Moteur de correspondance automatique CV-emploi avec Bright Data et OpenAI 4o mini
Avancé
Ceci est unHR, AIworkflow d'automatisation du domainecontenant 22 nœuds.Utilise principalement des nœuds comme Set, Function, SplitOut, McpClient, HttpRequest, combinant la technologie d'intelligence artificielle pour une automatisation intelligente. Bright Data MCP与OpenAI 4o minideautomatisation简历职位匹配引擎
Prérequis
- •Peut nécessiter les informations d'identification d'authentification de l'API cible
- •Clé API OpenAI
Nœuds utilisés (22)
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": "gIdIv8qN7zruqLbG",
"meta": {
"instanceId": "885b4fb4a6a9c2cb5621429a7b972df0d05bb724c20ac7dac7171b62f1c7ef40",
"templateCredsSetupCompleted": true
},
"name": "Automated Resume Job Matching Engine with Bright Data & OpenAI 4o mini",
"tags": [
{
"id": "Kujft2FOjmOVQAmJ",
"name": "Engineering",
"createdAt": "2025-04-09T01:31:00.558Z",
"updatedAt": "2025-04-09T01:31:00.558Z"
},
{
"id": "ZOwtAMLepQaGW76t",
"name": "Building Blocks",
"createdAt": "2025-04-13T15:23:40.462Z",
"updatedAt": "2025-04-13T15:23:40.462Z"
},
{
"id": "ddPkw7Hg5dZhQu2w",
"name": "AI",
"createdAt": "2025-04-13T05:38:08.053Z",
"updatedAt": "2025-04-13T05:38:08.053Z"
},
{
"id": "rKOa98eAi3IETrLu",
"name": "HR",
"createdAt": "2025-04-13T04:59:30.580Z",
"updatedAt": "2025-04-13T04:59:30.580Z"
}
],
"nodes": [
{
"id": "a75e1f8d-9dd4-4c87-b1ab-05c502b8cae7",
"name": "Boucler sur les éléments",
"type": "n8n-nodes-base.splitInBatches",
"position": [
736,
115
],
"parameters": {
"options": {}
},
"typeVersion": 3
},
{
"id": "92f0272d-dc5d-4424-9d96-cc2521e8a4ae",
"name": "Lors du clic sur 'Tester le workflow'",
"type": "n8n-nodes-base.manualTrigger",
"position": [
-740,
115
],
"parameters": {},
"typeVersion": 1
},
{
"id": "3820c9d3-be68-4a60-a810-943a9795bdbd",
"name": "Lister tous les outils pour Bright Data",
"type": "n8n-nodes-mcp.mcpClient",
"position": [
-520,
115
],
"parameters": {},
"credentials": {
"mcpClientApi": {
"id": "JtatFSfA2kkwctYa",
"name": "MCP Client (STDIO) account"
}
},
"typeVersion": 1
},
{
"id": "83219c20-7341-4e42-8cae-cc2e1e8e9b8e",
"name": "Définir les champs de saisie",
"type": "n8n-nodes-base.set",
"position": [
-300,
115
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "214e61a0-3587-453f-baf5-eac013990857",
"name": "resume",
"type": "string",
"value": "I am Pechi, Senior Python Developer with 9+ years of experience."
},
{
"id": "98c64f52-1564-4889-811d-39cac3951cc3",
"name": "keywords",
"type": "string",
"value": "Python"
},
{
"id": "34202143-4b07-4301-b5e9-767430952214",
"name": "location",
"type": "string",
"value": "India"
},
{
"id": "47d01515-302b-4a91-b9db-3af0033a56e1",
"name": "job_search_base_url",
"type": "string",
"value": "https://www.linkedin.com/jobs/search/"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "40a70c2b-5dcc-44f7-8fde-9c28748181cd",
"name": "Client MCP Bright Data pour l'extraction d'emplois",
"type": "n8n-nodes-mcp.mcpClient",
"notes": "Scrape a single webpage URL with advanced options for content extraction and get back the results in MarkDown language.",
"position": [
-80,
115
],
"parameters": {
"toolName": "scrape_as_html",
"operation": "executeTool",
"toolParameters": "={\n \"url\": \"{{ $json.job_search_base_url }}?keywords={{ $json.keywords }}&location={{ $json.location }}\"\n} "
},
"credentials": {
"mcpClientApi": {
"id": "JtatFSfA2kkwctYa",
"name": "MCP Client (STDIO) account"
}
},
"notesInFlow": true,
"typeVersion": 1
},
{
"id": "ff3193e5-cd22-40f4-8180-b76ad32055b3",
"name": "Diviser",
"type": "n8n-nodes-base.splitOut",
"position": [
516,
115
],
"parameters": {
"options": {},
"fieldToSplitOut": "output"
},
"typeVersion": 1
},
{
"id": "cd1fcbd8-acf3-4a91-8158-f664aaa839e7",
"name": "Client MCP Bright Data pour l'extraction d'emplois dans une boucle",
"type": "n8n-nodes-mcp.mcpClient",
"notes": "Scrape a single webpage URL with advanced options for content extraction and get back the results in MarkDown language.",
"position": [
956,
-10
],
"parameters": {
"toolName": "scrape_as_html",
"operation": "executeTool",
"toolParameters": "={\n \"url\": \"{{ $json.output }}\"\n} "
},
"credentials": {
"mcpClientApi": {
"id": "JtatFSfA2kkwctYa",
"name": "MCP Client (STDIO) account"
}
},
"notesInFlow": true,
"typeVersion": 1
},
{
"id": "d9f78a12-9eaa-4d9b-9e5c-5150d6e40e95",
"name": "Extracteur d'informations de description de poste",
"type": "@n8n/n8n-nodes-langchain.informationExtractor",
"position": [
1176,
-10
],
"parameters": {
"text": "=Extract the job description in a textual format\n\nHere's the content: {{ $json.result.content[0].text }}",
"options": {},
"attributes": {
"attributes": [
{
"name": "job_description",
"description": "Job Description"
}
]
}
},
"retryOnFail": true,
"typeVersion": 1
},
{
"id": "4636d7e9-8d13-4f57-95f9-936f6d8bbf1d",
"name": "Appariement d'emploi par IA",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
1552,
-10
],
"parameters": {
"text": "=Hi, you are a helpful job matcher, you analyze the given resume and job description and providing a job matching skills and score in a JSON format.\n\nHere's the Resume:\n{{ $('Set the Input fields').item.json.resume }}\n\nHere's the Job Desc:\n\n{{ $json.output.job_description }}",
"promptType": "define",
"hasOutputParser": true
},
"retryOnFail": true,
"typeVersion": 1.6
},
{
"id": "51b5d9dd-b0c8-4aaf-b789-f96e94519b94",
"name": "Analyseur de sortie structurée",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
1720,
200
],
"parameters": {
"jsonSchemaExample": "{\n \"job_match_analysis\": {\n \"resume_summary\": \"Senior Python Developer with 9+ years of experience.\",\n \"job_description_summary\": \"Seeking a developer with expertise in Sagemaker, Python, and LLM. The role involves client interaction, requirements understanding, design review, architecture validation, and team leadership.\",\n \"skill_match\": [\n {\n \"skill\": \"python\",\n \"resume\": \"Strong match - explicitly mentioned as core skill.\",\n \"job_description\": \"Strong match - listed as a primary skill.\",\n \"score\": 100\n },\n {\n \"skill\": \"sagemaker\",\n \"resume\": \"No match - not mentioned in the resume.\",\n \"job_description\": \"Strong match - listed as a primary skill.\",\n \"score\": 0\n },\n {\n \"skill\": \"llm\",\n \"resume\": \"No match - not mentioned in the resume.\",\n \"job_description\": \"Strong match - listed as a primary skill.\",\n \"score\": 0\n },\n {\n \"skill\": \"leadership\",\n \"resume\": \"Implicit match - Senior role implies leadership experience.\",\n \"job_description\": \"Explicit match - requires leading and guiding teams.\",\n \"score\": 75\n },\n {\n \"skill\": \"client_interaction\",\n \"resume\": \"No explicit mention, inferred from senior role.\",\n \"job_description\": \"Explicit match - requires interfacing with clients.\",\n \"score\": 50\n }\n ],\n \"overall_match_score\": 45,\n \"rationale\": \"The candidate's core skill (Python) is a strong match. The resume implies leadership skills, aligning with the job's team leadership requirements. However, the absence of Sagemaker and LLM experience significantly lowers the overall score. The candidate needs to demonstrate experience in these areas for a higher match.\",\n \"recommendations\": [\n \"Highlight any experience (even if limited) with Sagemaker or LLMs in the resume.\",\n \"Quantify Python experience with specific projects and technologies used.\",\n \"Emphasize any client-facing experience or responsibilities in previous roles.\",\n \"Showcase leadership experience with specific examples (e.g., mentoring junior developers, leading project teams).\"\n ]\n }\n}\n"
},
"typeVersion": 1.2
},
{
"id": "1dcb1ca7-e4e9-4775-9eb8-94c9e1f89e64",
"name": "Créer des données binaires pour l'appariement d'emploi par IA",
"type": "n8n-nodes-base.function",
"position": [
1928,
-60
],
"parameters": {
"functionCode": "items[0].binary = {\n data: {\n data: new Buffer(JSON.stringify(items[0].json, null, 2)).toString('base64')\n }\n};\nreturn items;"
},
"typeVersion": 1
},
{
"id": "da19ddc2-5e0f-4a4a-b524-1086b59c511f",
"name": "Webhook Notification pour l'appariement d'emploi par IA",
"type": "n8n-nodes-base.httpRequest",
"position": [
1928,
215
],
"parameters": {
"url": "https://webhook.site/7b5380a0-0544-48dc-be43-0116cb2d52c2",
"options": {},
"sendBody": true,
"contentType": "multipart-form-data",
"bodyParameters": {
"parameters": [
{
"name": "job_match_response",
"value": "={{ $json.output.job_match_analysis.toJsonString() }}"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "0561839e-9ca9-4c18-9a9e-98b9a1f796fc",
"name": "Note adhésive2",
"type": "n8n-nodes-base.stickyNote",
"position": [
640,
-320
],
"parameters": {
"width": 440,
"height": 120,
"content": "## Disclaimer\nThis template is only available on n8n self-hosted as it's making use of the community node for MCP Client."
},
"typeVersion": 1
},
{
"id": "d68fd51a-d74f-4236-89e1-6144f9e80943",
"name": "Note adhésive4",
"type": "n8n-nodes-base.stickyNote",
"position": [
-300,
-140
],
"parameters": {
"color": 5,
"width": 440,
"height": 220,
"content": "## LLM Usages\n\nOpenAI 4o mini LLM is being utilized for the structured data extraction handling."
},
"typeVersion": 1
},
{
"id": "29342cc1-10dd-490c-b274-fd5a82dbae1e",
"name": "Note adhésive",
"type": "n8n-nodes-base.stickyNote",
"position": [
640,
-160
],
"parameters": {
"color": 3,
"width": 1660,
"height": 620,
"content": "## Bright Data MCP Job Extract via Job Listings\nExtract job information via BrightData MCP and then perform the AI Job matching by utilizing the OpenAI GPT 4o mini LLM"
},
"typeVersion": 1
},
{
"id": "25d7b451-0f5e-4694-a821-ea7fe93b7d6f",
"name": "Note adhésive5",
"type": "n8n-nodes-base.stickyNote",
"position": [
-740,
-700
],
"parameters": {
"color": 7,
"width": 400,
"height": 400,
"content": "## Logo\n\n\n\n"
},
"typeVersion": 1
},
{
"id": "02e69f64-f7b4-4a0d-828c-3fcea324268e",
"name": "Note adhésive1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-740,
-240
],
"parameters": {
"width": 400,
"height": 320,
"content": "## Note\n\nDeals with the LinkedIn profile data extraction by utilizing the Bright Data MCP and OpenAI GPT 4o LLM.\n\n**Please make sure to set the input fields node with the LinkedIn profile URL with the resume, location, keywords etc.\n\nPlease make sure to update the Webhook Notification URL of your interest**"
},
"typeVersion": 1
},
{
"id": "cb84eebb-4215-4bb3-91f6-bf7897a8ddf6",
"name": "OpenAI Modèle de chat pour l'extraction de description de poste",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
1264,
210
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"id": "vPKynKbDzJ5ZU4cU",
"name": "OpenAi account"
}
},
"typeVersion": 1.2
},
{
"id": "4d14c3a1-5402-4f27-beda-dba41c1aa912",
"name": "OpenAI Modèle de chat pour l'appariement d'emploi par IA",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
1560,
200
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"id": "vPKynKbDzJ5ZU4cU",
"name": "OpenAi account"
}
},
"typeVersion": 1.2
},
{
"id": "2aec37e7-a67b-47b1-b3b2-7ea7e114bfff",
"name": "Écrire la réponse d'appariement d'emploi par IA sur le disque",
"type": "n8n-nodes-base.readWriteFile",
"position": [
2148,
-60
],
"parameters": {
"options": {},
"fileName": "=d:\\Job-Match-{{$now.toSeconds()}}.json",
"operation": "write"
},
"typeVersion": 1
},
{
"id": "af980102-85d0-4f90-842f-196605f6bcd6",
"name": "Extracteur de données d'emploi paginées",
"type": "@n8n/n8n-nodes-langchain.informationExtractor",
"position": [
140,
115
],
"parameters": {
"text": "=Extract all the job links from the provided content. \n\nHere's the content: {{ $json.result.content[0].text }}",
"options": {},
"schemaType": "manual",
"inputSchema": "{\n\t\"type\": \"array\",\n\t\"properties\": {\n\t\t\"link\": {\n\t\t\t\"type\": \"string\"\n\t\t}\n\t}\n}"
},
"retryOnFail": true,
"typeVersion": 1
},
{
"id": "cb8e32c9-c1ac-4441-a42a-42e6b0d78970",
"name": "OpenAI Modèle de chat pour l'extraction d'emplois paginés",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
228,
335
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"id": "vPKynKbDzJ5ZU4cU",
"name": "OpenAi account"
}
},
"typeVersion": 1.2
}
],
"active": false,
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"versionId": "b366450e-b10e-412e-b442-a0827ca430bb",
"connections": {
"ff3193e5-cd22-40f4-8180-b76ad32055b3": {
"main": [
[
{
"node": "a75e1f8d-9dd4-4c87-b1ab-05c502b8cae7",
"type": "main",
"index": 0
}
]
]
},
"4636d7e9-8d13-4f57-95f9-936f6d8bbf1d": {
"main": [
[
{
"node": "1dcb1ca7-e4e9-4775-9eb8-94c9e1f89e64",
"type": "main",
"index": 0
},
{
"node": "da19ddc2-5e0f-4a4a-b524-1086b59c511f",
"type": "main",
"index": 0
}
]
]
},
"a75e1f8d-9dd4-4c87-b1ab-05c502b8cae7": {
"main": [
[],
[
{
"node": "cd1fcbd8-acf3-4a91-8158-f664aaa839e7",
"type": "main",
"index": 0
}
]
]
},
"83219c20-7341-4e42-8cae-cc2e1e8e9b8e": {
"main": [
[
{
"node": "40a70c2b-5dcc-44f7-8fde-9c28748181cd",
"type": "main",
"index": 0
}
]
]
},
"51b5d9dd-b0c8-4aaf-b789-f96e94519b94": {
"ai_outputParser": [
[
{
"node": "4636d7e9-8d13-4f57-95f9-936f6d8bbf1d",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"af980102-85d0-4f90-842f-196605f6bcd6": {
"main": [
[
{
"node": "ff3193e5-cd22-40f4-8180-b76ad32055b3",
"type": "main",
"index": 0
}
]
]
},
"d9f78a12-9eaa-4d9b-9e5c-5150d6e40e95": {
"main": [
[
{
"node": "4636d7e9-8d13-4f57-95f9-936f6d8bbf1d",
"type": "main",
"index": 0
}
]
]
},
"3820c9d3-be68-4a60-a810-943a9795bdbd": {
"main": [
[
{
"node": "83219c20-7341-4e42-8cae-cc2e1e8e9b8e",
"type": "main",
"index": 0
}
]
]
},
"92f0272d-dc5d-4424-9d96-cc2521e8a4ae": {
"main": [
[
{
"node": "3820c9d3-be68-4a60-a810-943a9795bdbd",
"type": "main",
"index": 0
}
]
]
},
"4d14c3a1-5402-4f27-beda-dba41c1aa912": {
"ai_languageModel": [
[
{
"node": "4636d7e9-8d13-4f57-95f9-936f6d8bbf1d",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"1dcb1ca7-e4e9-4775-9eb8-94c9e1f89e64": {
"main": [
[
{
"node": "2aec37e7-a67b-47b1-b3b2-7ea7e114bfff",
"type": "main",
"index": 0
}
]
]
},
"da19ddc2-5e0f-4a4a-b524-1086b59c511f": {
"main": [
[
{
"node": "a75e1f8d-9dd4-4c87-b1ab-05c502b8cae7",
"type": "main",
"index": 0
}
]
]
},
"cb84eebb-4215-4bb3-91f6-bf7897a8ddf6": {
"ai_languageModel": [
[
{
"node": "d9f78a12-9eaa-4d9b-9e5c-5150d6e40e95",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"2aec37e7-a67b-47b1-b3b2-7ea7e114bfff": {
"main": [
[]
]
},
"40a70c2b-5dcc-44f7-8fde-9c28748181cd": {
"main": [
[
{
"node": "af980102-85d0-4f90-842f-196605f6bcd6",
"type": "main",
"index": 0
}
]
]
},
"cb8e32c9-c1ac-4441-a42a-42e6b0d78970": {
"ai_languageModel": [
[
{
"node": "af980102-85d0-4f90-842f-196605f6bcd6",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"cd1fcbd8-acf3-4a91-8158-f664aaa839e7": {
"main": [
[
{
"node": "d9f78a12-9eaa-4d9b-9e5c-5150d6e40e95",
"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 - Ressources Humaines, 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.
Workflows recommandés
Automatisation du data mining Etsy avec Bright Data et Google Gemini
Automatisation de l'extraction de données Etsy avec Bright Data et Google Gemini
Set
Function
Split Out
+
Set
Function
Split Out
19 NœudsRanjan Dailata
Produit
Recherche et extraction d'entreprises DNB avec Bright Data et OpenAI 4o mini
Recherche et extraction d'entreprises DNB avec Bright Data et OpenAI 4o mini
Set
Function
Mcp Client
+
Set
Function
Mcp Client
18 NœudsRanjan Dailata
Produit
Extraction, résumé et analyse des baisses de prix des produits Amazon avec Bright Data
utilisationBright DataetGoogle Geminiextraction、总结etanalyse亚马逊降价信息
Set
Wait
Merge
+
Set
Wait
Merge
26 NœudsRanjan Dailata
Intelligence Artificielle
Extracteur d'études de cas juridiques, Mineur de données avec Bright Data MCP et Google Gemini
Extracteur d'études de cas juridiques, mineur de données utilisant Bright Data MCP et Google Gemini
Set
Code
Wait
+
Set
Code
Wait
22 NœudsRanjan Dailata
Intelligence Artificielle
Extraction de profil LinkedIn et construction de CV JSON (Bright Data et Google Gemini)
Extraction de profils LinkedIn et construction de CV en JSON (Bright Data et Google Gemini)
Set
Code
Function
+
Set
Code
Function
19 NœudsRanjan Dailata
Ressources Humaines
Extraction et recherche de données ProductHunt pilotées par un agent IA (en utilisant Bright Data et Google Gemini)
Extraire et rechercher des données ProductHunt avec Bright Data MCP et Google Gemini AI
Set
Function
Mcp Client
+
Set
Function
Mcp Client
21 NœudsRanjan Dailata
Intelligence Artificielle
Informations sur le workflow
Niveau de difficulté
Avancé
Nombre de nœuds22
Catégorie2
Types de nœuds13
Description de la difficulté
Auteur
Ranjan Dailata
@ranjancseA Professional based out of India specialized in handling AI-powered automations. Contact me at ranjancse@gmail.com
Liens externes
Voir sur n8n.io →
Partager ce workflow