Workflow n8n
Automatisation n8n : recherche d'images inversée avec OpenAI
- Ce workflow n8n a pour objectif d'automatiser la recherche d'images inversée en utilisant des outils d'intelligence artificielle comme OpenAI et des API externes. Dans un contexte où les entreprises cherchent à enrichir leurs données visuelles et à améliorer leur stratégie de contenu, ce workflow s'avère particulièrement utile pour les équipes marketing et les créateurs de contenu. Il permet de récupérer des informations pertinentes sur des images en ligne, d'analyser leur contenu et d'enrichir les données associées dans des bases comme Airtable.
- Le processus commence par un déclencheur manuel qui active le workflow. Ensuite, le modèle de chat OpenAI est utilisé pour générer des réponses basées sur les images fournies. Par la suite, le workflow interroge Airtable pour obtenir les lignes applicables, suivies par des appels API vers des services comme SERP Google pour effectuer la recherche d'images inversée. Les résultats sont ensuite traités et enrichis, permettant ainsi d'obtenir des informations structurées sur les images.
- Les bénéfices de cette automatisation n8n sont multiples : elle réduit le temps nécessaire à la recherche d'images, améliore la précision des données collectées et permet une meilleure gestion des ressources visuelles. En intégrant des outils avancés d'IA, les utilisateurs peuvent ainsi optimiser leur stratégie de contenu tout en minimisant les efforts manuels.
Tags clés :automatisationOpenAIAirtableimages inverséesn8n
Catégorie: Manual · Tags: automatisation, OpenAI, Airtable, images inversées, n8n❤ 0
Workflow n8n OpenAI, Airtable, images inversées : vue d'ensemble
Schéma des nœuds et connexions de ce workflow n8n, généré à partir du JSON n8n.
Workflow n8n OpenAI, Airtable, images inversées : détail des nœuds
Inscris-toi pour voir l'intégralité du workflow
Inscription gratuite
S'inscrire gratuitementBesoin d'aide ?{
"meta": {
"instanceId": "26ba763460b97c249b82942b23b6384876dfeb9327513332e743c5f6219c2b8e"
},
"nodes": [
{
"id": "192d3e4f-6bb0-4b87-a1fa-e32c9efb49cc",
"name": "When clicking \"Test workflow\"",
"type": "n8n-nodes-base.manualTrigger",
"position": [
336,
34
],
"parameters": {},
"typeVersion": 1
},
{
"id": "32a7a772-76a6-4614-a6ab-d2b152a5811f",
"name": "OpenAI Chat Model1",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
1220,
180
],
"parameters": {
"model": "gpt-4o",
"options": {
"temperature": 0
}
},
"credentials": {
"openAiApi": {
"id": "8gccIjcuf3gvaoEr",
"name": "OpenAi account"
}
},
"typeVersion": 1
},
{
"id": "8c444314-ed7d-4ca0-b0fa-b6d1e964c698",
"name": "Get Applicable Rows",
"type": "n8n-nodes-base.airtable",
"position": [
516,
34
],
"parameters": {
"base": {
"__rl": true,
"mode": "list",
"value": "appbgxPBurOmQK3E7",
"cachedResultUrl": "https://airtable.com/appbgxPBurOmQK3E7",
"cachedResultName": "Building Inventory Survey Example"
},
"table": {
"__rl": true,
"mode": "id",
"value": "tblEHkoTvKpa4Aa0Q"
},
"options": {},
"operation": "search",
"returnAll": false,
"filterByFormula": "AND(Image!=\"\", AI_status=FALSE())"
},
"credentials": {
"airtableTokenApi": {
"id": "Und0frCQ6SNVX3VV",
"name": "Airtable Personal Access Token account"
}
},
"typeVersion": 2
},
{
"id": "f90578fa-b886-4653-8ff7-0c91884dc517",
"name": "Execute Workflow Trigger",
"type": "n8n-nodes-base.executeWorkflowTrigger",
"position": [
1257,
733
],
"parameters": {},
"typeVersion": 1
},
{
"id": "8f5959eb-45bd-4185-a959-10268827e41d",
"name": "Edit Fields",
"type": "n8n-nodes-base.set",
"position": [
1417,
733
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "7263764b-8409-4cea-8db3-3278dd7ef9d8",
"name": "=route",
"type": "string",
"value": "={{ $json.route }}"
},
{
"id": "55c3b207-2e98-4137-8413-f72cbff17986",
"name": "query",
"type": "string",
"value": "={{ $json.query }}"
},
{
"id": "6eb873de-3c3a-4135-9dc0-1d441c63647c",
"name": "",
"type": "string",
"value": ""
}
]
}
},
"typeVersion": 3.3
},
{
"id": "2c7f7274-12e9-4dd3-8ee4-679b408d5430",
"name": "Fallback Response",
"type": "n8n-nodes-base.set",
"position": [
1580,
875
],
"parameters": {
"mode": "raw",
"options": {},
"jsonOutput": "{\n \"response\": {\n \"ok\": false,\n \"error\": \"The requested tool was not found or the service may be unavailable. Do not retry.\"\n }\n}\n"
},
"typeVersion": 3.3
},
{
"id": "09f36f4d-eb88-4d93-a8b3-e9ba66b46b54",
"name": "SERP Google Reverse Image API",
"type": "n8n-nodes-base.httpRequest",
"position": [
1860,
549
],
"parameters": {
"url": "https://serpapi.com/search.json",
"options": {},
"sendQuery": true,
"authentication": "predefinedCredentialType",
"queryParameters": {
"parameters": [
{
"name": "engine",
"value": "google_reverse_image"
},
{
"name": "image_url",
"value": "={{ $json.query }}"
}
]
},
"nodeCredentialType": "serpApi"
},
"credentials": {
"serpApi": {
"id": "aJCKjxx6U3K7ydDe",
"name": "SerpAPI account"
}
},
"typeVersion": 4.2
},
{
"id": "8e3a0f38-8663-4f5c-837f-4b9aa21f14fb",
"name": "Reverse Image Search Response",
"type": "n8n-nodes-base.set",
"position": [
2037,
547
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "de99a504-713f-4c78-8679-08139b2def31",
"name": "response",
"type": "string",
"value": "={{ JSON.stringify($json.image_results.map(x => ({ position: x.position, title: x.title, link: x.link, description: x.snippet }))) }}"
}
]
}
},
"typeVersion": 3.3
},
{
"id": "0cd2269a-5b1f-4f10-b180-7f9cff9b1102",
"name": "Reverse Image Search Tool",
"type": "@n8n/n8n-nodes-langchain.toolWorkflow",
"position": [
1300,
340
],
"parameters": {
"name": "reverse_image_search",
"fields": {
"values": [
{
"name": "route",
"stringValue": "serp.google_reverse_image"
}
]
},
"workflowId": "={{ $workflow.id }}",
"description": "Call this tool to perform a reverse image search. Reverse image searches return urls where similar looking products exists. Fetch the returned urls to gather more information. This tool requires the following object request body.\n```\n{\n \"type\": \"object\",\n \"properties\": {\n \"image_url\": { \"type\": \"string\" },\n }\n}\n```\nimage_url should be an absolute URL to the image."
},
"typeVersion": 1.1
},
{
"id": "9825651e-b382-4e0a-97ef-37764cb5be9e",
"name": "Firecrawl Scrape API",
"type": "n8n-nodes-base.httpRequest",
"position": [
1860,
889
],
"parameters": {
"url": "https://api.firecrawl.dev/v0/scrape",
"method": "POST",
"options": {},
"sendBody": true,
"sendHeaders": true,
"authentication": "genericCredentialType",
"bodyParameters": {
"parameters": [
{
"name": "url",
"value": "={{ $json.query }}"
}
]
},
"genericAuthType": "httpHeaderAuth",
"headerParameters": {
"parameters": [
{
"name": "Content-Type",
"value": "application/json"
}
]
}
},
"credentials": {
"httpHeaderAuth": {
"id": "OUOnyTkL9vHZNorB",
"name": "Firecrawl API"
}
},
"typeVersion": 4.2
},
{
"id": "7f61d60b-b052-4b7c-abfd-9eb8e05a45a2",
"name": "Scrape Success?",
"type": "n8n-nodes-base.if",
"position": [
2020,
889
],
"parameters": {
"options": {},
"conditions": {
"options": {
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "a15a164f-d0c5-478f-8b27-f3d51746c214",
"operator": {
"type": "boolean",
"operation": "true",
"singleValue": true
},
"leftValue": "={{ $json.success }}",
"rightValue": ""
}
]
}
},
"typeVersion": 2
},
{
"id": "29c65ef4-6350-490a-b8e3-a5c869e656b2",
"name": "Firecrawl Scrape Success Response",
"type": "n8n-nodes-base.set",
"position": [
2180,
889
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "7db5c81f-de90-40e1-8086-3f13d40451c7",
"name": "response",
"type": "string",
"value": "={{ $json.data.markdown.substring(0, 3000) }}"
}
]
}
},
"typeVersion": 3.3
},
{
"id": "229b4008-d8a8-4609-854a-fc244a4ed630",
"name": "Firecrawl scrape Error Response",
"type": "n8n-nodes-base.set",
"position": [
2180,
1049
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "e691d86a-d366-44a2-baa6-3dba42527f6e",
"name": "response",
"type": "string",
"value": "{ error: \"Unable to scrape website due to unknown error. Do not retry.\" }"
}
]
}
},
"typeVersion": 3.3
},
{
"id": "f080069b-e849-45e0-88cf-03707d22c704",
"name": "Firecrawl Web Scaper Tool",
"type": "@n8n/n8n-nodes-langchain.toolWorkflow",
"position": [
1440,
340
],
"parameters": {
"name": "webpage_url_scraper_tool",
"fields": {
"values": [
{
"name": "route",
"stringValue": "firecrawl.scrape"
}
]
},
"workflowId": "={{ $workflow.id }}",
"description": "Call this tool to retrieve page contents of a url.\n```\n{\n \"type\": \"object\",\n \"properties\": {\n \"url\": { \"type\": \"string\" },\n }\n}\n```\nurl should be an absolute URL."
},
"typeVersion": 1.1
},
{
"id": "4eff88bb-bd5e-4d6a-b5e1-8521632c461f",
"name": "Structured Output Parser",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
1500,
180
],
"parameters": {
"jsonSchema": "{\n \"type\": \"object\",\n \"properties\": {\n \"title\": { \"type\": \"string\" },\n \"description\": { \"type\": \"string\" },\n \"model\": { \"type\": \"string\" },\n \"material\": { \"type\": \"string\" },\n \"color\": { \"type\": \"string\" },\n \"condition\": { \"type\": \"string\" }\n }\n}"
},
"typeVersion": 1.1
},
{
"id": "328d106b-a473-4f54-82fd-55c30d813da9",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
280,
-260
],
"parameters": {
"color": 7,
"width": 402.5984702109446,
"height": 495.4071184783251,
"content": "## 1. Use Airtable to Capture Survey Photos\n[Read more about AirTable](https://docs.n8n.io/integrations/builtin/app-nodes/n8n-nodes-base.airtable)\n\nTo enable this workflow, we need a database where we can retreive the title and photo to analyse and write the generate values back to. Airtable is perfect for this since it has a robust API we can work with.\n\nFor this demo, we'll manually trigger but this can be changed for forms or other triggers."
},
"typeVersion": 1
},
{
"id": "e358775d-ff83-411d-9364-b43c87d98134",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
716.3106363781314,
-160
],
"parameters": {
"color": 7,
"width": 359.40869874940336,
"height": 428.4787925736586,
"content": "## 2. Use AI Vision Model to Analyse the Photo.\n[Read more about OpenAI Vision](https://docs.n8n.io/integrations/builtin/app-nodes/n8n-nodes-langchain.openai)\n\nWe'll use OpenAi vision model to create a detailed description of the product in the photo. We split this step from the agent because it uses an image model rather than the usual text-based one."
},
"typeVersion": 1
},
{
"id": "51b4a70c-9583-4e8a-8e8d-896a80ad53c3",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
1111.3914848823072,
-293.9250474768817
],
"parameters": {
"color": 7,
"width": 593.0683948010671,
"height": 803.956942672397,
"content": "## 3. Build an AI Agent who Searches the Internet\n[Read more about OpenAI Agents](https://docs.n8n.io/integrations/builtin/app-nodes/n8n-nodes-langchain.openai)\n\nThis AI Agent has the ability to perform reverse image searches using our captured photos as well visit external webpages in order to obtain accurate product names and attributes. The Agent along with the tools might mimic what the average human user would carry out the same task.\n\n* For reverse image search, we're using SERP API service however we won't use the built-in SERP node as we need to specify custom parameters. \n* For scraping, we'll use [Firecrawl](https://www.firecrawl.dev/) as this service also helps to parse and return the page as markdown which is more efficient."
},
"typeVersion": 1
},
{
"id": "adfb519b-a5c7-432c-be32-5acfcc388b49",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
1740,
-149.28190375244515
],
"parameters": {
"color": 7,
"width": 373.3601237414979,
"height": 397.7168664109706,
"content": "## 4. Overwrite our Rows with Enriched Results\n\nAnd Viola! Our AI agent has potentially saved hours of manual data entry work for our surveyor. This technique can be used for many other usecases."
},
"typeVersion": 1
},
{
"id": "6444e217-b944-450e-892a-5822d4d390ce",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
1200,
549
],
"parameters": {
"color": 7,
"width": 554.6092633638649,
"height": 490.7010880746526,
"content": "## 5. Using the Custom Workflow Tool\n[Read more about Workflow Tools](https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolworkflow)\n\nAI Agents rely on Tools to make decisions and become exponentially more powerful the more tools they have. A common pattern to manage multiple tools is to create a routing system for tools using the API pattern."
},
"typeVersion": 1
},
{
"id": "bf2459cf-a931-4232-9504-b36b15721194",
"name": "Enrich Product Rows",
"type": "n8n-nodes-base.airtable",
"position": [
1880,
60
],
"parameters": {
"base": {
"__rl": true,
"mode": "list",
"value": "appbgxPBurOmQK3E7",
"cachedResultUrl": "https://airtable.com/appbgxPBurOmQK3E7",
"cachedResultName": "Building Inventory Survey Example"
},
"table": {
"__rl": true,
"mode": "id",
"value": "tblEHkoTvKpa4Aa0Q"
},
"columns": {
"value": {
"id": "={{ $('Get Applicable Rows').item.json.id }}",
"Color": "={{ $json.output.output.color }}",
"Model": "={{ $json.output.output.model }}",
"Title": "={{ $json.output.output.title }}",
"Material": "={{ $json.output.output.material }}",
"AI_status": true,
"Condition": "={{ $json.output.output.condition }}",
"Description": "={{ $json.output.output.description }}"
},
"schema": [
{
"id": "id",
"type": "string",
"display": true,
"removed": false,
"readOnly": true,
"required": false,
"displayName": "id",
"defaultMatch": true
},
{
"id": "Title",
"type": "string",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Title",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Image",
"type": "array",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Image",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Description",
"type": "string",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Description",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Model",
"type": "string",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Model",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Material",
"type": "string",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Material",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Color",
"type": "string",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Color",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Condition",
"type": "string",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "Condition",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "AI_status",
"type": "boolean",
"display": true,
"removed": false,
"readOnly": false,
"required": false,
"displayName": "AI_status",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"id"
]
},
"options": {},
"operation": "update"
},
"credentials": {
"airtableTokenApi": {
"id": "Und0frCQ6SNVX3VV",
"name": "Airtable Personal Access Token account"
}
},
"typeVersion": 2
},
{
"id": "19d736bf-c29d-46a2-93bc-b536ff28c4b5",
"name": "Sticky Note6",
"type": "n8n-nodes-base.stickyNote",
"position": [
-100,
-260
],
"parameters": {
"width": 359.6648027457353,
"height": 381.0536322713287,
"content": "## Try It Out!\n### This workflow does the following:\n* Scans an Airtable spreadsheet for rows with product photo images.\n* Uses an AI vision model to attempt to identify the product.\n* Uses an AI Agent to research the product on the internet to enrich the product data.\n* Overwrites our Airtable spreadsheet with the enriched data.\n\n### Need Help?\nJoin the [Discord](https://discord.com/invite/XPKeKXeB7d) or ask in the [Forum](https://community.n8n.io/)!\n\nHappy Hacking!"
},
"typeVersion": 1
},
{
"id": "25f15c48-16bf-4f92-942d-c224ed88d208",
"name": "Analyse Image",
"type": "@n8n/n8n-nodes-langchain.openAi",
"position": [
840,
80
],
"parameters": {
"text": "=Focus on the {{ $json.Title }} in the image - we'll refer to this as the \"object\". Identify the following attributes of the object. If you cannot determine confidently, then leave blank and move to next attribute.\n* Decription of the object.\n* The model/make of the object.\n* The material(s) used in the construction of the object.\n* The color(s) of the object\n* The condition of the object. Use one of poor, good, excellent.\n",
"options": {},
"resource": "image",
"imageUrls": "={{ $json.Image[0].thumbnails.large.url }}",
"operation": "analyze"
},
"credentials": {
"openAiApi": {
"id": "8gccIjcuf3gvaoEr",
"name": "OpenAi account"
}
},
"typeVersion": 1.3
},
{
"id": "e6c99f71-ccc9-426e-b916-cc38864e3224",
"name": "Object Identifier Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
1260,
20
],
"parameters": {
"text": "=system: Your role is to help an building surveyor perform a object classification and data collection task whereby the surveyor will take photos of various objects and your job is to try and identify accurately certain product attributes of the objects as detailed below.\n\nThe surveyor has given you the following:\n1) photo url ```{{ $('Get Applicable Rows').item.json.Image[0].thumbnails.large.url }}```.\n2) photo description ```{{ $json.content }}```.\n\nFor each product attribute the surveyor is unable to determine, you may:\n1) use the reverse image search tool to search the product on the internet via the provided image url.\n2) use the web scraper tool to read webpages on the internet which may be relevant to the product.\n3) If after using these tools, you are still unable to determine the required product attributes then leave the data blank.\n\nUse all the information provided and gathered, to extract the following product attributes: title, description, model, material, color and condition.",
"agent": "openAiFunctionsAgent",
"options": {},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 1.5
},
{
"id": "661b14bd-6511-4f20-981c-2e68a7c34ec5",
"name": "Actions Router",
"type": "n8n-nodes-base.switch",
"position": [
1577,
733
],
"parameters": {
"rules": {
"values": [
{
"outputKey": "serp.google_reverse_image",
"conditions": {
"options": {
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"operator": {
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.route }}",
"rightValue": "serp.google_reverse_image"
}
]
},
"renameOutput": true
},
{
"outputKey": "firecrawl.scrape",
"conditions": {
"options": {
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "0a1f54ae-39f1-468d-ba6e-1376d13e4ee8",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.route }}",
"rightValue": "firecrawl.scrape"
}
]
},
"renameOutput": true
}
]
},
"options": {
"fallbackOutput": "extra"
}
},
"typeVersion": 3
},
{
"id": "c5078221-9239-4ec0-b25e-7cd880b58216",
"name": "Sticky Note5",
"type": "n8n-nodes-base.stickyNote",
"position": [
480,
20
],
"parameters": {
"width": 181.2788838920522,
"height": 297.0159375852115,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n🚨**Required**\n* Set Airtable Base and Table IDs here."
},
"typeVersion": 1
},
{
"id": "c58c0db4-9b99-4a77-90ae-66fa3981b684",
"name": "Sticky Note7",
"type": "n8n-nodes-base.stickyNote",
"position": [
1840,
40
],
"parameters": {
"width": 181.2788838920522,
"height": 297.0159375852115,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n🚨**Required**\n* Set Airtable Base and Table IDs here."
},
"typeVersion": 1
},
{
"id": "e3a666d7-d7a5-43f5-8f04-7972332f8916",
"name": "Sticky Note8",
"type": "n8n-nodes-base.stickyNote",
"position": [
1780,
440
],
"parameters": {
"color": 7,
"width": 460.3301604548244,
"height": 298.81538450684064,
"content": "## 5.1 Google Reverse Image Tool\nThis tool uses Google's reverse image API to return websites where similar images are found."
},
"typeVersion": 1
},
{
"id": "d7407cdb-16bb-4bd9-a28e-7a72a5289354",
"name": "Sticky Note9",
"type": "n8n-nodes-base.stickyNote",
"position": [
1780,
769.9385328672522
],
"parameters": {
"color": 7,
"width": 575.3216480295998,
"height": 463.34699288922565,
"content": "## 5.2 Webscraper Tool\nThis tool uses Firecrawl.dev API to crawl webpages and returns those pages in markdown format."
},
"typeVersion": 1
}
],
"pinData": {},
"connections": {
"Edit Fields": {
"main": [
[
{
"node": "Actions Router",
"type": "main",
"index": 0
}
]
]
},
"Analyse Image": {
"main": [
[
{
"node": "Object Identifier Agent",
"type": "main",
"index": 0
}
]
]
},
"Actions Router": {
"main": [
[
{
"node": "SERP Google Reverse Image API",
"type": "main",
"index": 0
}
],
[
{
"node": "Firecrawl Scrape API",
"type": "main",
"index": 0
}
],
[
{
"node": "Fallback Response",
"type": "main",
"index": 0
}
]
]
},
"Scrape Success?": {
"main": [
[
{
"node": "Firecrawl Scrape Success Response",
"type": "main",
"index": 0
}
],
[
{
"node": "Firecrawl scrape Error Response",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model1": {
"ai_languageModel": [
[
{
"node": "Object Identifier Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Get Applicable Rows": {
"main": [
[
{
"node": "Analyse Image",
"type": "main",
"index": 0
}
]
]
},
"Firecrawl Scrape API": {
"main": [
[
{
"node": "Scrape Success?",
"type": "main",
"index": 0
}
]
]
},
"Object Identifier Agent": {
"main": [
[
{
"node": "Enrich Product Rows",
"type": "main",
"index": 0
}
]
]
},
"Execute Workflow Trigger": {
"main": [
[
{
"node": "Edit Fields",
"type": "main",
"index": 0
}
]
]
},
"Structured Output Parser": {
"ai_outputParser": [
[
{
"node": "Object Identifier Agent",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"Firecrawl Web Scaper Tool": {
"ai_tool": [
[
{
"node": "Object Identifier Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Reverse Image Search Tool": {
"ai_tool": [
[
{
"node": "Object Identifier Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"SERP Google Reverse Image API": {
"main": [
[
{
"node": "Reverse Image Search Response",
"type": "main",
"index": 0
}
]
]
},
"When clicking \"Test workflow\"": {
"main": [
[
{
"node": "Get Applicable Rows",
"type": "main",
"index": 0
}
]
]
}
}
}Workflow n8n OpenAI, Airtable, images inversées : pour qui est ce workflow ?
Ce workflow s'adresse principalement aux équipes marketing, aux créateurs de contenu et aux entreprises souhaitant enrichir leur base de données visuelles. Un niveau technique intermédiaire est recommandé pour la mise en place et la personnalisation de ce workflow n8n.
Workflow n8n OpenAI, Airtable, images inversées : problème résolu
Ce workflow résout le problème de la recherche manuelle d'images et de l'enrichissement de données associées. Il élimine les frustrations liées à la collecte d'informations sur des images en ligne, réduit le temps passé à effectuer des recherches manuelles et minimise les risques d'erreurs humaines. Grâce à cette automatisation, les utilisateurs obtiennent des résultats rapides et précis, leur permettant de se concentrer sur des tâches à plus forte valeur ajoutée.
Workflow n8n OpenAI, Airtable, images inversées : étapes du workflow
Étape 1 : Le workflow est déclenché manuellement.
- Étape 1 : Le modèle de chat OpenAI génère des réponses basées sur les images fournies.
- Étape 2 : Les lignes applicables sont récupérées d'Airtable.
- Étape 3 : Une requête est envoyée à l'API SERP Google pour effectuer la recherche d'images inversée.
- Étape 4 : Les résultats de la recherche sont analysés et enrichis.
- Étape 5 : Les données structurées sont préparées pour une utilisation ultérieure.
Workflow n8n OpenAI, Airtable, images inversées : guide de personnalisation
Pour personnaliser ce workflow, commencez par ajuster les paramètres du déclencheur manuel selon vos besoins. Modifiez les clés API pour les services externes comme SERP Google et Airtable. Vous pouvez également adapter les modèles de réponse d'OpenAI en fonction des spécificités de votre projet. Enfin, n'hésitez pas à ajouter ou retirer des étapes selon les outils que vous souhaitez intégrer dans votre flux de travail.