Analyse des ingrédients

Avancé

Ceci est unContent Creation, Multimodal AIworkflow d'automatisation du domainecontenant 17 nœuds.Utilise principalement des nœuds comme If, Switch, Telegram, Agent, TelegramTrigger. Utiliser Telegram et Gemini 2.5 Flash pour analyser les photos des ingrédients de produits

Prérequis
  • Token Bot Telegram
  • 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
{
  "id": "OHJxgg0BdTf2l363",
  "meta": {
    "instanceId": "eebe9c0070b02d0ee22eb0ed0c31d070c78a8b6ed60658384408eca35acc94ee",
    "templateCredsSetupCompleted": true
  },
  "name": "ingredients",
  "tags": [],
  "nodes": [
    {
      "id": "90b0a91c-bba7-41f3-8d90-af4947a7da10",
      "name": "Google Gemini Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
      "position": [
        688,
        -144
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 1
    },
    {
      "id": "716161e7-f0bb-4e4c-b0e2-ec98d4e199ff",
      "name": "Structured Output Parser",
      "type": "@n8n/n8n-nodes-langchain.outputParserStructured",
      "position": [
        848,
        -144
      ],
      "parameters": {
        "jsonSchemaExample": "{\n  \"recommendation\": \"Do Not Use\",\n  \"reason\": \"While this product contains...\"\n}\n"
      },
      "typeVersion": 1.3
    },
    {
      "id": "107f1ce4-0198-4a53-8f94-8fb9ffe53370",
      "name": "Google Gemini Chat Model1",
      "type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
      "position": [
        688,
        192
      ],
      "parameters": {
        "options": {}
      },
      "credentials": {
        "googlePalmApi": {
          "id": "CLs7gtUQzHCSgvqQ",
          "name": "Google Gemini(PaLM) Api account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "d3996282-5fb7-4e0e-8d1d-195b5703ac59",
      "name": "Structured Output Parser1",
      "type": "@n8n/n8n-nodes-langchain.outputParserStructured",
      "position": [
        832,
        192
      ],
      "parameters": {
        "jsonSchemaExample": "{\n  \"advantages\": [\"List clear benefits of these ingredients, including positive effects on health, skin, or hair.\"],\n  \"disadvantages\": [\"List risks or concerns such as allergens, irritants, harsh chemicals, or health warnings.\"],\n  \"recommended_for\": [\"Describe the group of people who can safely benefit from this product.\"],\n  \"not_recommended_for\": [\"Describe the group of people who should avoid it, such as those with allergies, sensitivities, or certain conditions.\"]\n}\n"
      },
      "typeVersion": 1.3
    },
    {
      "id": "5817f756-9d0f-445e-b860-29c530a93f86",
      "name": "Google Gemini Chat Model2",
      "type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
      "position": [
        96,
        320
      ],
      "parameters": {
        "options": {}
      },
      "credentials": {
        "googlePalmApi": {
          "id": "CLs7gtUQzHCSgvqQ",
          "name": "Google Gemini(PaLM) Api account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "a8169fcb-ebf7-4aab-ab3c-e3fb4f4ea181",
      "name": "Obtenir une photo/texte de message",
      "type": "n8n-nodes-base.telegramTrigger",
      "position": [
        -288,
        16
      ],
      "webhookId": "365bd415-f745-4c2b-b0c5-42a5024a74e2",
      "parameters": {
        "updates": [
          "message"
        ],
        "additionalFields": {}
      },
      "typeVersion": 1.2
    },
    {
      "id": "d3486786-42e0-4bbb-8449-ec011df85da6",
      "name": "Analyse les images de produits en utilisant Google Gemini",
      "type": "@n8n/n8n-nodes-langchain.googleGemini",
      "position": [
        288,
        -128
      ],
      "parameters": {
        "text": "=Analyze this product image and extract only the list of ingredients. Ignore other text like brand names, slogans, or nutritional info. Return the ingredients as clean text in order and What the product is.",
        "modelId": {
          "__rl": true,
          "mode": "list",
          "value": "models/gemini-2.5-flash",
          "cachedResultName": "models/gemini-2.5-flash"
        },
        "options": {},
        "resource": "image",
        "inputType": "binary",
        "operation": "analyze"
      },
      "credentials": {
        "googlePalmApi": {
          "id": "CLs7gtUQzHCSgvqQ",
          "name": "Google Gemini(PaLM) Api account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "d6a1725c-be05-4e59-aab2-462ae3d47ee2",
      "name": "Récupère le fichier photo depuis Telegram",
      "type": "n8n-nodes-base.telegram",
      "position": [
        80,
        -128
      ],
      "webhookId": "121a1894-5bff-43b7-9f14-9101a71ad6ae",
      "parameters": {
        "fileId": "={{ $json.message.photo[3].file_id }}",
        "resource": "file",
        "additionalFields": {}
      },
      "credentials": {
        "telegramApi": {
          "id": "PFSwgv89YFhycXc3",
          "name": "Telegram account"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "492eb15b-d490-47b7-9ecd-0f31bef855fd",
      "name": "Analyse les ingrédients avec la légende utilisateur (décision Utiliser/Ne pas utiliser)",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        688,
        -288
      ],
      "parameters": {
        "text": "=Product ingredients :- {{ $json.content.parts[0].text }}\n\nUser's Caption :- {{ $('Get a Message photo/text').item.json.message.caption }}",
        "options": {
          "systemMessage": "=You are a product safety and health advisor.  \nYou will receive two inputs:  \n1. A list of product ingredients.  \n2. A caption/description of the product.  \n\nYour task is to:  \n- Analyze the ingredients for safety, health impact, and potential concerns (like allergens, harmful chemicals, artificial additives, or beneficial elements).  \n- Consider the product’s purpose (from the caption).  \n- Decide if the user **should use this product or not**.  \n\nOutput Format:  \n{\n  \"recommendation\": \"Use\" or \"Do Not Use\",\n  \"reason\": \"Detailed explanation covering positives, negatives, and potential risks or benefits.\"\n}\n\nadd only necessary information not include unnecessary information on reason.\n"
        },
        "promptType": "define",
        "hasOutputParser": true
      },
      "typeVersion": 2.2
    },
    {
      "id": "08b6a395-6c56-4ca2-b0ec-1c47393f21b0",
      "name": "Envoie la recommandation Utiliser/Ne pas utiliser",
      "type": "n8n-nodes-base.telegram",
      "position": [
        1008,
        -288
      ],
      "webhookId": "30cc03fb-37a2-44eb-b085-16558436900c",
      "parameters": {
        "text": "=** {{ $json.output.recommendation }} **\n\n{{ $json.output.reason }}",
        "chatId": "={{ $('Get a Message photo/text').item.json.message.chat.id }}",
        "additionalFields": {
          "appendAttribution": false
        }
      },
      "credentials": {
        "telegramApi": {
          "id": "PFSwgv89YFhycXc3",
          "name": "Telegram account"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "89350602-2843-4643-97a4-6dab08a54dee",
      "name": "Analyse les ingrédients sans légende (analyse détaillée)",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        688,
        32
      ],
      "parameters": {
        "text": "=Product ingredients :- {{ $('Analyzes product images using Google Gemini').item.json.content.parts[0].text }}",
        "options": {
          "systemMessage": "=You are a product health and safety advisor.  \nYou will be given a list of ingredients from a product.  \nYour job is to analyze them and provide a structured, detailed output.\n\n\nRules:\n- Do not invent ingredients that are not present.\n- Base all reasoning strictly on the provided ingredient list.\n- Be clear, factual, and practical for everyday users.\n\ngive only 3 main points in each."
        },
        "promptType": "define",
        "hasOutputParser": true
      },
      "typeVersion": 2.2
    },
    {
      "id": "5c6f145c-36b6-4241-8086-890bf8c50fd6",
      "name": "Envoie l'analyse détaillée des ingrédients",
      "type": "n8n-nodes-base.telegram",
      "position": [
        1040,
        32
      ],
      "webhookId": "1f346d74-2f77-4382-8a4e-a830106ae145",
      "parameters": {
        "text": "=**Advantages**\n• {{ $json.output.advantages[0] }}\n• {{ $json.output.advantages[1] }}\n• {{ $json.output.advantages[2] }}\n\n**Disadvantages**\n• {{ $json.output.disadvantages[0] }}\n• {{ $json.output.disadvantages[1] }}\n• {{ $json.output.disadvantages[2] }}\n\n**Recommended For**\n• {{ $json.output.recommended_for[0] }}\n• {{ $json.output.recommended_for[1] }}\n• {{ $json.output.recommended_for[2] }}\n\n**Not-Recommended For**\n• {{ $json.output.not_recommended_for[0] }}\n• {{ $json.output.not_recommended_for[1] }}\n• {{ $json.output.not_recommended_for[2] }}",
        "chatId": "={{ $('Get a Message photo/text').item.json.message.chat.id }}",
        "additionalFields": {
          "appendAttribution": false
        }
      },
      "credentials": {
        "telegramApi": {
          "id": "PFSwgv89YFhycXc3",
          "name": "Telegram account"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "f63050eb-d0f2-4531-b7ce-ae47c5f235dc",
      "name": "Route en fonction de la présence d'une légende",
      "type": "n8n-nodes-base.switch",
      "position": [
        496,
        -128
      ],
      "parameters": {
        "rules": {
          "values": [
            {
              "conditions": {
                "options": {
                  "version": 2,
                  "leftValue": "",
                  "caseSensitive": true,
                  "typeValidation": "strict"
                },
                "combinator": "and",
                "conditions": [
                  {
                    "id": "825bbdf2-81ff-4f74-b416-145034bfd7a5",
                    "operator": {
                      "type": "string",
                      "operation": "exists",
                      "singleValue": true
                    },
                    "leftValue": "={{ $('Get a Message photo/text').item.json.message.caption }}",
                    "rightValue": ""
                  }
                ]
              }
            },
            {
              "conditions": {
                "options": {
                  "version": 2,
                  "leftValue": "",
                  "caseSensitive": true,
                  "typeValidation": "strict"
                },
                "combinator": "and",
                "conditions": [
                  {
                    "id": "3901b67c-046b-47d4-81ed-3d246c63b975",
                    "operator": {
                      "type": "string",
                      "operation": "notExists",
                      "singleValue": true
                    },
                    "leftValue": "={{ $('Get a Message photo/text').item.json.message.caption }}",
                    "rightValue": ""
                  }
                ]
              }
            }
          ]
        },
        "options": {}
      },
      "typeVersion": 3.2
    },
    {
      "id": "5eeb91bb-c816-45b4-ab16-39415cef6405",
      "name": "Gère les messages texte et les salutations",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        96,
        160
      ],
      "parameters": {
        "text": "={{ $json.message.text }}",
        "options": {
          "systemMessage": "=You are an ingredient analysis assistant.  \nYour main job is to analyze product ingredients and provide insights such as:  \n- Advantages  \n- Disadvantages  \n- Who should use it  \n- Who should avoid it  \n- Final Verdict (Use / Do Not Use)  \n\nRules:  \n\n--- If the user provides a list of ingredients, respond with a structured analysis using markdown format with bold headers:  \n   **Advantages**  \n   **Disadvantages**  \n   **Recommended For**  \n   **Not Recommended For**  \n   **Final Verdict**  \n\n--- If the user greets you or sends casual small-talk (e.g., \"hi\", \"hello\", \"how are you\"), reply in a friendly way. Example:  \n   \"Hey! I’m fine 😃 Please upload a photo of the product’s ingredients and I’ll tell you whether you should use it or not.\"  \n\n--- If the user asks about something unrelated to ingredients (e.g., sports, politics, weather), politely redirect them. Example:  \n   \"⚠️ I can only help with product ingredient analysis. Please share product ingredients or upload a photo of the label for review.\"  \n\n4. Always keep the tone clear, helpful, and user-friendly.  \n"
        },
        "promptType": "define"
      },
      "typeVersion": 2.2
    },
    {
      "id": "6b3650d2-31c1-4e0c-bf7f-151cbbc39ce6",
      "name": "Envoie des réponses conversationnelles",
      "type": "n8n-nodes-base.telegram",
      "position": [
        416,
        160
      ],
      "webhookId": "e03cccf2-8660-4cc0-8508-328a56b1a2a9",
      "parameters": {
        "text": "={{ $json.output }}",
        "chatId": "={{ $('Get a Message photo/text').item.json.message.chat.id }}",
        "additionalFields": {
          "appendAttribution": false
        }
      },
      "credentials": {
        "telegramApi": {
          "id": "PFSwgv89YFhycXc3",
          "name": "Telegram account"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "72e77331-2127-4c9e-abba-9c7403aa82f4",
      "name": "Vérifie si le message contient une photo",
      "type": "n8n-nodes-base.if",
      "position": [
        -96,
        16
      ],
      "parameters": {
        "options": {},
        "conditions": {
          "options": {
            "version": 2,
            "leftValue": "",
            "caseSensitive": true,
            "typeValidation": "strict"
          },
          "combinator": "and",
          "conditions": [
            {
              "id": "c7623137-fcd6-43be-b941-6c527bc2e63f",
              "operator": {
                "type": "string",
                "operation": "exists",
                "singleValue": true
              },
              "leftValue": "={{ $json.message.photo[3].file_id }}",
              "rightValue": ""
            }
          ]
        }
      },
      "typeVersion": 2.2
    },
    {
      "id": "fc2ccb12-fe74-4c0b-91b0-8f978b7e369b",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1136,
        -672
      ],
      "parameters": {
        "width": 2416,
        "height": 1552,
        "content": "# 📌 Product Ingredient Analyzer Bot\n## 🔄What this workflow does\n- Telegram bot that analyzes product ingredients from photos using Google Gemini AI. \nProvides health & safety recommendations based on user context.\n\n## 🧩 How it works\n1. 📥 Get a Message photo/text\n- Listens for Telegram messages (photos or text)\n\n\n\n2. 🔍 Checks if message contains photo\n- Has photo → Extract ingredients\n- No photo → Handle as text chat\n\n\n\n📸 Photo Branch\n3. 📂 Retrieves photo → 🤖 Analyzes with Gemini\n- Extracts ingredient list from product label\n- Ignores brand names and nutritional info\n\n\n\n4. 🔀 Routes based on caption\n- With caption → Simple Use/Don't Use verdict\n- No caption → Detailed 4-category analysis\n\n\n\n5. 📤 Sends response\n- With caption: Bold recommendation + reason\n- Without caption: Advantages, Disadvantages, Recommended For, Not Recommended For (3 points each)\n\n\n\n💬 Text Branch\n6. 🤝 Handles text messages\n- Greetings → Friendly prompt to upload photo\n- Ingredient list → Provides analysis\n- Off-topic → Polite redirect\n\n\n## ✅ Sample Messages\n### Photo + caption \"sensitive skin\":\n- Do Not Use\n-- Contains SLS and fragrances that irritate sensitive skin.\n\n### Photo only:\n- Advantages\n• Hyaluronic acid for hydration\n• Niacinamide reduces inflammation\n• Vitamin E protection\n- Disadvantages\n• Contains parabens\n• Synthetic fragrance\n• May clog pores\n\n### Text \"Hi\":\n- Hey! 😃 Upload a product photo and I'll analyze the ingredients.\n\n\n## 💡 Best for\n-🧴 Skincare \n• 🧼 Hair care \n• 🍫 Food labels \n• 🧽 Cleaning products\n\n## ⚠️ Requirements\n- Telegram bot token\n- Google Gemini API credentials"
      },
      "typeVersion": 1
    }
  ],
  "active": false,
  "pinData": {},
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "a223be73-0476-435b-81c8-cb791ceaad47",
  "connections": {
    "a8169fcb-ebf7-4aab-ab3c-e3fb4f4ea181": {
      "main": [
        [
          {
            "node": "72e77331-2127-4c9e-abba-9c7403aa82f4",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "90b0a91c-bba7-41f3-8d90-af4947a7da10": {
      "ai_languageModel": [
        [
          {
            "node": "492eb15b-d490-47b7-9ecd-0f31bef855fd",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "716161e7-f0bb-4e4c-b0e2-ec98d4e199ff": {
      "ai_outputParser": [
        [
          {
            "node": "492eb15b-d490-47b7-9ecd-0f31bef855fd",
            "type": "ai_outputParser",
            "index": 0
          }
        ]
      ]
    },
    "107f1ce4-0198-4a53-8f94-8fb9ffe53370": {
      "ai_languageModel": [
        [
          {
            "node": "89350602-2843-4643-97a4-6dab08a54dee",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "5817f756-9d0f-445e-b860-29c530a93f86": {
      "ai_languageModel": [
        [
          {
            "node": "5eeb91bb-c816-45b4-ab16-39415cef6405",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "d3996282-5fb7-4e0e-8d1d-195b5703ac59": {
      "ai_outputParser": [
        [
          {
            "node": "89350602-2843-4643-97a4-6dab08a54dee",
            "type": "ai_outputParser",
            "index": 0
          }
        ]
      ]
    },
    "72e77331-2127-4c9e-abba-9c7403aa82f4": {
      "main": [
        [
          {
            "node": "d6a1725c-be05-4e59-aab2-462ae3d47ee2",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "5eeb91bb-c816-45b4-ab16-39415cef6405",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "f63050eb-d0f2-4531-b7ce-ae47c5f235dc": {
      "main": [
        [
          {
            "node": "492eb15b-d490-47b7-9ecd-0f31bef855fd",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "89350602-2843-4643-97a4-6dab08a54dee",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "d6a1725c-be05-4e59-aab2-462ae3d47ee2": {
      "main": [
        [
          {
            "node": "d3486786-42e0-4bbb-8449-ec011df85da6",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "5eeb91bb-c816-45b4-ab16-39415cef6405": {
      "main": [
        [
          {
            "node": "6b3650d2-31c1-4e0c-bf7f-151cbbc39ce6",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "d3486786-42e0-4bbb-8449-ec011df85da6": {
      "main": [
        [
          {
            "node": "f63050eb-d0f2-4531-b7ce-ae47c5f235dc",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "89350602-2843-4643-97a4-6dab08a54dee": {
      "main": [
        [
          {
            "node": "5c6f145c-36b6-4241-8086-890bf8c50fd6",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "492eb15b-d490-47b7-9ecd-0f31bef855fd": {
      "main": [
        [
          {
            "node": "08b6a395-6c56-4ca2-b0ec-1c47393f21b0",
            "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 ?

Avancé - Création de contenu, IA Multimodale

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
Avancé
Nombre de nœuds17
Catégorie2
Types de nœuds9
Description de la difficulté

Adapté aux utilisateurs avancés, avec des workflows complexes contenant 16+ nœuds

Auteur
Parth Pansuriya

Parth Pansuriya

@parthpansuriya

I build smart and scalable automation workflows using n8n to simplify tasks, connect apps, and boost productivity. From WhatsApp bots to AI-powered systems, I create seamless automations tailored for business and creators.

Liens externes
Voir sur n8n.io

Partager ce workflow

Catégories

Catégories: 34