Workflow n8n
Automatisation Google Sheets avec n8n : analyse de modèles LLM
Ce workflow n8n a pour objectif de tester plusieurs modèles de langage local à l'aide de LM Studio et d'analyser leurs performances. Dans un contexte où les entreprises cherchent à optimiser l'utilisation des modèles d'intelligence artificielle, ce workflow permet de capturer des données précieuses sur les performances des modèles en temps réel. Les cas d'usage incluent l'évaluation de la qualité des réponses générées par les modèles et l'optimisation des processus de communication.
- Étape 1 : le déclencheur 'When chat message received' active le workflow lors de la réception d'un message.
- Étape 2 : le noeud 'Get Models' récupère les modèles disponibles via une requête HTTP.
- Étape 3 : les noeuds 'Sticky Note' sont utilisés pour afficher des informations pertinentes tout au long du processus.
- Étape 4 : le noeud 'Run Model with Dynamic Inputs' exécute le modèle sélectionné avec des entrées dynamiques.
- Étape 5 : les résultats sont analysés à l'aide du noeud 'Analyze LLM Response Metrics' et sauvegardés dans Google Sheets via le noeud 'Save Results to Google Sheets'. Ce workflow offre une valeur ajoutée significative en permettant aux entreprises de mieux comprendre et d'optimiser l'utilisation des modèles LLM, réduisant ainsi le temps d'analyse et améliorant la qualité des interactions.
Tags clés :automatisationGoogle SheetsLLMn8nanalyse de données
Catégorie: Webhook · Tags: automatisation, Google Sheets, LLM, n8n, analyse de données❤ 0
Workflow n8n Google Sheets, LLM, analyse de données : vue d'ensemble
Schéma des nœuds et connexions de ce workflow n8n, généré à partir du JSON n8n.
Workflow n8n Google Sheets, LLM, analyse de données : détail des nœuds
Inscris-toi pour voir l'intégralité du workflow
Inscription gratuite
S'inscrire gratuitementBesoin d'aide ?{
"id": "WulUYgcXvako9hBy",
"meta": {
"instanceId": "d6b86682c7e02b79169c1a61ad0484dcda5bc8b0ea70f1a95dac239c2abfd057",
"templateCredsSetupCompleted": true
},
"name": "Testing Mulitple Local LLM with LM Studio",
"tags": [
{
"id": "RkTiZTdbLvr6uzSg",
"name": "Training",
"createdAt": "2024-06-18T16:09:35.806Z",
"updatedAt": "2024-06-18T16:09:35.806Z"
},
{
"id": "W3xdiSeIujD7XgBA",
"name": "Template",
"createdAt": "2024-06-18T22:15:34.874Z",
"updatedAt": "2024-06-18T22:15:34.874Z"
}
],
"nodes": [
{
"id": "08c457ef-5c1f-46d8-a53e-f492b11c83f9",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
1600,
420
],
"parameters": {
"color": 6,
"width": 478.38709677419376,
"height": 347.82258064516134,
"content": "## 🧠Text Analysis\n### Readability Score Ranges:\nWhen testing model responses, readability scores can range across different levels. Here’s a breakdown:\n\n- **90–100**: Very easy to read (5th grade or below)\n- **80–89**: Easy to read (6th grade)\n- **70–79**: Fairly easy to read (7th grade)\n- **60–69**: Standard (8th to 9th grade)\n- **50–59**: Fairly difficult (10th to 12th grade)\n- **30–49**: Difficult (College)\n- **0–29**: Very difficult (College graduate)\n- **Below 0**: Extremely difficult (Post-graduate level)\n"
},
"typeVersion": 1
},
{
"id": "7801734c-5eb9-4abd-b234-e406462931f7",
"name": "Get Models",
"type": "n8n-nodes-base.httpRequest",
"onError": "continueErrorOutput",
"position": [
20,
180
],
"parameters": {
"url": "http://192.168.1.179:1234/v1/models",
"options": {
"timeout": 10000,
"allowUnauthorizedCerts": false
}
},
"typeVersion": 4.2
},
{
"id": "5ee93d9a-ad2e-4ea9-838e-2c12a168eae6",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-140,
-100
],
"parameters": {
"width": 377.6129032258063,
"height": 264.22580645161304,
"content": "## ⚙️ 2. Update Local IP\nUpdate the **'Base URL'** `http://192.168.1.1:1234/v1/models` in the workflow to match the IP of your LM Studio server. (Running LM Server)[https://lmstudio.ai/docs/basics/server]\n\nThis node will query the LM Studio server to retrieve a list of all loaded model IDs at the time of the query. If you change or add models to LM Studio, you’ll need to rerun this node to get an updated list of active LLMs.\n"
},
"typeVersion": 1
},
{
"id": "f2b6a6ed-0ef1-4f2c-8350-9abd59d08e61",
"name": "When chat message received",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
-300,
180
],
"webhookId": "39c3c6d5-ea06-4faa-b0e3-4e77a05b0297",
"parameters": {
"options": {}
},
"typeVersion": 1.1
},
{
"id": "dbaf0ad1-9027-4317-a996-33a3fcc9e258",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-740,
200
],
"parameters": {
"width": 378.75806451612857,
"height": 216.12903225806457,
"content": "## 🛠️1. Setup - LM Studio\nFirst, download and install [LM Studio](https://lmstudio.ai/). Identify which LLM models you want to use for testing.\n\nNext, the selected models are loaded into the server capabilities to prepare them for testing. For a detailed guide on how to set up multiple models, refer to the [LM Studio Basics](https://lmstudio.ai/docs/basics) documentation.\n"
},
"typeVersion": 1
},
{
"id": "36770fd1-7863-4c42-a68d-8d240ae3683b",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
360,
400
],
"parameters": {
"width": 570.0000000000002,
"height": 326.0645161290325,
"content": "## 3. 💡Update the LM Settings\n\nFrom here, you can modify the following\n parameters to fine-tune model behavior:\n\n- **Temperature**: Controls randomness. Higher values (e.g., 1.0) produce more diverse results, while lower values (e.g., 0.2) make responses more focused and deterministic.\n- **Top P**: Adjusts nucleus sampling, where the model considers only a subset of probable tokens. A lower value (e.g., 0.5) narrows the response range.\n- **Presence Penalty**: Penalizes new tokens based on their presence in the input, encouraging the model to generate more varied responses.\n"
},
"typeVersion": 1
},
{
"id": "6b36f094-a3bf-4ff7-9385-4f7a2c80d54f",
"name": "Get timeDifference",
"type": "n8n-nodes-base.dateTime",
"position": [
1600,
160
],
"parameters": {
"endDate": "={{ $json.endDateTime }}",
"options": {},
"operation": "getTimeBetweenDates",
"startDate": "={{ $('Capture Start Time').item.json.startDateTime }}"
},
"typeVersion": 2
},
{
"id": "a0b8f29d-2f2f-4fcf-a54a-dff071e321e5",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
1900,
-260
],
"parameters": {
"width": 304.3225806451618,
"height": 599.7580645161281,
"content": "## 📊4. Create Google Sheet (Optional)\n1. First, create a Google Sheet with the following headers:\n - Prompt\n - Time Sent\n - Time Received\n - Total Time Spent\n - Model\n - Response\n - Readability Score\n - Average Word Length\n - Word Count\n - Sentence Count\n - Average Sentence Length\n2. After creating the sheet, update the corresponding Google Sheets node in the workflow to map the data fields correctly.\n"
},
"typeVersion": 1
},
{
"id": "d376a5fb-4e07-42a3-aa0c-8ccc1b9feeb7",
"name": "Sticky Note5",
"type": "n8n-nodes-base.stickyNote",
"position": [
-760,
-200
],
"parameters": {
"color": 5,
"width": 359.2903225806448,
"height": 316.9032258064518,
"content": "## 🏗️Setup Steps\n1. **Download and Install LM Studio**: Ensure LM Studio is correctly installed on your machine.\n2. **Update the Base URL**: Replace the base URL with the IP address of your LLM instance. Ensure the connection is established.\n3. **Configure LLM Settings**: Verify that your LLM models are properly set up and configured in LM Studio.\n4. **Create a Google Sheet**: Set up a Google Sheet with the necessary headers (Prompt, Time Sent, Time Received, etc.) to track your testing results.\n"
},
"typeVersion": 1
},
{
"id": "b21cad30-573e-4adf-a1d0-f34cf9628819",
"name": "Sticky Note6",
"type": "n8n-nodes-base.stickyNote",
"position": [
560,
-160
],
"parameters": {
"width": 615.8064516129025,
"height": 272.241935483871,
"content": "## 📖Prompting Multiple LLMs\n\nWhen testing for specific outcomes (such as conciseness or readability), you can add a **System Prompt** in the LLM Chain to guide the models' responses.\n\n**System Prompt Suggestion**:\n- Focus on ensuring that responses are concise, clear, and easily understandable by a 5th-grade reading level. \n- This prompt will help you compare models based on how well they meet readability standards and stay on point.\n \nAdjust the prompt to fit your desired testing criteria.\n"
},
"typeVersion": 1
},
{
"id": "dd5f7e7b-bc69-4b67-90e6-2077b6b93148",
"name": "Run Model with Dunamic Inputs",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
1020,
400
],
"parameters": {
"model": "={{ $node['Extract Model IDsto Run Separately'].json.id }}",
"options": {
"topP": 1,
"baseURL": "http://192.168.1.179:1234/v1",
"timeout": 250000,
"temperature": 1,
"presencePenalty": 0
}
},
"credentials": {
"openAiApi": {
"id": "LBE5CXY4yeWrZCsy",
"name": "OpenAi account"
}
},
"typeVersion": 1
},
{
"id": "a0ee6c9a-cf76-4633-9c43-a7dc10a1f73e",
"name": "Analyze LLM Response Metrics",
"type": "n8n-nodes-base.code",
"position": [
2000,
160
],
"parameters": {
"jsCode": "// Get the input data from n8n\nconst inputData = items.map(item => item.json);\n\n// Function to count words in a string\nfunction countWords(text) {\n return text.trim().split(/\\s+/).length;\n}\n\n// Function to count sentences in a string\nfunction countSentences(text) {\n const sentences = text.match(/[^.!?]+[.!?]+/g) || [];\n return sentences.length;\n}\n\n// Function to calculate average sentence length\nfunction averageSentenceLength(text) {\n const sentences = text.match(/[^.!?]+[.!?]+/g) || [];\n const sentenceLengths = sentences.map(sentence => sentence.trim().split(/\\s+/).length);\n const totalWords = sentenceLengths.reduce((acc, val) => acc + val, 0);\n return sentenceLengths.length ? (totalWords / sentenceLengths.length) : 0;\n}\n\n// Function to calculate average word length\nfunction averageWordLength(text) {\n const words = text.trim().split(/\\s+/);\n const totalCharacters = words.reduce((acc, word) => acc + word.length, 0);\n return words.length ? (totalCharacters / words.length) : 0;\n}\n\n// Function to calculate Flesch-Kincaid Readability Score\nfunction fleschKincaidReadability(text) {\n // Split text into sentences (approximate)\n const sentences = text.match(/[^.!?]+[.!?]*[\\n]*/g) || [];\n // Split text into words\n const words = text.trim().split(/\\s+/);\n // Estimate syllable count by matching vowel groups\n const syllableCount = (text.toLowerCase().match(/[aeiouy]{1,2}/g) || []).length;\n\n const sentenceCount = sentences.length;\n const wordCount = words.length;\n\n // Avoid division by zero\n if (wordCount === 0 || sentenceCount === 0) return 0;\n\n const averageWordsPerSentence = wordCount / sentenceCount;\n const averageSyllablesPerWord = syllableCount / wordCount;\n\n // Flesch-Kincaid formula\n return 206.835 - (1.015 * averageWordsPerSentence) - (84.6 * averageSyllablesPerWord);\n}\n\n\n// Prepare the result array for n8n output\nconst resultArray = [];\n\n// Loop through the input data and analyze each LLM response\ninputData.forEach(item => {\n const llmResponse = item.llm_response;\n\n // Perform the analyses\n const wordCount = countWords(llmResponse);\n const sentenceCount = countSentences(llmResponse);\n const avgSentenceLength = averageSentenceLength(llmResponse);\n const readabilityScore = fleschKincaidReadability(llmResponse);\n const avgWordLength = averageWordLength(llmResponse);\n\n // Structure the output to include original input and new calculated values\n resultArray.push({\n json: {\n llm_response: item.llm_response,\n prompt: item.prompt,\n model: item.model,\n start_time: item.start_time,\n end_time: item.end_time,\n time_diff: item.time_diff,\n word_count: wordCount,\n sentence_count: sentenceCount,\n average_sent_length: avgSentenceLength,\n readability_score: readabilityScore,\n average_word_length: avgWordLength\n }\n });\n});\n\n// Return the result array to n8n\nreturn resultArray;\n"
},
"typeVersion": 2
},
{
"id": "adef5d92-cb7e-417e-acbb-1a5d6c26426a",
"name": "Save Results to Google Sheets",
"type": "n8n-nodes-base.googleSheets",
"position": [
2180,
160
],
"parameters": {
"columns": {
"value": {
"Model": "={{ $('Extract Model IDsto Run Separately').item.json.id }}",
"Prompt": "={{ $json.prompt }}",
"Response ": "={{ $('LLM Response Analysis').item.json.text }}",
"TIme Sent": "={{ $json.start_time }}",
"Word_count": "={{ $json.word_count }}",
"Sentence_count": "={{ $json.sentence_count }}",
"Time Recieved ": "={{ $json.end_time }}",
"Total TIme spent ": "={{ $json.time_diff }}",
"readability_score": "={{ $json.readability_score }}",
"Average_sent_length": "={{ $json.average_sent_length }}",
"average_word_length": "={{ $json.average_word_length }}"
},
"schema": [
{
"id": "Prompt",
"type": "string",
"display": true,
"required": false,
"displayName": "Prompt",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "TIme Sent",
"type": "string",
"display": true,
"required": false,
"displayName": "TIme Sent",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Time Recieved ",
"type": "string",
"display": true,
"required": false,
"displayName": "Time Recieved ",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Total TIme spent ",
"type": "string",
"display": true,
"required": false,
"displayName": "Total TIme spent ",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Model",
"type": "string",
"display": true,
"required": false,
"displayName": "Model",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Response ",
"type": "string",
"display": true,
"required": false,
"displayName": "Response ",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "readability_score",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "readability_score",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "average_word_length",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "average_word_length",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Word_count",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "Word_count",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Sentence_count",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "Sentence_count",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Average_sent_length",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "Average_sent_length",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": []
},
"options": {},
"operation": "append",
"sheetName": {
"__rl": true,
"mode": "list",
"value": "gid=0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1GdoTjKOrhWOqSZb-AoLNlXgRGBdXKSbXpy-EsZaPGvg/edit#gid=0",
"cachedResultName": "Sheet1"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "1GdoTjKOrhWOqSZb-AoLNlXgRGBdXKSbXpy-EsZaPGvg",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1GdoTjKOrhWOqSZb-AoLNlXgRGBdXKSbXpy-EsZaPGvg/edit?usp=drivesdk",
"cachedResultName": "Teacking LLM Success"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "DMnEU30APvssJZwc",
"name": "Google Sheets account"
}
},
"typeVersion": 4.5
},
{
"id": "2e147670-67af-4dde-8ba8-90b685238599",
"name": "Capture End Time",
"type": "n8n-nodes-base.dateTime",
"position": [
1380,
160
],
"parameters": {
"options": {},
"outputFieldName": "endDateTime"
},
"typeVersion": 2
},
{
"id": "5a8d3334-b7f8-4f14-8026-055db795bb1f",
"name": "Capture Start Time",
"type": "n8n-nodes-base.dateTime",
"position": [
520,
160
],
"parameters": {
"options": {},
"outputFieldName": "startDateTime"
},
"typeVersion": 2
},
{
"id": "c42d1748-a10d-4792-8526-5ea1c542eeec",
"name": "Prepare Data for Analysis",
"type": "n8n-nodes-base.set",
"position": [
1800,
160
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "920ffdcc-2ae1-4ccb-bc54-049d9d84bd42",
"name": "llm_response",
"type": "string",
"value": "={{ $('LLM Response Analysis').item.json.text }}"
},
{
"id": "c3e70e1b-055c-4a91-aeb0-3d00d41af86d",
"name": "prompt",
"type": "string",
"value": "={{ $('When chat message received').item.json.chatInput }}"
},
{
"id": "cfa45a85-7e60-4a09-b1ed-f9ad51161254",
"name": "model",
"type": "string",
"value": "={{ $('Extract Model IDsto Run Separately').item.json.id }}"
},
{
"id": "a49758c8-4828-41d9-b1d8-4e64dc06920b",
"name": "start_time",
"type": "string",
"value": "={{ $('Capture Start Time').item.json.startDateTime }}"
},
{
"id": "6206be8f-f088-4c4d-8a84-96295937afe2",
"name": "end_time",
"type": "string",
"value": "={{ $('Capture End Time').item.json.endDateTime }}"
},
{
"id": "421b52f9-6184-4bfa-b36a-571e1ea40ce4",
"name": "time_diff",
"type": "string",
"value": "={{ $json.timeDifference.days }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "04679ba8-f13c-4453-99ac-970095bffc20",
"name": "Extract Model IDsto Run Separately",
"type": "n8n-nodes-base.splitOut",
"position": [
300,
160
],
"parameters": {
"options": {},
"fieldToSplitOut": "data"
},
"typeVersion": 1
},
{
"id": "97cdd050-5538-47e1-a67a-ea6e90e89b19",
"name": "Sticky Note7",
"type": "n8n-nodes-base.stickyNote",
"position": [
2240,
-160
],
"parameters": {
"width": 330.4677419354838,
"height": 182.9032258064516,
"content": "### Optional\nYou can just delete the google sheet node, and review the results by hand. \n\nUtilizing the google sheet, allows you to provide mulitple prompts and review the analysis against all of those runs."
},
"typeVersion": 1
},
{
"id": "5a1558ec-54e8-4860-b3db-edcb47c52413",
"name": "Add System Prompt",
"type": "n8n-nodes-base.set",
"position": [
740,
160
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "fd48436f-8242-4c01-a7c3-246d28a8639f",
"name": "system_prompt",
"type": "string",
"value": "Ensure that messages are concise and to the point readable by a 5th grader."
}
]
},
"includeOtherFields": true
},
"typeVersion": 3.4
},
{
"id": "74df223b-17ab-4189-a171-78224522e1c7",
"name": "LLM Response Analysis",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
1000,
160
],
"parameters": {
"text": "={{ $('When chat message received').item.json.chatInput }}",
"messages": {
"messageValues": [
{
"message": "={{ $json.system_prompt }}"
}
]
},
"promptType": "define"
},
"typeVersion": 1.4
},
{
"id": "65d8b0d3-7285-4c64-8ca5-4346e68ec075",
"name": "Sticky Note8",
"type": "n8n-nodes-base.stickyNote",
"position": [
380,
780
],
"parameters": {
"color": 3,
"width": 570.0000000000002,
"height": 182.91935483870984,
"content": "## 🚀Pro Tip \n\nIf you are getting strange results, ensure that you are Deleting the previous chat (next to the Chat Button) to ensure you aren't bleeding responses into the next chat. "
},
"typeVersion": 1
}
],
"active": false,
"pinData": {},
"settings": {
"timezone": "America/Denver",
"callerPolicy": "workflowsFromSameOwner",
"executionOrder": "v1",
"saveManualExecutions": true
},
"versionId": "a80bee71-8e21-40ff-8803-42d38f316bfb",
"connections": {
"Get Models": {
"main": [
[
{
"node": "Extract Model IDsto Run Separately",
"type": "main",
"index": 0
}
]
]
},
"Capture End Time": {
"main": [
[
{
"node": "Get timeDifference",
"type": "main",
"index": 0
}
]
]
},
"Add System Prompt": {
"main": [
[
{
"node": "LLM Response Analysis",
"type": "main",
"index": 0
}
]
]
},
"Capture Start Time": {
"main": [
[
{
"node": "Add System Prompt",
"type": "main",
"index": 0
}
]
]
},
"Get timeDifference": {
"main": [
[
{
"node": "Prepare Data for Analysis",
"type": "main",
"index": 0
}
]
]
},
"LLM Response Analysis": {
"main": [
[
{
"node": "Capture End Time",
"type": "main",
"index": 0
}
]
]
},
"Prepare Data for Analysis": {
"main": [
[
{
"node": "Analyze LLM Response Metrics",
"type": "main",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "Get Models",
"type": "main",
"index": 0
}
]
]
},
"Analyze LLM Response Metrics": {
"main": [
[
{
"node": "Save Results to Google Sheets",
"type": "main",
"index": 0
}
]
]
},
"Run Model with Dunamic Inputs": {
"ai_languageModel": [
[
{
"node": "LLM Response Analysis",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Extract Model IDsto Run Separately": {
"main": [
[
{
"node": "Capture Start Time",
"type": "main",
"index": 0
}
]
]
}
}
}Workflow n8n Google Sheets, LLM, analyse de données : pour qui est ce workflow ?
Ce workflow s'adresse aux entreprises et équipes techniques qui souhaitent tester et analyser des modèles de langage local. Il est particulièrement utile pour les équipes de data science et de développement d'IA, ainsi que pour les PME et les startups qui intègrent des solutions d'intelligence artificielle dans leurs processus.
Workflow n8n Google Sheets, LLM, analyse de données : problème résolu
Ce workflow résout le problème de l'évaluation et de l'analyse des performances des modèles de langage local. Il élimine les frustrations liées à la collecte manuelle de données et à l'analyse des résultats, permettant ainsi aux utilisateurs de gagner du temps et d'obtenir des insights précieux sur l'efficacité de leurs modèles. En automatisant ce processus, les utilisateurs peuvent se concentrer sur l'amélioration continue de leurs modèles et de leurs interactions.
Workflow n8n Google Sheets, LLM, analyse de données : étapes du workflow
Étape 1 : le workflow est déclenché par un message reçu via le noeud 'When chat message received'.
- Étape 1 : les modèles disponibles sont récupérés grâce au noeud 'Get Models'.
- Étape 2 : des notes autocollantes sont créées pour afficher des informations pertinentes.
- Étape 3 : le noeud 'Run Model with Dynamic Inputs' exécute le modèle sélectionné.
- Étape 4 : le temps de réponse est mesuré avec le noeud 'Get timeDifference'.
- Étape 5 : les résultats sont analysés via le noeud 'Analyze LLM Response Metrics'.
- Étape 6 : enfin, les résultats sont sauvegardés dans Google Sheets avec le noeud 'Save Results to Google Sheets'.
Workflow n8n Google Sheets, LLM, analyse de données : guide de personnalisation
Pour personnaliser ce workflow, vous pouvez modifier les paramètres du noeud 'Get Models' pour cibler des modèles spécifiques ou ajuster les entrées dynamiques dans le noeud 'Run Model with Dynamic Inputs'. Vous pouvez également changer le nom de la feuille et les colonnes dans le noeud 'Save Results to Google Sheets' pour adapter le stockage des résultats à vos besoins. Assurez-vous de sécuriser le webhook en configurant les options d'authentification nécessaires et envisagez d'ajouter des notifications pour suivre l'exécution du workflow.