoftAzureMonitorOAuth2Api": {
          "id": "jUzjMChitb3DNqcr",
          "name": "Microsoft Azure Monitor"
        }
      },
      "typeVersion": 1.1
    },
    {
      "id": "0159f464-6fb5-4ddf-8536-5dc7798bc484",
      "name": "Obtenir les événements de la VM",
      "type": "@n8n/n8n-nodes-langchain.toolHttpRequest",
      "position": [
        1980,
        -940
      ],
      "parameters": {
        "url": "=https://management.azure.com/subscriptions/{{ $json.azure_subscription_id }}/providers/microsoft.insights/eventtypes/management/values",
        "fields": "category.localizedValue, level, resourceGroupName, operationName.localizedValue, properties.title, properties.details, properties.type, properties.cause,eventTimestamp",
        "dataField": "value",
        "sendQuery": true,
        "authentication": "predefinedCredentialType",
        "fieldsToInclude": "selected",
        "parametersQuery": {
          "values": [
            {
              "name": "api-version",
              "value": "2015-04-01",
              "valueProvider": "fieldValue"
            },
            {
              "name": "$filter",
              "value": "=eventTimestamp ge '{{ $if('{start_timestamp}', '{start_timestamp}', DateTime.utc().minus({ days: 90 }).startOf('second').toISO()) }}'\n    {{ $if({vm_name}, ` and resourceId eq '/SUBSCRIPTIONS/${$json.azure_subscription_id}/RESOURCEGROUPS/{resource_group_name}/PROVIDERS/MICROSOFT.COMPUTE/VIRTUALMACHINES/{vm_name}`, ` and resourceGroupName eq '{resource_group_name}'`) }}'\n}",
              "valueProvider": "fieldValue"
            }
          ]
        },
        "toolDescription": "This tool returns a list of Azure Activity Log events related to management operations within a specific subscription. These events capture control-plane actions performed on Azure resources, such as creating, updating, or deleting virtual machines, storage accounts, resource groups, role assignments, and more. The log includes data on who initiated the action, when it occurred, what the operation was, its result (e.g. Succeeded, Failed), and which resource was affected.\n\nEach event in the response contains detailed fields such as eventTimestamp, operationName, status, caller, resourceId, and correlationId. This data is commonly used for auditing, compliance, and security monitoring. You can apply filters using query parameters like time range ($filter) to retrieve logs from a specific period. These logs do not contain data-plane information (like reading from a VM or querying a database)—only control-plane actions that change Azure resource state or configuration.",
        "optimizeResponse": true,
        "nodeCredentialType": "microsoftAzureMonitorOAuth2Api",
        "placeholderDefinitions": {
          "values": [
            {
              "name": "resource_group_name",
              "type": "string",
              "description": "Required"
            },
            {
              "name": "vm_name",
              "type": "string",
              "description": "Not required"
            },
            {
              "name": "start_timestamp",
              "type": "string",
              "description": "Not required. Value requires timestamp in ISO 8601 format. Convert for the user if another format is provided."
            }
          ]
        }
      },
      "credentials": {
        "microsoftAzureMonitorOAuth2Api": {
          "id": "jUzjMChitb3DNqcr",
          "name": "Microsoft Azure Monitor"
        }
      },
      "typeVersion": 1.1
    },
    {
      "id": "560c6ffe-e248-4b26-8752-db8be5e4056d",
      "name": "Obtenir la date actuelle",
      "type": "@n8n/n8n-nodes-langchain.toolCode",
      "position": [
        1840,
        -780
      ],
      "parameters": {
        "name": "get_current_date",
        "jsCode": "const curDate = new Date().toISOString()\nreturn curDate",
        "description": "Call this tool to get the current date"
      },
      "typeVersion": 1.1
    },
    {
      "id": "3adb5a18-38fe-4b94-9f5f-6937d51fe90f",
      "name": "Obtenir la vue d'instance de la VM",
      "type": "@n8n/n8n-nodes-langchain.toolHttpRequest",
      "position": [
        1500,
        -560
      ],
      "parameters": {
        "url": "=https://management.azure.com/subscriptions/{{ $json.azure_subscription_id }}/resourceGroups/{azure_resource_group_name}/providers/Microsoft.Compute/virtualMachines/{vm_name}/instanceView",
        "sendQuery": true,
        "authentication": "predefinedCredentialType",
        "parametersQuery": {
          "values": [
            {
              "name": "api-version",
              "value": "2023-09-01",
              "valueProvider": "fieldValue"
            }
          ]
        },
        "toolDescription": "This tool returns the instance view of a specific virtual machine. This provides runtime details that aren’t available through the standard VM configuration API. It includes information such as the VM’s power state (e.g., PowerState/running, stopped), provisioning status, and boot diagnostics.\n\nThe response also contains detailed status codes for each component of the VM, such as the OS disk, data disks, and VM agent. These status entries help diagnose health or startup issues. Unlike the general VM list, this endpoint is focused on the current operational state of the VM and is commonly used in monitoring dashboards or automation scripts that need to respond to VM lifecycle events.",
        "nodeCredentialType": "microsoftAzureMonitorOAuth2Api",
        "placeholderDefinitions": {
          "values": [
            {
              "name": "azure_resource_group_name",
              "type": "string"
            },
            {
              "name": "vm_name",
              "type": "string"
            }
          ]
        }
      },
      "credentials": {
        "microsoftAzureMonitorOAuth2Api": {
          "id": "jUzjMChitb3DNqcr",
          "name": "Microsoft Azure Monitor"
        }
      },
      "typeVersion": 1.1
    }
  ],
  "pinData": {},
  "connections": {
    "214c1831-bd0d-431a-b811-bc29122f5bf1": {
      "main": [
        []
      ]
    },
    "0159f464-6fb5-4ddf-8536-5dc7798bc484": {
      "ai_tool": [
        [
          {
            "node": "214c1831-bd0d-431a-b811-bc29122f5bf1",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "838e66a3-0b0e-441d-aa02-d9dda32e3ce7": {
      "ai_memory": [
        [
          {
            "node": "214c1831-bd0d-431a-b811-bc29122f5bf1",
            "type": "ai_memory",
            "index": 0
          }
        ]
      ]
    },
    "560c6ffe-e248-4b26-8752-db8be5e4056d": {
      "ai_tool": [
        [
          {
            "node": "214c1831-bd0d-431a-b811-bc29122f5bf1",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "b5cd2f51-dde8-410f-a622-78d87bca9883": {
      "ai_tool": [
        [
          {
            "node": "214c1831-bd0d-431a-b811-bc29122f5bf1",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "3adb5a18-38fe-4b94-9f5f-6937d51fe90f": {
      "ai_tool": [
        [
          {
            "node": "214c1831-bd0d-431a-b811-bc29122f5bf1",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "1c5bee5e-bbd8-4a0c-bcdf-817540cf5b0f": {
      "main": [
        [
          {
            "node": "214c1831-bd0d-431a-b811-bc29122f5bf1",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "f2bc18f2-aa40-43b5-8738-0faa64aa5beb": {
      "ai_tool": [
        [
          {
            "node": "214c1831-bd0d-431a-b811-bc29122f5bf1",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "006eb130-f4e6-4f6b-af5a-0f045eef9426": {
      "ai_languageModel": [
        [
          {
            "node": "214c1831-bd0d-431a-b811-bc29122f5bf1",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "30acbfb9-6938-475c-a97c-c8e9f93d8034": {
      "ai_tool": [
        [
          {
            "node": "214c1831-bd0d-431a-b811-bc29122f5bf1",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "58093475-6b4a-44b7-8a94-783de4c662f4": {
      "main": [
        [
          {
            "node": "1c5bee5e-bbd8-4a0c-bcdf-817540cf5b0f",
            "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 - DevOps, 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.

Informations sur le workflow
Niveau de difficulté
Intermédiaire
Nombre de nœuds11
Catégorie2
Types de nœuds7
Description de la difficulté

Adapté aux utilisateurs expérimentés, avec des workflows de complexité moyenne contenant 6-15 nœuds

Liens externes
Voir sur n8n.io

Partager ce workflow

Catégories

Catégories: 34