This is my workflow. Despite having 74 news items, only one news story keeps repeating. If there are 74 news stories, they should all appear differently, but the same one keeps recurring. Additionally, Hinglish news appears in between, whereas I need the

[GAURAV_SRIVASTAVA1]

{
“nodes”: [
{
“parameters”: {
“options”: {}
},
“type”: “n8n-nodes-base.splitInBatches”,
“typeVersion”: 3,
“position”: [
752,
-720
],
“id”: “9ea4a330-1fbc-4ae8-b6ac-7b898eb5ced8”,
“name”: “Loop Over Items”
},
{
“parameters”: {
“chatId”: “-1003802161244”,
“text”: “==भाग {{ $json.part }} / {{ $json.total }} \n\n\n{{ $json.chunk.replaceAll('‘, ‘’) }}",
“additionalFields”: {
“appendAttribution”: false,
“parse_mode”: “HTML”
}
},
“type”: “n8n-nodes-base.telegram”,
“typeVersion”: 1.2,
“position”: [
640,
336
],
“id”: “ccf65da5-cca5-43fd-b737-51679e353c2d”,
“name”: “TG Part 1”,
“webhookId”: “4b31cc56-9617-44f1-b5a8-e370af508412”,
“credentials”: {
“telegramApi”: {
“id”: “RXo8wm3qdDOSMvUW”,
“name”: “Telegram account”
}
}
},
{
“parameters”: {
“conditions”: {
“options”: {
“caseSensitive”: true,
“leftValue”: “”,
“typeValidation”: “strict”,
“version”: 1
},
“conditions”: [
{
“leftValue”: “={{ ($json.finalContent || ‘’).length }}”,
“operator”: {
“type”: “number”,
“operation”: “larger”
},
“rightValue”: 500,
“id”: “b4314b9d-b326-4d9c-bf91-d322ca1687dc”
},
{
“id”: “ce58183c-cee4-4587-9891-7928f107e92f”,
“leftValue”: “={{ $json.link }}”,
“rightValue”: “daily-news-editorials”,
“operator”: {
“type”: “string”,
“operation”: “contains”
}
},
{
“id”: “c8252ecd-f269-45f2-b4f9-bcc80e43d66a”,
“leftValue”: “={{ $json.link }}”,
“rightValue”: “upsc-editorial-analysis”,
“operator”: {
“type”: “string”,
“operation”: “contains”
}
},
{
“id”: “3cec5682-ecc8-4a97-b1db-1611583f6d49”,
“leftValue”: “={{ $json.finalTitle }}”,
“rightValue”: “संपादकीय”,
“operator”: {
“type”: “string”,
“operation”: “contains”
}
}
],
“combinator”: “or”
},
“options”: {}
},
“type”: “n8n-nodes-base.filter”,
“typeVersion”: 2,
“position”: [
-480,
-784
],
“id”: “9e952ab0-3360-4205-bede-0b0f80fe306e”,
“name”: “Large Articles Only”
},
{
“parameters”: {
“url”: “=https://r.jina.ai/{{ $json.link }}”,
“sendHeaders”: true,
“headerParameters”: {
“parameters”: [
{
“name”: “X-Return-Format”,
“value”: “markdown”
}
]
},
“options”: {
“response”: {
“response”: {
“responseFormat”: “text”
}
}
}
},
“type”: “n8n-nodes-base.httpRequest”,
“typeVersion”: 4.4,
“position”: [
1184,
64
],
“id”: “21062c52-bae6-4aef-9bd4-cc0dda44e16c”,
“name”: “HTTP Request”,
“retryOnFail”: true
},
{
“parameters”: {
“jsCode”: “// 1. AI का जवाब निकालो\nconst text = $json.output || $json.text || $json.response || $json.content || “”;\n\n// 2. अगर जवाब खाली है, तो रुक जाओ\nif (!text || text.trim() === “”) {\n return [];\n}\n\n// 3. टेलीग्राम के लिए टुकड़े करो (3500 अक्षर)\nconst chunkSize = 3500;\nconst chunks = [];\n\nfor (let i = 0; i < text.length; i += chunkSize) {\n chunks.push({\n json: {\n chunk: text.substring(i, i + chunkSize),\n part: (i / chunkSize) + 1,\n total: Math.ceil(text.length / chunkSize)\n }\n });\n}\n\nreturn chunks;”
},
“type”: “n8n-nodes-base.code”,
“typeVersion”: 2,
“position”: [
-64,
336
],
“id”: “23d9bd7d-c78f-4f80-823e-d2aa085f10c7”,
“name”: “Code in JavaScript”
},
{
“parameters”: {
“documentId”: {
“__rl”: true,
“value”: “=19UkaWQQfGbbbnIwRfLM3_GK4QMJ7M4T8wmRUt5_m9Pc”,
“mode”: “id”
},
“sheetName”: {
“__rl”: true,
“mode”: “name”,
“value”: “=Sheet1”
},
“filtersUI”: {
“values”: [
{
“lookupColumn”: “date”,
“lookupValue”: “={{ $today.format(‘yyyy-MM-dd’) }}”
}
]
},
“combineFilters”: “OR”,
“options”: {}
},
“type”: “n8n-nodes-base.googleSheets”,
“typeVersion”: 4.7,
“position”: [
-48,
-720
],
“id”: “b7fbe7bf-68b8-4d38-aa7b-f0955e646d36”,
“name”: “Get row(s) in sheet”,
“alwaysOutputData”: true,
“credentials”: {
“googleSheetsOAuth2Api”: {
“id”: “eQatzwfWRNLwJOug”,
“name”: “Google Sheets account”
}
}
},
{
“parameters”: {
“operation”: “append”,
“documentId”: {
“__rl”: true,
“value”: “=19UkaWQQfGbbbnIwRfLM3_GK4QMJ7M4T8wmRUt5_m9Pc”,
“mode”: “id”
},
“sheetName”: {
“__rl”: true,
“value”: “gid=0”,
“mode”: “list”,
“cachedResultName”: “Sheet1”,
“cachedResultUrl”: “https://docs.google.com/spreadsheets/d/19UkaWQQfGbbbnIwRfLM3_GK4QMJ7M4T8wmRUt5_m9Pc/edit#gid=0”
},
“columns”: {
“mappingMode”: “defineBelow”,
“value”: {
"title ": “=={{ $json.input?.title || $json.title || ‘’ }}”,
“link”: “={{ $(‘Edit Fields1 mere data’).first().json.link }}”,
“content”: “={{ $json.output || ‘’ }}”,
“date”: “={{ $today.format(‘yyyy-MM-dd’) }}”
},
“matchingColumns”: [],
“schema”: [
{
“id”: "title ",
“displayName”: "title ",
“required”: false,
“defaultMatch”: false,
“display”: true,
“type”: “string”,
“canBeUsedToMatch”: true,
“removed”: false
},
{
“id”: “link”,
“displayName”: “link”,
“required”: false,
“defaultMatch”: false,
“display”: true,
“type”: “string”,
“canBeUsedToMatch”: true,
“removed”: false
},
{
“id”: “content”,
“displayName”: “content”,
“required”: false,
“defaultMatch”: false,
“display”: true,
“type”: “string”,
“canBeUsedToMatch”: true,
“removed”: false
},
{
“id”: “date”,
“displayName”: “date”,
“required”: false,
“defaultMatch”: false,
“display”: true,
“type”: “string”,
“canBeUsedToMatch”: true,
“removed”: false
},
{
“id”: “ok”,
“displayName”: “ok”,
“required”: false,
“defaultMatch”: false,
“display”: true,
“type”: “string”,
“canBeUsedToMatch”: true,
“removed”: true
},
{
“id”: “result”,
“displayName”: “result”,
“required”: false,
“defaultMatch”: false,
“display”: true,
“type”: “string”,
“canBeUsedToMatch”: true,
“removed”: true
}
],
“attemptToConvertTypes”: false,
“convertFieldsToString”: false
},
“options”: {}
},
“type”: “n8n-nodes-base.googleSheets”,
“typeVersion”: 4.7,
“position”: [
-960,
-144
],
“id”: “02528e8d-bf05-4b2f-9f5d-aef3e18da4c0”,
“name”: “Append row in sheet”,
“credentials”: {
“googleSheetsOAuth2Api”: {
“id”: “eQatzwfWRNLwJOug”,
“name”: “Google Sheets account”
}
}
},
{
“parameters”: {
“assignments”: {
“assignments”: [
{
“id”: “6a2942c5-3251-459a-8213-d6e56a6fc93a”,
“name”: “article_text”,
“value”: “=={{ $json.data }}”,
“type”: “string”
},
{
“id”: “994d0784-03f4-4857-9af9-4b86c92a919e”,
“name”: “title”,
“value”: “=={{ $node[“Edit Fields”].json.title }}”,
“type”: “string”
},
{
“id”: “1abcd113-26a8-4333-bec9-f069a2fb4daa”,
“name”: “link”,
“value”: “={{ $json.link }}”,
“type”: “string”
}
]
},
“includeOtherFields”: true,
“options”: {}
},
“type”: “n8n-nodes-base.set”,
“typeVersion”: 3.4,
“position”: [
-2096,
432
],
“id”: “0e763222-08c4-4869-9dcf-e7d48cbfe8c7”,
“name”: “Edit Fields1 mere data”
},
{
“parameters”: {
“rule”: {
“interval”: [
{
“field”: “hours”,
“hoursInterval”: 2,
“triggerAtMinute”: 11
}
]
}
},
“type”: “n8n-nodes-base.scheduleTrigger”,
“typeVersion”: 1.3,
“position”: [
-2160,
-880
],
“id”: “777443ab-7a71-4152-bdac-73a27f9bcf67”,
“name”: “Schedule Trigger”
},
{
“parameters”: {
“assignments”: {
“assignments”: [
{
“id”: “526e15e6-ab47-44a5-bc56-6fe66beb241d”,
“name”: “title”,
“value”: “={{ $json.link.split(’/‘).pop().replaceAll(’-', ’ ') }}”,
“type”: “string”
},
{
“id”: “75e9856e-43e4-4117-936a-618f9c5585b4”,
“name”: “link”,
“value”: “={{ $json.link.includes(‘http’) ? $json.link : “https://www.drishtiias.com” + $json.link }}”,
“type”: “string”
},
{
“id”: “4f747b02-ebb1-4ddc-95bd-2b840c297808”,
“name”: “content”,
“value”: “=={{ $json[“content:encoded”] || $json.content || $json.description || “” }}”,
“type”: “string”
},
{
“id”: “0feadf36-3acb-4491-a1a7-0afd23361110”,
“name”: “date”,
“value”: “={{ $json.link.match(/\d{4}\/\d{2}\/\d{2}/) ? $json.link.match(/\d{4}\/\d{2}\/\d{2}/)[0] : $today.format(‘yyyy-MM-dd’) }}”,
“type”: “string”
}
]
},
“options”: {}
},
“type”: “n8n-nodes-base.set”,
“typeVersion”: 3.4,
“position”: [
-656,
-800
],
“id”: “364e5677-8dc2-4a03-8706-efa24bb06edd”,
“name”: “Edit Fields”
},
{
“parameters”: {
“url”: “Not Found,
“sendHeaders”: true,
“headerParameters”: {
“parameters”: [
{
“name”: “User-Agent”,
“value”: “Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36”
},
{
“name”: “Accept”,
“value”: "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,/;q=0.8"
}
]
},
“options”: {}
},
“type”: “n8n-nodes-base.httpRequest”,
“typeVersion”: 4.4,
“position”: [
-1760,
-1104
],
“id”: “8a91a6f2-933c-4cde-b370-e6c78fea7581”,
“name”: “HTTP Request1”
},
{
“parameters”: {
“operation”: “extractHtmlContent”,
“extractionValues”: {
“values”: [
{
“key”: “link”,
“cssSelector”: "a[href=“/daily-news-editorials/”]”,
“returnValue”: “attribute”,
“attribute”: “href”,
“returnArray”: true
},
{
“key”: “date_raw”,
“cssSelector”: “span.editorial-date”,
“returnArray”: true
}
]
},
“options”: {}
},
“type”: “n8n-nodes-base.html”,
“typeVersion”: 1.2,
“position”: [
-1328,
-1104
],
“id”: “909c7ddf-7b64-4b67-a5a4-29142bcf39a9”,
“name”: “HTML”
},
{
“parameters”: {
“fieldToSplitOut”: “link”,
“include”: “allOtherFields”,
“options”: {}
},
“type”: “n8n-nodes-base.splitOut”,
“typeVersion”: 1,
“position”: [
-816,
-816
],
“id”: “18b1c7f2-8737-49c5-b5df-cfc930129d9a”,
“name”: “Split Out”
},
{
“parameters”: {
“url”: “EDITORIALS Archives - INSIGHTS IAS - Simplifying UPSC IAS Exam Preparation,
“options”: {}
},
“type”: “n8n-nodes-base.httpRequest”,
“typeVersion”: 4.4,
“position”: [
-1760,
-624
],
“id”: “8f69cbad-5575-41be-8262-1e702ab91720”,
“name”: “HTTP Request2”
},
{
“parameters”: {
“operation”: “extractHtmlContent”,
“extractionValues”: {
“values”: [
{
“key”: “link”,
“cssSelector”: “a[href*=”/2026/"] ",
“returnValue”: “attribute”,
“attribute”: “href”,
“returnArray”: true
}
]
},
“options”: {}
},
“type”: “n8n-nodes-base.html”,
“typeVersion”: 1.2,
“position”: [
-1328,
-624
],
“id”: “126a1ef8-121a-4342-815b-2aa410a74129”,
“name”: “HTML1”
},
{
“parameters”: {},
“type”: “n8n-nodes-base.merge”,
“typeVersion”: 3.2,
“position”: [
-1008,
-816
],
“id”: “3ad1b4b4-7803-4b93-a889-519a23572940”,
“name”: “Merge”
},
{
“parameters”: {
“promptType”: “define”,
“text”: “=You are a UPSC content analyst.\n\nConvert the given ARTICLE into an ultra-short CRUX note in point form.\n\nSTRICT FORMAT RULES:\n\n1. Use ONLY “+ ” bullet points (plus sign).\n2. Keep every point extremely short (max 1 line).\n3. Use BOLD HEADINGS for each section.\n4. Structure exactly like this:\n\n Core Idea\n\n+ …\n\n Major Government Measures\n\n+ …\n\n Key Issues\n\n+ …\n\n Way Forward\n\n+ …\n\n5. Add FULL FORMS at first use:\n(DBT – Direct Benefit Transfer, DPDP – Digital Personal Data Protection Act, etc.)\n\n6. Use emojis ONLY in section headings.\n(No emojis inside bullet points.)\n\n7. Tone: UPSC analytical + crisp.\n\n8. Do NOT explain.\nDo NOT add conclusions.\nDo NOT add summaries.\nDo NOT add hashtags.\nDo NOT add any line after last bullet.\n\n9. Every bullet must start with “+” only.\n\n10. Language: Pure Hindi (policy style).\n\n11. Convert long ideas into micro-points.\n\n12. If numbers/data exist, compress them into one short line.\n\n13. Final output must look like Telegram-ready revision notes.\n\nONLY return formatted content.\nNothing else.”,
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.agent”,
“typeVersion”: 3.1,
“position”: [
-1456,
-48
],
“id”: “deb5ca48-8892-43fa-9926-6da314161ae6”,
“name”: “AI Analysis (Hindi)”,
“executeOnce”: false,
“retryOnFail”: true,
“waitBetweenTries”: 5000,
“onError”: “continueRegularOutput”
},
{
“parameters”: {
“modelName”: “models/gemini-2.0-flash-001”,
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.lmChatGoogleGemini”,
“typeVersion”: 1,
“position”: [
-1456,
160
],
“id”: “2093d5d2-5f10-4c07-b4e1-85f1fbddb0a5”,
“name”: “Google Gemini Chat Model”,
“credentials”: {
“googlePalmApi”: {
“id”: “D6KyeNFNnZkRxVJM”,
“name”: “Google Gemini(PaLM) Api account”
}
},
“onError”: “continueRegularOutput”
},
{
“parameters”: {
“mergeByFields”: {
“values”: [
{
“field1”: “link”,
“field2”: “link”
}
]
},
“fuzzyCompare”: true,
“options”: {}
},
“type”: “n8n-nodes-base.compareDatasets”,
“typeVersion”: 2.3,
“position”: [
224,
-784
],
“id”: “c99d297c-750e-49ad-ae4e-8c290a8d9716”,
“name”: “Compare Datasets”
},
{
“parameters”: {
“conditions”: {
“options”: {
“caseSensitive”: true,
“leftValue”: “”,
“typeValidation”: “strict”,
“version”: 3
},
“conditions”: [
{
“id”: “21a6b2fc-98c3-4f58-b59f-0c9f176705e9”,
“leftValue”: “={{ $json.output }}”,
“rightValue”: “”,
“operator”: {
“type”: “string”,
“operation”: “notEmpty”,
“singleValue”: true
}
}
],
“combinator”: “and”
},
“options”: {}
},
“type”: “n8n-nodes-base.if”,
“typeVersion”: 2.3,
“position”: [
-464,
352
],
“id”: “0b62164f-8714-4297-b8eb-f9fa8c5d81f3”,
“name”: “If”
},
{
“parameters”: {
“model”: “llama-3.1-8b-instant”,
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.lmChatGroq”,
“typeVersion”: 1,
“position”: [
1184,
1968
],
“id”: “27482d13-1458-431f-ad7d-10ae339dfcb8”,
“name”: “Groq Chat Model”,
“credentials”: {
“groqApi”: {
“id”: “hIz6z3bRMQ9I31Ff”,
“name”: “Groq account”
}
}
},
{
“parameters”: {
“amount”: 15
},
“type”: “n8n-nodes-base.wait”,
“typeVersion”: 1.1,
“position”: [
288,
336
],
“id”: “4ccad74e-cec2-4c4a-8053-185f604b88e8”,
“name”: “Wait 5s1”,
“webhookId”: “123a8d23-bd26-4771-b088-8b655a6b8e3a”
},
{
“parameters”: {
“promptType”: “define”,
“text”: “You are a UPSC content analyst.\n\nConvert the given ARTICLE into an ultra-short CRUX note in point form.\n\nSTRICT FORMAT RULES:\n\n1. Use ONLY “+ ” bullet points (plus sign).\n2. Keep every point extremely short (max 1 line).\n3. Use BOLD HEADINGS for each section.\n4. Structure exactly like this:\n\n Core Idea\n\n+ …\n\n Major Government Measures\n\n+ …\n\n Key Issues\n\n+ …\n\n Way Forward\n\n+ …\n\n5. Add FULL FORMS at first use:\n(DBT – Direct Benefit Transfer, DPDP – Digital Personal Data Protection Act, etc.)\n\n6. Use emojis ONLY in section headings.\n(No emojis inside bullet points.)\n\n7. Tone: UPSC analytical + crisp.\n\n8. Do NOT explain.\nDo NOT add conclusions.\nDo NOT add summaries.\nDo NOT add hashtags.\nDo NOT add any line after last bullet.\n\n9. Every bullet must start with “+” only.\n\n10. Language: Pure Hindi (policy style).\n\n11. Convert long ideas into micro-points.\n\n12. If numbers/data exist, compress them into one short line.\n\n13. Final output must look like Telegram-ready revision notes.\n\nONLY return formatted content.\nNothing else.”,
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.agent”,
“typeVersion”: 3.1,
“position”: [
-528,
1376
],
“id”: “d211f759-5ea4-466b-9068-4f6a293fe7ce”,
“name”: “AI Agent”,
“retryOnFail”: true,
“waitBetweenTries”: 5000,
“onError”: “continueErrorOutput”
},
{
“parameters”: {
“amount”: 60
},
“type”: “n8n-nodes-base.wait”,
“typeVersion”: 1.1,
“position”: [
-768,
1376
],
“id”: “f76ab106-45e8-4e60-85c0-6a7978b536bd”,
“name”: “Wait1”,
“webhookId”: “1f5f2165-deff-497e-94a9-d3c9cfc82822”
},
{
“parameters”: {
“amount”: 20
},
“type”: “n8n-nodes-base.wait”,
“typeVersion”: 1.1,
“position”: [
1040,
-704
],
“id”: “b2e819eb-3892-407a-aad6-c45b68690e7c”,
“name”: “Wait2”,
“webhookId”: “c8310e24-da48-48c0-884c-a662e09e3bfc”
},
{
“parameters”: {
“modelName”: “models/gemini-2.0-flash-001”,
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.lmChatGoogleGemini”,
“typeVersion”: 1,
“position”: [
-528,
1632
],
“id”: “fb237c40-8ff3-4a31-afdc-64b100f6c722”,
“name”: “Google Gemini Chat Model1”,
“retryOnFail”: true,
“credentials”: {
“googlePalmApi”: {
“id”: “NvX5cYhKvgQISbLg”,
“name”: “Google Gemini(PaLM) Api account 2”
}
},
“onError”: “continueErrorOutput”
},
{
“parameters”: {
“amount”: 60
},
“type”: “n8n-nodes-base.wait”,
“typeVersion”: 1.1,
“position”: [
96,
1376
],
“id”: “9a787065-cd80-4114-b908-f50acd4c3d5d”,
“name”: “Wait3”,
“webhookId”: “60e7f084-5ba2-4583-99ce-311b9f8a27db”
},
{
“parameters”: {
“promptType”: “define”,
“text”: “You are a UPSC content analyst.\n\nConvert the given ARTICLE into an ultra-short CRUX note in point form.\n\nSTRICT FORMAT RULES:\n\n1. Use ONLY “+ ” bullet points (plus sign).\n2. Keep every point extremely short (max 1 line).\n3. Use BOLD HEADINGS for each section.\n4. Structure exactly like this:\n\n Core Idea\n\n+ …\n\n Major Government Measures\n\n+ …\n\n Key Issues\n\n+ …\n\n Way Forward\n\n+ …\n\n5. Add FULL FORMS at first use:\n(DBT – Direct Benefit Transfer, DPDP – Digital Personal Data Protection Act, etc.)\n\n6. Use emojis ONLY in section headings.\n(No emojis inside bullet points.)\n\n7. Tone: UPSC analytical + crisp.\n\n8. Do NOT explain.\nDo NOT add conclusions.\nDo NOT add summaries.\nDo NOT add hashtags.\nDo NOT add any line after last bullet.\n\n9. Every bullet must start with “+” only.\n\n10. Language: Pure Hindi (policy style).\n\n11. Convert long ideas into micro-points.\n\n12. If numbers/data exist, compress them into one short line.\n\n13. Final output must look like Telegram-ready revision notes.\n\nONLY return formatted content.\nNothing else.”,
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.agent”,
“typeVersion”: 3.1,
“position”: [
336,
1376
],
“id”: “0b50f0ef-fd16-4d2b-875c-d32b1e2b9d91”,
“name”: “AI Agent1”,
“retryOnFail”: true,
“onError”: “continueErrorOutput”
},
{
“parameters”: {
“modelName”: “models/gemini-2.0-flash-001”,
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.lmChatGoogleGemini”,
“typeVersion”: 1,
“position”: [
336,
1696
],
“id”: “997f1698-bea9-4e71-bc0c-0395152da9f3”,
“name”: “Google Gemini Chat Model2”,
“credentials”: {
“googlePalmApi”: {
“id”: “NvX5cYhKvgQISbLg”,
“name”: “Google Gemini(PaLM) Api account 2”
}
}
},
{
“parameters”: {
“amount”: 60
},
“type”: “n8n-nodes-base.wait”,
“typeVersion”: 1.1,
“position”: [
992,
1392
],
“id”: “caa839b4-a2fe-4fca-a454-b2703591fec6”,
“name”: “Wait4”,
“webhookId”: “bc9a9926-ea17-4593-9eb6-627184e45b8f”
},
{
“parameters”: {
“promptType”: “define”,
“text”: “You are a UPSC content analyst.\n\nConvert the given ARTICLE into an ultra-short CRUX note in point form.\n\nSTRICT FORMAT RULES:\n\n1. Use ONLY “+ ” bullet points (plus sign).\n2. Keep every point extremely short (max 1 line).\n3. Use BOLD HEADINGS for each section.\n4. Structure exactly like this:\n\n Core Idea\n\n+ …\n\n Major Government Measures\n\n+ …\n\n Key Issues\n\n+ …\n\n Way Forward\n\n+ …\n\n5. Add FULL FORMS at first use:\n(DBT – Direct Benefit Transfer, DPDP – Digital Personal Data Protection Act, etc.)\n\n6. Use emojis ONLY in section headings.\n(No emojis inside bullet points.)\n\n7. Tone: UPSC analytical + crisp.\n\n8. Do NOT explain.\nDo NOT add conclusions.\nDo NOT add summaries.\nDo NOT add hashtags.\nDo NOT add any line after last bullet.\n\n9. Every bullet must start with “+” only.\n\n10. Language: Pure Hindi (policy style).\n\n11. Convert long ideas into micro-points.\n\n12. If numbers/data exist, compress them into one short line.\n\n13. Final output must look like Telegram-ready revision notes.\n\nONLY return formatted content.\nNothing else.”,
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.agent”,
“typeVersion”: 3.1,
“position”: [
1184,
1696
],
“id”: “871ceef9-7c2e-450f-a75c-8fcfc7da9a8d”,
“name”: “AI Agent2”,
“retryOnFail”: true,
“onError”: “continueErrorOutput”
},
{
“parameters”: {
“modelName”: “models/gemini-2.0-flash-001”,
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.lmChatGoogleGemini”,
“typeVersion”: 1,
“position”: [
-1440,
1616
],
“id”: “0d9dfeda-17be-4a18-9af7-c3409fd1f3c9”,
“name”: “Google Gemini Chat Model3”,
“credentials”: {
“googlePalmApi”: {
“id”: “NvX5cYhKvgQISbLg”,
“name”: “Google Gemini(PaLM) Api account 2”
}
}
},
{
“parameters”: {
“conditions”: {
“options”: {
“caseSensitive”: true,
“leftValue”: “”,
“typeValidation”: “strict”,
“version”: 3
},
“conditions”: [
{
“id”: “6d43bcef-fa4f-498c-ad37-b7a502697acb”,
“leftValue”: “={{ $json.article_text }}”,
“rightValue”: “”,
“operator”: {
“type”: “string”,
“operation”: “notEmpty”,
“singleValue”: true
}
}
],
“combinator”: “and”
},
“options”: {}
},
“type”: “n8n-nodes-base.if”,
“typeVersion”: 2.3,
“position”: [
-1840,
432
],
“id”: “f48bef9c-fe04-4e25-934e-ffa344e4255c”,
“name”: “If1”
},
{
“parameters”: {
“amount”: 60
},
“type”: “n8n-nodes-base.wait”,
“typeVersion”: 1.1,
“position”: [
-1728,
-48
],
“id”: “159a35fd-76d8-4e76-8400-a850cdf877d8”,
“name”: “Wait”,
“webhookId”: “9ede2a2e-3b0e-4737-8d9a-057beaafc22f”
},
{
“parameters”: {
“assignments”: {
“assignments”: [
{
“id”: “144810ce-50c1-4e83-a099-614d9452f716”,
“name”: “article_text”,
“value”: “= {{ $json.link.split(‘/’).pop().replaceAll(‘-’, ’ ') }}\n// $json = HTTP Request ka current output ”,
“type”: “string”
},
{
“id”: “0a1de94b-9139-4028-b753-75ebffe99a00”,
“name”: “link”,
“value”: “=={{ $json.link || $input.first().json.link }}”,
“type”: “string”
}
]
},
“includeOtherFields”: true,
“options”: {}
},
“type”: “n8n-nodes-base.set”,
“typeVersion”: 3.4,
“position”: [
-1024,
1376
],
“id”: “c9a73328-756e-4363-af50-9f38888b9fae”,
“name”: “Edit Fields1”
},
{
“parameters”: {
“assignments”: {
“assignments”: [
{
“id”: “f6201df1-5a43-49de-a960-b441c5fa1c94”,
“name”: “article_text”,
“value”: “={{ $json.title }}”,
“type”: “string”
},
{
“id”: “a85b2d2a-56a1-476b-9c56-53c0cbacc380”,
“name”: “link”,
“value”: “={{ $json.link }}”,
“type”: “string”
},
{
“id”: “07768f14-f748-4b54-8d52-5f2859971cf6”,
“name”: “title”,
“value”: “={{ $json.title }}”,
“type”: “string”
}
]
},
“includeOtherFields”: true,
“options”: {}
},
“type”: “n8n-nodes-base.set”,
“typeVersion”: 3.4,
“position”: [
-352,
768
],
“id”: “601ba358-64af-4595-94df-57013dc562ff”,
“name”: “Edit Fields2”
},
{
“parameters”: {
“assignments”: {
“assignments”: [
{
“id”: “65a35b5a-dcbd-47b9-90bc-b92259911ad3”,
“name”: “article_text”,
“value”: “={{ $json.article_text }}”,
“type”: “string”
},
{
“id”: “e404898d-5a5b-4f94-b20a-e55d39a1ecea”,
“name”: “link”,
“value”: “={{ $json.link }}”,
“type”: “string”
},
{
“id”: “2bbf6f0d-988b-4b9d-8449-6f08846b7acb”,
“name”: “title”,
“value”: “={{ $json.title }}”,
“type”: “string”
}
]
},
“includeOtherFields”: true,
“options”: {}
},
“type”: “n8n-nodes-base.set”,
“typeVersion”: 3.4,
“position”: [
-112,
1392
],
“id”: “31410484-cb32-456d-b75f-8f4170b32705”,
“name”: “Edit Fields3”
},
{
“parameters”: {
“assignments”: {
“assignments”: [
{
“id”: “2de808a2-927b-4f9a-a9f9-7556b7b8a501”,
“name”: “article_text”,
“value”: “={{ $json.title }}”,
“type”: “string”
},
{
“id”: “3b98aef1-52ac-4d30-b301-3c912b73909a”,
“name”: “link”,
“value”: “={{ $json.link }}”,
“type”: “string”
},
{
“id”: “7605a1f0-269e-4de4-b456-8dde185c835f”,
“name”: “title”,
“value”: “={{ $json.title }}”,
“type”: “string”
}
]
},
“includeOtherFields”: true,
“options”: {}
},
“type”: “n8n-nodes-base.set”,
“typeVersion”: 3.4,
“position”: [
720,
1392
],
“id”: “6a6adaaf-7862-457e-9b55-cb925e6a5e4c”,
“name”: “Edit Fields4”
},
{
“parameters”: {
“promptType”: “define”,
“text”: “=You are a UPSC content analyst.\n\nConvert the given ARTICLE into an ultra-short CRUX note in point form.\n\nSTRICT FORMAT RULES:\n\n1. Use ONLY “+ ” bullet points (plus sign).\n2. Keep every point extremely short (max 1 line).\n3. Use BOLD HEADINGS for each section.\n4. Structure exactly like this:\n\n Core Idea\n\n+ …\n\n Major Government Measures\n\n+ …\n\n Key Issues\n\n+ …\n\n Way Forward\n\n+ …\n\n5. Add FULL FORMS at first use:\n(DBT – Direct Benefit Transfer, DPDP – Digital Personal Data Protection Act, etc.)\n\n6. Use emojis ONLY in section headings.\n(No emojis inside bullet points.)\n\n7. Tone: UPSC analytical + crisp.\n\n8. Do NOT explain.\nDo NOT add conclusions.\nDo NOT add summaries.\nDo NOT add hashtags.\nDo NOT add any line after last bullet.\n\n9. Every bullet must start with “+” only.\n\n10. Language: Pure Hindi (policy style).\n\n11. Convert long ideas into micro-points.\n\n12. If numbers/data exist, compress them into one short line.\n\n13. Final output must look like Telegram-ready revision notes.\n\nONLY return formatted content.\nNothing else.”,
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.agent”,
“typeVersion”: 3.1,
“position”: [
-1440,
1360
],
“id”: “689761d8-1fc2-4d34-826f-ad704ccca81b”,
“name”: “AI Analysis (Hindi)1 gemini”,
“executeOnce”: false,
“retryOnFail”: true,
“waitBetweenTries”: 5000,
“onError”: “continueErrorOutput”
}
],
“connections”: {
“Loop Over Items”: {
“main”: [
,
[
{
“node”: “Wait2”,
“type”: “main”,
“index”: 0
}
]
]
},
“TG Part 1”: {
“main”: [
[
{
“node”: “Loop Over Items”,
“type”: “main”,
“index”: 0
}
]
]
},
“Large Articles Only”: {
“main”: [
[
{
“node”: “Compare Datasets”,
“type”: “main”,
“index”: 0
}
]
]
},
“HTTP Request”: {
“main”: [
[
{
“node”: “Edit Fields1 mere data”,
“type”: “main”,
“index”: 0
}
]
]
},
“Code in JavaScript”: {
“main”: [
[
{
“node”: “Wait 5s1”,
“type”: “main”,
“index”: 0
}
]
]
},
“Get row(s) in sheet”: {
“main”: [
[
{
“node”: “Compare Datasets”,
“type”: “main”,
“index”: 1
}
]
]
},
“Append row in sheet”: {
“main”: [

]
},
“Edit Fields1 mere data”: {
“main”: [
[
{
“node”: “If1”,
“type”: “main”,
“index”: 0
}
]
]
},
“Schedule Trigger”: {
“main”: [
[
{
“node”: “HTTP Request1”,
“type”: “main”,
“index”: 0
},
{
“node”: “HTTP Request2”,
“type”: “main”,
“index”: 0
}
]
]
},
“Edit Fields”: {
“main”: [
[
{
“node”: “Large Articles Only”,
“type”: “main”,
“index”: 0
}
]
]
},
“HTTP Request1”: {
“main”: [
[
{
“node”: “HTML”,
“type”: “main”,
“index”: 0
}
]
]
},
“HTML”: {
“main”: [
[
{
“node”: “Merge”,
“type”: “main”,
“index”: 0
}
]
]
},
“Split Out”: {
“main”: [
[
{
“node”: “Edit Fields”,
“type”: “main”,
“index”: 0
}
]
]
},
“HTTP Request2”: {
“main”: [
[
{
“node”: “HTML1”,
“type”: “main”,
“index”: 0
}
]
]
},
“HTML1”: {
“main”: [
[
{
“node”: “Merge”,
“type”: “main”,
“index”: 1
}
]
]
},
“Merge”: {
“main”: [
[
{
“node”: “Split Out”,
“type”: “main”,
“index”: 0
}
]
]
},
“AI Analysis (Hindi)”: {
“main”: [
[
{
“node”: “If”,
“type”: “main”,
“index”: 0
},
{
“node”: “Append row in sheet”,
“type”: “main”,
“index”: 0
}
]
]
},
“Google Gemini Chat Model”: {
“ai_languageModel”: [
[
{
“node”: “AI Analysis (Hindi)”,
“type”: “ai_languageModel”,
“index”: 0
}
]
]
},
“Compare Datasets”: {
“main”: [
[
{
“node”: “Loop Over Items”,
“type”: “main”,
“index”: 0
}
]
]
},
“If”: {
“main”: [
[
{
“node”: “Code in JavaScript”,
“type”: “main”,
“index”: 0
}
],
[
{
“node”: “Edit Fields2”,
“type”: “main”,
“index”: 0
}
]
]
},
“Groq Chat Model”: {
“ai_languageModel”: [
[
{
“node”: “AI Agent2”,
“type”: “ai_languageModel”,
“index”: 0
}
]
]
},
“Wait 5s1”: {
“main”: [
[
{
“node”: “TG Part 1”,
“type”: “main”,
“index”: 0
}
]
]
},
“AI Agent”: {
“main”: [
,
[
{
“node”: “Edit Fields3”,
“type”: “main”,
“index”: 0
}
]
]
},
“Wait1”: {
“main”: [
[
{
“node”: “AI Agent”,
“type”: “main”,
“index”: 0
}
]
]
},
“Wait2”: {
“main”: [
[
{
“node”: “HTTP Request”,
“type”: “main”,
“index”: 0
}
]
]
},
“Google Gemini Chat Model1”: {
“ai_languageModel”: [
[
{
“node”: “AI Agent”,
“type”: “ai_languageModel”,
“index”: 0
}
]
]
},
“Wait3”: {
“main”: [
[
{
“node”: “AI Agent1”,
“type”: “main”,
“index”: 0
}
]
]
},
“AI Agent1”: {
“main”: [
,
[
{
“node”: “Edit Fields4”,
“type”: “main”,
“index”: 0
}
]
]
},
“Google Gemini Chat Model2”: {
“ai_languageModel”: [
[
{
“node”: “AI Agent1”,
“type”: “ai_languageModel”,
“index”: 0
}
]
]
},
“Wait4”: {
“main”: [
[
{
“node”: “AI Agent2”,
“type”: “main”,
“index”: 0
}
]
]
},
“AI Agent2”: {
“main”: [
[
{
“node”: “Code in JavaScript”,
“type”: “main”,
“index”: 0
}
],

]
},
“Google Gemini Chat Model3”: {
“ai_languageModel”: [
[
{
“node”: “AI Analysis (Hindi)1 gemini”,
“type”: “ai_languageModel”,
“index”: 0
}
]
]
},
“If1”: {
“main”: [
[
{
“node”: “Wait”,
“type”: “main”,
“index”: 0
}
],
[
{
“node”: “Loop Over Items”,
“type”: “main”,
“index”: 0
}
]
]
},
“Wait”: {
“main”: [
[
{
“node”: “AI Analysis (Hindi)”,
“type”: “main”,
“index”: 0
}
]
]
},
“Edit Fields1”: {
“main”: [
[
{
“node”: “Wait1”,
“type”: “main”,
“index”: 0
}
]
]
},
“Edit Fields2”: {
“main”: [
[
{
“node”: “AI Analysis (Hindi)1 gemini”,
“type”: “main”,
“index”: 0
}
]
]
},
“Edit Fields3”: {
“main”: [
[
{
“node”: “Wait3”,
“type”: “main”,
“index”: 0
}
]
]
},
“Edit Fields4”: {
“main”: [
[
{
“node”: “Wait4”,
“type”: “main”,
“index”: 0
}
]
]
},
“AI Analysis (Hindi)1 gemini”: {
“main”: [
,
[
{
“node”: “Edit Fields1”,
“type”: “main”,
“index”: 0
}
]
]
}
},
“pinData”: {},
“meta”: {
“templateCredsSetupCompleted”: true,
“instanceId”: “ce0e513f732586fec848aca55a53d5f59f6c3dfc77a49c8756ef38d275aa794a”
}
}. This is my workflow. Despite having 74 news items, only one news story keeps repeating. If there are 74 news stories, they should all appear differently, but the same one keeps recurring. Additionally, Hinglish news appears in between, whereas I need the

[Haian_Abou-Karam]

Hi,
AI model is not the The issue , in fact, it’s the data flow and loop logic:

1: Same News Repeating Again & Again, Why?

it is coming from this node:

Append row in sheet

this is an important issue:

“link”: “={{ $('Edit Fields1 mere data').first().json.link }}”

to fix, replace it with this:

$json.link

2: Hinglish Appearing Between Pure Hindi Notes

Inside your prompt insert this:

14. Do NOT use any English words.
Replace all English policy terms with official Hindi equivalents.

add also this one:

If any English word appears, rewrite output fully in Hindi.

3: You Are Over-Complicating AI Flow…

I recommend you, using this flow:

Schedule Trigger
→ Fetch Links → Merge → Split Out → Compare Dataset → Loop Over Items → HTTP Request (Article) → AI Analysis (ONE node only) → Append row in sheet → Telegram

Remove all duplicate AI nodes.

in summary, the most important thing is this issue, remove it right now:

$('Edit Fields1 mere data').first().json.link

[GAURAV_SRIVASTAVA1]

hello ,first thank you for your reply and giving me suggestion to workflow , with help of goole ai studio i build this workflow i know this is complicated, can you suggest me without any pricing plan how i can automate this workflow , because too much ai agent helping for credit (token) , what should be the suggestion i make my workflow simple aur regular anything can you share with me

[Haian_Abou-Karam]

Hi, @GAURAV_SRIVASTAVA1

I guess you build a workflow that do the following:

1. Collects news links from sources
2. Prevents duplicates
3. Downloads article content
4. Uses AI to analyze & summarize in pure Hindi
5. Stores results in Google Sheets
6. Sends formatted news to Telegram
   Here are the modified Workflow JSON, you can start with:

Now, test the nodes one by one and read the official documentation for each node.

This is just a starting point — modify and improve it as needed.
I recommend that you study:

---

Tutorial: Build an AI workflow in n8n | n8n Docs

---

Before that, I recommend studying at least n8n Course Level One

---

Text courses | n8n Docs

---

I hope you will reach your goal.

[GAURAV_SRIVASTAVA1]

i am very glad ,thank you so much you really help me , one of the question i want to ask that i am using only one ai agent ,( unpaid plan) if i add 2-3 ai agent it will give me more token , without paying any price, is it possible to add 2-3 ai agent for more article flow ,

[Haian_Abou-Karam]

@GAURAV_SRIVASTAVA1
Thank you — I’m really glad the workflow is working now

About your question: adding 2–3 AI Agents will not give you more tokens on an unpaid plan. The token limits are applied at the account/API level, not per agent or per workflow. So even if you create multiple agents, they all share the same usage limits.

If you are currently using n8n mainly to learn automation, I strongly recommend trying a local lightweight LLM instead of relying only on cloud tokens. You can run small models locally and connect them to n8n, which lets you experiment freely without worrying about token limits.
There is a good video explaining the setup here: 17:18

---

How to Build AI Agents in n8n for Beginners! (Full Guide - NoCode)

In this video, learn how to create an AI assistant agent using the n8n local for free. This step-by-step tutorial guides you through setting up the workflow automation, demonstrating each part of the process on-screen. Perfect for those looking into self-hosted options, this N8n tutorial shows you how to use the local version. [How to Build AI Agents in n8n for Beginners! (Full Guide - NoCode)]

---

If you plan to work on a real production project, then it’s important to understand token usage and cost optimization. In that case, combining cloud models with a local LLM can still be a very good strategy.

I’m preparing a small tip/tutorial about this topic and will share it soon I’ll, mention you when I publish it

[GAURAV_SRIVASTAVA1]

{
“nodes”: [
{
“parameters”: {
“rule”: {
“interval”: [
{
“triggerAtHour”: 3
}
]
}
},
“id”: “faf83921-7b1a-48f7-914f-ffea99ef0e1e”,
“name”: “Schedule Trigger”,
“type”: “n8n-nodes-base.scheduleTrigger”,
“typeVersion”: 1,
“position”: [
-1008,
112
]
},
{
“parameters”: {
“url”: “INSIGHTS IAS – Simplifying UPSC IAS Exam Preparation,
“options”: {}
},
“id”: “d0cb8301-f510-4e1f-b065-16834e4c1302”,
“name”: “Fetch RSS”,
“type”: “n8n-nodes-base.rssFeedRead”,
“typeVersion”: 1,
“position”: [
-800,
112
]
},
{
“parameters”: {
“operation”: “limit”
},
“id”: “f5171e5f-193a-4c77-b8e3-b10937f056b7”,
“name”: “Split Items”,
“type”: “n8n-nodes-base.itemLists”,
“typeVersion”: 3,
“position”: [
-608,
112
]
},
{
“parameters”: {
“documentId”: {
“__rl”: true,
“value”: “19UkaWQQfGbbbnIwRfLM3_GK4QMJ7M4T8wmRUt5_m9Pc”,
“mode”: “list”,
“cachedResultName”: “UPSC_Sent_Links)”,
“cachedResultUrl”: “https://docs.google.com/spreadsheets/d/19UkaWQQfGbbbnIwRfLM3_GK4QMJ7M4T8wmRUt5_m9Pc/edit?usp=drivesdk”
},
“sheetName”: {
“__rl”: true,
“value”: “gid=0”,
“mode”: “list”,
“cachedResultName”: “Sheet1”,
“cachedResultUrl”: “https://docs.google.com/spreadsheets/d/19UkaWQQfGbbbnIwRfLM3_GK4QMJ7M4T8wmRUt5_m9Pc/edit#gid=0”
},
“filtersUI”: {
“values”: [
{
“lookupColumn”: "title ",
“lookupValue”: “={{ $node[“Split Items”].json.link }}”
}
]
},
“options”: {
“outputFormatting”: {
“values”: {
“general”: “FORMATTED_VALUE”,
“date”: “FORMATTED_STRING”
}
}
}
},
“id”: “046542a3-ee04-4b24-8932-28e5f8e71b7d”,
“name”: “Check Duplicate”,
“type”: “n8n-nodes-base.googleSheets”,
“typeVersion”: 4,
“position”: [
-192,
112
],
“alwaysOutputData”: true,
“retryOnFail”: true,
“credentials”: {
“googleSheetsOAuth2Api”: {
“id”: “eQatzwfWRNLwJOug”,
“name”: “Google Sheets account”
}
}
},
{
“parameters”: {
“conditions”: {
“options”: {
“caseSensitive”: true,
“leftValue”: “”,
“typeValidation”: “strict”,
“version”: 1
},
“conditions”: [
{
“id”: “5ea693a7-62ef-4f4b-831f-662a39a95951”,
“leftValue”: “={{ $node[“Check Duplicate”].json.row_number }}”,
“rightValue”: “”,
“operator”: {
“type”: “string”,
“operation”: “empty”,
“singleValue”: true
}
}
],
“combinator”: “and”
},
“options”: {}
},
“id”: “d65523b9-acd7-4b35-a2e8-c0524de82ef1”,
“name”: “IF New”,
“type”: “n8n-nodes-base.if”,
“typeVersion”: 2,
“position”: [
0,
112
]
},
{
“parameters”: {
“operation”: “append”,
“documentId”: {
“__rl”: true,
“value”: “19UkaWQQfGbbbnIwRfLM3_GK4QMJ7M4T8wmRUt5_m9Pc”,
“mode”: “list”,
“cachedResultName”: “UPSC_Sent_Links)”,
“cachedResultUrl”: “https://docs.google.com/spreadsheets/d/19UkaWQQfGbbbnIwRfLM3_GK4QMJ7M4T8wmRUt5_m9Pc/edit?usp=drivesdk”
},
“sheetName”: {
“__rl”: true,
“value”: “gid=0”,
“mode”: “list”,
“cachedResultName”: “Sheet1”,
“cachedResultUrl”: “https://docs.google.com/spreadsheets/d/19UkaWQQfGbbbnIwRfLM3_GK4QMJ7M4T8wmRUt5_m9Pc/edit#gid=0”
},
“columns”: {
“mappingMode”: “defineBelow”,
“value”: {
"title ": “={{ $node[“Split Items”].json.title }}”,
"link ": “={{ $node[“Split Items”].json.link }}”,
“content”: “={{ $json.text }}”
},
“matchingColumns”: ,
“schema”: [
{
“id”: "title ",
“displayName”: "title ",
“required”: false,
“defaultMatch”: false,
“display”: true,
“type”: “string”,
“canBeUsedToMatch”: true
},
{
“id”: "link ",
“displayName”: "link ",
“required”: false,
“defaultMatch”: false,
“display”: true,
“type”: “string”,
“canBeUsedToMatch”: true
},
{
“id”: “content”,
“displayName”: “content”,
“required”: false,
“defaultMatch”: false,
“display”: true,
“type”: “string”,
“canBeUsedToMatch”: true
}
],
“attemptToConvertTypes”: false,
“convertFieldsToString”: false
},
“options”: {}
},
“id”: “127639ac-2f61-42a4-a6fb-92b5dedeab7f”,
“name”: “Append Sheet”,
“type”: “n8n-nodes-base.googleSheets”,
“typeVersion”: 4,
“position”: [
992,
96
],
“credentials”: {
“googleSheetsOAuth2Api”: {
“id”: “eQatzwfWRNLwJOug”,
“name”: “Google Sheets account”
}
}
},
{
“parameters”: {
“chatId”: “@ExamFocusPrep”,
“text”: “= {{ $node[“AI Analysis”].json.text.substring(0, 3000) }}”,
“additionalFields”: {
“parse_mode”: “HTML”
}
},
“id”: “cc4775ae-8999-4bb2-8df9-08f1ef4bfbd2”,
“name”: “Send Telegram”,
“type”: “n8n-nodes-base.telegram”,
“typeVersion”: 1,
“position”: [
1168,
96
],
“webhookId”: “d97685d9-4b4a-46fa-a429-aec2410683e1”,
“credentials”: {
“telegramApi”: {
“id”: “RXo8wm3qdDOSMvUW”,
“name”: “Telegram account”
}
}
},
{
“parameters”: {
“modelName”: “models/gemini-2.0-flash-lite-001”,
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.lmChatGoogleGemini”,
“typeVersion”: 1,
“position”: [
688,
352
],
“id”: “40b920f5-ed2f-4fc5-a869-f2c6ab40bb4c”,
“name”: “Google Gemini Chat Model”,
“credentials”: {
“googlePalmApi”: {
“id”: “D6KyeNFNnZkRxVJM”,
“name”: “Google Gemini(PaLM) Api account”
}
}
},
{
“parameters”: {
“amount”: 30
},
“type”: “n8n-nodes-base.wait”,
“typeVersion”: 1.1,
“position”: [
1360,
96
],
“id”: “14984ee7-0330-4cb4-97f1-40918b3f320b”,
“name”: “Wait”,
“webhookId”: “c635092c-bcff-4e82-8850-ac697104bfeb”
},
{
“parameters”: {
“chatId”: “@ExamFocusPrep”,
“text”: “={{ $node[“AI Analysis”].json.text.substring(3000, 6000) }}\n”,
“additionalFields”: {
“appendAttribution”: false,
“parse_mode”: “HTML”
}
},
“type”: “n8n-nodes-base.telegram”,
“typeVersion”: 1.2,
“position”: [
1520,
96
],
“id”: “6304bcd9-63d2-4fb4-b3e1-d243fe818a54”,
“name”: “Send a text message”,
“webhookId”: “6936fc23-7eee-4cef-a311-a49669039984”,
“credentials”: {
“telegramApi”: {
“id”: “RXo8wm3qdDOSMvUW”,
“name”: “Telegram account”
}
}
},
{
“parameters”: {
“promptType”: “define”,
“text”: “=You are a professional Hindi news analyst. \n\nRules: \n- Write only in pure Hindi. \n- Do NOT use English words. \n- Replace English policy terms with official Hindi equivalents. \n- Be factual and neutral. \n- If any English appears, rewrite fully in Hindi.\n\nFormatting Rules for Telegram:\n- DO NOT use asterisks (**) for bolding or headings. \n- Use simple emojis (like , , or ) to highlight headings or key points instead of markdown.\n- You MUST add a double line break (blank empty line) between every paragraph and every list item. Do not merge text into a single block.\n- Keep sentences short, clean, and highly readable for mobile users.”,
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.agent”,
“typeVersion”: 3.1,
“position”: [
688,
96
],
“id”: “4b4a9d15-4d16-453a-bf91-2470c29208bb”,
“name”: “AI Agent”,
“retryOnFail”: true
},
{
“parameters”: {
“url”: “={{ $node[“Split Items”].json[“link”] }}”,
“options”: {}
},
“id”: “39446514-155d-499b-8b0a-61f240c79dfb”,
“name”: “Get Article”,
“type”: “n8n-nodes-base.httpRequest”,
“typeVersion”: 4,
“position”: [
160,
96
]
},
{
“parameters”: {
“mode”: “insert”,
“memoryKey”: {
“__rl”: true,
“mode”: “list”,
“value”: “vector_store_key”
}
},
“type”: “@n8n/n8n-nodes-langchain.vectorStoreInMemory”,
“typeVersion”: 1.3,
“position”: [
336,
96
],
“id”: “0776047e-0b0f-4e61-a7d0-faafc3cb06f5”,
“name”: “Simple Vector Store”
},
{
“parameters”: {
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.documentDefaultDataLoader”,
“typeVersion”: 1.1,
“position”: [
448,
336
],
“id”: “3cadb49d-c25d-4fb7-a29c-c743eccad245”,
“name”: “Default Data Loader”
},
{
“parameters”: {},
“type”: “@n8n/n8n-nodes-langchain.embeddingsGoogleGemini”,
“typeVersion”: 1,
“position”: [
240,
336
],
“id”: “2c959447-8a8c-4987-a8b6-3e8b42990149”,
“name”: “Embeddings Google Gemini”,
“credentials”: {
“googlePalmApi”: {
“id”: “D6KyeNFNnZkRxVJM”,
“name”: “Google Gemini(PaLM) Api account”
}
}
},
{
“parameters”: {
“mode”: “retrieve-as-tool”,
“memoryKey”: {
“__rl”: true,
“value”: “vector_store_key”,
“mode”: “list”,
“cachedResultName”: “vector_store_key”
}
},
“type”: “@n8n/n8n-nodes-langchain.vectorStoreInMemory”,
“typeVersion”: 1.3,
“position”: [
848,
368
],
“id”: “5ad0a363-4b40-417e-9dd6-991bea0fcd05”,
“name”: “Simple Vector Store1”
},
{
“parameters”: {
“modelName”: “models/gemini-embedding-001”
},
“type”: “@n8n/n8n-nodes-langchain.embeddingsGoogleGemini”,
“typeVersion”: 1,
“position”: [
864,
576
],
“id”: “3e4bc832-02da-4bde-9937-e3322c205746”,
“name”: “Embeddings Google Gemini1”,
“credentials”: {
“googlePalmApi”: {
“id”: “D6KyeNFNnZkRxVJM”,
“name”: “Google Gemini(PaLM) Api account”
}
}
},
{
“parameters”: {
“amount”: 61
},
“type”: “n8n-nodes-base.wait”,
“typeVersion”: 1.1,
“position”: [
-400,
112
],
“id”: “7d60dc2f-14c4-4af2-b2d7-f2c21e70c999”,
“name”: “Wait1”,
“webhookId”: “16563518-be94-4f07-855e-f423afbf0e89”
}
],
“connections”: {
“Schedule Trigger”: {
“main”: [
[
{
“node”: “Fetch RSS”,
“type”: “main”,
“index”: 0
}
]
]
},
“Fetch RSS”: {
“main”: [
[
{
“node”: “Split Items”,
“type”: “main”,
“index”: 0
}
]
]
},
“Split Items”: {
“main”: [
[
{
“node”: “Wait1”,
“type”: “main”,
“index”: 0
}
]
]
},
“Check Duplicate”: {
“main”: [
[
{
“node”: “IF New”,
“type”: “main”,
“index”: 0
}
]
]
},
“IF New”: {
“main”: [
[
{
“node”: “Get Article”,
“type”: “main”,
“index”: 0
}
]
]
},
“Append Sheet”: {
“main”: [
[
{
“node”: “Send Telegram”,
“type”: “main”,
“index”: 0
}
]
]
},
“Send Telegram”: {
“main”: [
[
{
“node”: “Wait”,
“type”: “main”,
“index”: 0
}
]
]
},
“Google Gemini Chat Model”: {
“ai_languageModel”: [
[
{
“node”: “AI Agent”,
“type”: “ai_languageModel”,
“index”: 0
}
]
]
},
“Wait”: {
“main”: [
[
{
“node”: “Send a text message”,
“type”: “main”,
“index”: 0
}
]
]
},
“Send a text message”: {
“main”: [

]
},
“AI Agent”: {
“main”: [
[
{
“node”: “Append Sheet”,
“type”: “main”,
“index”: 0
}
]
]
},
“Get Article”: {
“main”: [
[
{
“node”: “Simple Vector Store”,
“type”: “main”,
“index”: 0
}
]
]
},
“Simple Vector Store”: {
“main”: [
[
{
“node”: “AI Agent”,
“type”: “main”,
“index”: 0
}
]
]
},
“Default Data Loader”: {
“ai_document”: [
[
{
“node”: “Simple Vector Store”,
“type”: “ai_document”,
“index”: 0
}
]
]
},
“Embeddings Google Gemini”: {
“ai_embedding”: [
[
{
“node”: “Simple Vector Store”,
“type”: “ai_embedding”,
“index”: 0
}
]
]
},
“Simple Vector Store1”: {
“ai_tool”: [
[
{
“node”: “AI Agent”,
“type”: “ai_tool”,
“index”: 0
}
]
]
},
“Embeddings Google Gemini1”: {
“ai_embedding”: [
[
{
“node”: “Simple Vector Store1”,
“type”: “ai_embedding”,
“index”: 0
}
]
]
},
“Wait1”: {
“main”: [
[
{
“node”: “Check Duplicate”,
“type”: “main”,
“index”: 0
}
]
]
}
},
“pinData”: {},
“meta”: {
“templateCredsSetupCompleted”: true,
“instanceId”: “ce0e513f732586fec848aca55a53d5f59f6c3dfc77a49c8756ef38d275aa794a”
}
} here is my code of workflow i am working what you provide, but giveing me message that too many request can you give me suggestion that how i resolve it

[Haian_Abou-Karam]

@GAURAV_SRIVASTAVA1

here is my code of workflow i am working what you provide, but giveing me message that too many request can you give me suggestion that how i resolve it

Try These:

Put Delay nod before AI Agent
test and tell me please?
* Think also about using “Enable Fallback Model”,

[GAURAV_SRIVASTAVA1]

i did what said by you but why this is not working i also took help claude gemini but it wont help , how i fix it ,

[Haian_Abou-Karam]

Nice Job, You are too close; you’ve built a powerful automation
* There are two classic “looping” problems in n8n:
1- Static Data Referencing (causing the repeats)
2- API Rate Limiting (the 429 error).

Here is how to fix your workflow to ensure all 74 items process uniquely and stay in pure Hindi.

---

1. Fixing the “Repeating News” Issue

The reason the same news repeats is likely because your AI Agent or “Edit Fields” nodes are using a “static reference” (like .first()) instead of a “dynamic reference” for each item in the loop.

The Fix it:

• In your AI Agent node, –> In the “Prompt” or “Text” field, ensure you are referencing the input data using

• {{ $json.article_text }} or {{ $json.content }}.
  

• Check your “Edit Fields” nodes: In your JSON, I see references like

• $(‘Edit Fields1 mere data’).first().json.link
  

• . The .first() command tells n8n to always take the very first item from that node, no matter which item is currently in the loop.

• Solution: Change all expressions from

• $node["NodeName"].first().json.field
  

• to simply $json.field. This forces n8n to look at the “current” item being processed in the batch.

2. Fixing the “429: Too Many Requests” Error

Your screenshot shows Gemini is failing because you are sending requests too fast. The free tier of Gemini has a limit (often 15 requests per minute).

The Fix:

1. Be sour that you Split In Batches as I told you before: Set the Batch Size to 1.

2. Wait Node: You already have a “Wait” node, but make sure it is placed immediately before the AI Agent. Set it to at least 10-15-20 sec.

3. Looping: Ensure the “done” output of your last node in the chain (Telegram/Google Sheets) loops back to the “Loop Over Items” (Split in Batches) node to grab the next single item.

---

3. Fix the “Hinglish” Issue

AI models often default to Hinglish if the source text contains English terms. To force Pure Hindi (Shuddh Hindi), you need to tighten the System Prompt.

Reference Type	Result	Use Case
{{ $json.title }}	Dynamic (Changes for every item)	Use this for loops.
{{ $node["Node"].first().json.title }}	Static (Stays on the 1st item)	Use only for “Global” settings.

Role: You are an expert Editor for a prestigious UPSC Editorial Analysis wing. Your task is to convert the provided article into a high-level, formal Hindi "CRUX" note for civil service aspirants.

LANGUAGE MANDATE (STRICT):
1. USE ONLY SHUDDH HINDI (शुद्ध हिंदी): Use official, administrative vocabulary (प्रशासनिक शब्दावली).
2. ZERO HINGLISH: Never use English words written in Devanagari if a Hindi equivalent exists (e.g., use 'प्रणाली' instead of 'सिस्टम', 'साझा' instead of 'शेयर').
3. ACRONYMS: For technical terms (e.g., GST, DBT), provide the full Hindi name first, followed by the acronym in brackets: "प्रत्यक्ष लाभ हस्तांतरण (DBT)".
4. TONE: Objective, analytical, and professional.

FORMATTING RULES:
- Use ONLY "+" bullet points.
- Use BOLD HEADINGS for sections.
- Add exactly ONE relevant emoji per heading only.
- Each bullet point must be a single, crisp line.

STRUCTURE:
🚀 मुख्य विचार (Core Idea)
+ [Enter crisp 1-line point here]

🏛️ प्रमुख सरकारी उपाय (Major Govt Measures)
+ [Enter crisp 1-line point here]

⚠️ मुख्य चुनौतियां (Key Issues)
+ [Enter crisp 1-line point here]

🌱 आगे की राह (Way Forward)
+ [Enter crisp 1-line point here]

ARTICLE TO ANALYZE:
{{ $json.article_text }}

[GAURAV_SRIVASTAVA1]

i did what you said but again not working {
“nodes”: [
{
“parameters”: {
“rule”: {
“interval”: [
{
“triggerAtHour”: 3
}
]
}
},
“id”: “faf83921-7b1a-48f7-914f-ffea99ef0e1e”,
“name”: “Schedule Trigger”,
“type”: “n8n-nodes-base.scheduleTrigger”,
“typeVersion”: 1,
“position”: [
-1008,
112
]
},
{
“parameters”: {
“url”: “INSIGHTS IAS – Simplifying UPSC IAS Exam Preparation,
“options”: {}
},
“id”: “d0cb8301-f510-4e1f-b065-16834e4c1302”,
“name”: “Fetch RSS”,
“type”: “n8n-nodes-base.rssFeedRead”,
“typeVersion”: 1,
“position”: [
-800,
112
]
},
{
“parameters”: {
“operation”: “limit”
},
“id”: “f5171e5f-193a-4c77-b8e3-b10937f056b7”,
“name”: “Split Items”,
“type”: “n8n-nodes-base.itemLists”,
“typeVersion”: 3,
“position”: [
-608,
112
]
},
{
“parameters”: {
“documentId”: {
“__rl”: true,
“value”: “19UkaWQQfGbbbnIwRfLM3_GK4QMJ7M4T8wmRUt5_m9Pc”,
“mode”: “list”,
“cachedResultName”: “UPSC_Sent_Links)”,
“cachedResultUrl”: “https://docs.google.com/spreadsheets/d/19UkaWQQfGbbbnIwRfLM3_GK4QMJ7M4T8wmRUt5_m9Pc/edit?usp=drivesdk”
},
“sheetName”: {
“__rl”: true,
“value”: “gid=0”,
“mode”: “list”,
“cachedResultName”: “Sheet1”,
“cachedResultUrl”: “https://docs.google.com/spreadsheets/d/19UkaWQQfGbbbnIwRfLM3_GK4QMJ7M4T8wmRUt5_m9Pc/edit#gid=0”
},
“filtersUI”: {
“values”: [
{
“lookupColumn”: "title ",
“lookupValue”: “={{ $node[“Split Items”].json.link }}”
}
]
},
“options”: {
“outputFormatting”: {
“values”: {
“general”: “FORMATTED_VALUE”,
“date”: “FORMATTED_STRING”
}
}
}
},
“id”: “046542a3-ee04-4b24-8932-28e5f8e71b7d”,
“name”: “Check Duplicate”,
“type”: “n8n-nodes-base.googleSheets”,
“typeVersion”: 4,
“position”: [
-352,
112
],
“alwaysOutputData”: true,
“retryOnFail”: true,
“credentials”: {
“googleSheetsOAuth2Api”: {
“id”: “eQatzwfWRNLwJOug”,
“name”: “Google Sheets account”
}
}
},
{
“parameters”: {
“conditions”: {
“options”: {
“caseSensitive”: true,
“leftValue”: “”,
“typeValidation”: “strict”,
“version”: 1
},
“conditions”: [
{
“id”: “5ea693a7-62ef-4f4b-831f-662a39a95951”,
“leftValue”: “={{ $node[“Check Duplicate”].json.row_number }}”,
“rightValue”: “”,
“operator”: {
“type”: “string”,
“operation”: “empty”,
“singleValue”: true
}
}
],
“combinator”: “and”
},
“options”: {}
},
“id”: “d65523b9-acd7-4b35-a2e8-c0524de82ef1”,
“name”: “IF New”,
“type”: “n8n-nodes-base.if”,
“typeVersion”: 2,
“position”: [
-128,
112
]
},
{
“parameters”: {
“operation”: “append”,
“documentId”: {
“__rl”: true,
“value”: “19UkaWQQfGbbbnIwRfLM3_GK4QMJ7M4T8wmRUt5_m9Pc”,
“mode”: “list”,
“cachedResultName”: “UPSC_Sent_Links)”,
“cachedResultUrl”: “https://docs.google.com/spreadsheets/d/19UkaWQQfGbbbnIwRfLM3_GK4QMJ7M4T8wmRUt5_m9Pc/edit?usp=drivesdk”
},
“sheetName”: {
“__rl”: true,
“value”: “gid=0”,
“mode”: “list”,
“cachedResultName”: “Sheet1”,
“cachedResultUrl”: “https://docs.google.com/spreadsheets/d/19UkaWQQfGbbbnIwRfLM3_GK4QMJ7M4T8wmRUt5_m9Pc/edit#gid=0”
},
“columns”: {
“mappingMode”: “defineBelow”,
“value”: {
"title ": “={{ $json.title }}”,
"link ": “={{ $json.link }}”,
“content”: “={{ $json.text }}”
},
“matchingColumns”: ,
“schema”: [
{
“id”: "title ",
“displayName”: "title ",
“required”: false,
“defaultMatch”: false,
“display”: true,
“type”: “string”,
“canBeUsedToMatch”: true
},
{
“id”: "link ",
“displayName”: "link ",
“required”: false,
“defaultMatch”: false,
“display”: true,
“type”: “string”,
“canBeUsedToMatch”: true
},
{
“id”: “content”,
“displayName”: “content”,
“required”: false,
“defaultMatch”: false,
“display”: true,
“type”: “string”,
“canBeUsedToMatch”: true
}
],
“attemptToConvertTypes”: false,
“convertFieldsToString”: false
},
“options”: {}
},
“id”: “127639ac-2f61-42a4-a6fb-92b5dedeab7f”,
“name”: “Append Sheet”,
“type”: “n8n-nodes-base.googleSheets”,
“typeVersion”: 4,
“position”: [
992,
96
],
“credentials”: {
“googleSheetsOAuth2Api”: {
“id”: “eQatzwfWRNLwJOug”,
“name”: “Google Sheets account”
}
}
},
{
“parameters”: {
“chatId”: “@ExamFocusPrep”,
“text”: “= {{ $node[“AI Analysis”].json.text.substring(0, 3000) }}”,
“additionalFields”: {
“parse_mode”: “HTML”
}
},
“id”: “cc4775ae-8999-4bb2-8df9-08f1ef4bfbd2”,
“name”: “Send Telegram”,
“type”: “n8n-nodes-base.telegram”,
“typeVersion”: 1,
“position”: [
1168,
96
],
“webhookId”: “d97685d9-4b4a-46fa-a429-aec2410683e1”,
“credentials”: {
“telegramApi”: {
“id”: “RXo8wm3qdDOSMvUW”,
“name”: “Telegram account”
}
}
},
{
“parameters”: {
“modelName”: “models/gemini-2.0-flash-lite-001”,
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.lmChatGoogleGemini”,
“typeVersion”: 1,
“position”: [
688,
352
],
“id”: “40b920f5-ed2f-4fc5-a869-f2c6ab40bb4c”,
“name”: “Google Gemini Chat Model”,
“credentials”: {
“googlePalmApi”: {
“id”: “D6KyeNFNnZkRxVJM”,
“name”: “Google Gemini(PaLM) Api account”
}
}
},
{
“parameters”: {
“amount”: 30
},
“type”: “n8n-nodes-base.wait”,
“typeVersion”: 1.1,
“position”: [
1360,
96
],
“id”: “14984ee7-0330-4cb4-97f1-40918b3f320b”,
“name”: “Wait”,
“webhookId”: “c635092c-bcff-4e82-8850-ac697104bfeb”
},
{
“parameters”: {
“chatId”: “@ExamFocusPrep”,
“text”: “={{ $json.output }}”,
“additionalFields”: {
“appendAttribution”: false,
“parse_mode”: “HTML”
}
},
“type”: “n8n-nodes-base.telegram”,
“typeVersion”: 1.2,
“position”: [
1520,
96
],
“id”: “6304bcd9-63d2-4fb4-b3e1-d243fe818a54”,
“name”: “Send a text message”,
“webhookId”: “6936fc23-7eee-4cef-a311-a49669039984”,
“credentials”: {
“telegramApi”: {
“id”: “RXo8wm3qdDOSMvUW”,
“name”: “Telegram account”
}
}
},
{
“parameters”: {
“promptType”: “define”,
“text”: “=Role: You are an expert Editor for a prestigious UPSC Editorial Analysis wing. Your task is to convert the provided article into a high-level, formal Hindi “CRUX” note for civil service aspirants.\n\nLANGUAGE MANDATE (STRICT):\n1. USE ONLY SHUDDH HINDI (शुद्ध हिंदी)\n2. ZERO HINGLISH — use ‘प्रणाली’ not ‘सिस्टम’, ‘साझा’ not ‘शेयर’\n3. ACRONYMS: पहले Hindi name फिर bracket mein acronym — “प्रत्यक्ष लाभ हस्तांतरण (DBT)”\n4. TONE: Objective, analytical, professional\n\nFORMATTING:\n- ONLY “+” bullet points\n- BOLD HEADINGS for sections\n- ONE emoji per heading only\n- Each bullet = single crisp line\n\nSTRUCTURE:\n🚀 मुख्य विचार (Core Idea)\n+ [point]\n\n🏛️ प्रमुख सरकारी उपाय (Major Govt Measures)\n+ [point]\n\n⚠️ मुख्य चुनौतियां (Key Issues)\n+ [point]\n\n🌱 आगे की राह (Way Forward)\n+ [point]\n\nARTICLE TO ANALYZE:\n{{ $json.pageContent }}”,
“options”: {
“batching”: {
“batchSize”: 1,
“delayBetweenBatches”: 65
}
}
},
“type”: “@n8n/n8n-nodes-langchain.agent”,
“typeVersion”: 3.1,
“position”: [
688,
96
],
“id”: “4b4a9d15-4d16-453a-bf91-2470c29208bb”,
“name”: “AI Agent”,
“retryOnFail”: true
},
{
“parameters”: {
“url”: “={{ $node[“Split Items”].json[“link”] }}”,
“options”: {}
},
“id”: “39446514-155d-499b-8b0a-61f240c79dfb”,
“name”: “Get Article”,
“type”: “n8n-nodes-base.httpRequest”,
“typeVersion”: 4,
“position”: [
96,
96
]
},
{
“parameters”: {
“mode”: “insert”,
“memoryKey”: {
“__rl”: true,
“mode”: “list”,
“value”: “vector_store_key”
},
“embeddingBatchSize”: 50,
“clearStore”: true
},
“type”: “@n8n/n8n-nodes-langchain.vectorStoreInMemory”,
“typeVersion”: 1.3,
“position”: [
240,
96
],
“id”: “0776047e-0b0f-4e61-a7d0-faafc3cb06f5”,
“name”: “Simple Vector Store”
},
{
“parameters”: {
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.documentDefaultDataLoader”,
“typeVersion”: 1.1,
“position”: [
448,
336
],
“id”: “3cadb49d-c25d-4fb7-a29c-c743eccad245”,
“name”: “Default Data Loader”
},
{
“parameters”: {
“modelName”: “models/gemini-embedding-001”
},
“type”: “@n8n/n8n-nodes-langchain.embeddingsGoogleGemini”,
“typeVersion”: 1,
“position”: [
240,
336
],
“id”: “2c959447-8a8c-4987-a8b6-3e8b42990149”,
“name”: “Embeddings Google Gemini”,
“credentials”: {
“googlePalmApi”: {
“id”: “NvX5cYhKvgQISbLg”,
“name”: “Google Gemini(PaLM) Api account 2”
}
}
},
{
“parameters”: {
“mode”: “retrieve-as-tool”,
“memoryKey”: {
“__rl”: true,
“value”: “vector_store_key”,
“mode”: “list”,
“cachedResultName”: “vector_store_key”
}
},
“type”: “@n8n/n8n-nodes-langchain.vectorStoreInMemory”,
“typeVersion”: 1.3,
“position”: [
848,
368
],
“id”: “5ad0a363-4b40-417e-9dd6-991bea0fcd05”,
“name”: “Simple Vector Store1”
},
{
“parameters”: {
“modelName”: “models/gemini-embedding-001”
},
“type”: “@n8n/n8n-nodes-langchain.embeddingsGoogleGemini”,
“typeVersion”: 1,
“position”: [
864,
576
],
“id”: “3e4bc832-02da-4bde-9937-e3322c205746”,
“name”: “Embeddings Google Gemini1”,
“credentials”: {
“googlePalmApi”: {
“id”: “D6KyeNFNnZkRxVJM”,
“name”: “Google Gemini(PaLM) Api account”
}
}
},
{
“parameters”: {
“amount”: 61
},
“type”: “n8n-nodes-base.wait”,
“typeVersion”: 1.1,
“position”: [
544,
96
],
“id”: “7d60dc2f-14c4-4af2-b2d7-f2c21e70c999”,
“name”: “Wait1”,
“webhookId”: “16563518-be94-4f07-855e-f423afbf0e89”
}
],
“connections”: {
“Schedule Trigger”: {
“main”: [
[
{
“node”: “Fetch RSS”,
“type”: “main”,
“index”: 0
}
]
]
},
“Fetch RSS”: {
“main”: [
[
{
“node”: “Split Items”,
“type”: “main”,
“index”: 0
}
]
]
},
“Split Items”: {
“main”: [
[
{
“node”: “Check Duplicate”,
“type”: “main”,
“index”: 0
}
]
]
},
“Check Duplicate”: {
“main”: [
[
{
“node”: “IF New”,
“type”: “main”,
“index”: 0
}
]
]
},
“IF New”: {
“main”: [
[
{
“node”: “Get Article”,
“type”: “main”,
“index”: 0
}
]
]
},
“Append Sheet”: {
“main”: [
[
{
“node”: “Send Telegram”,
“type”: “main”,
“index”: 0
}
]
]
},
“Send Telegram”: {
“main”: [
[
{
“node”: “Wait”,
“type”: “main”,
“index”: 0
}
]
]
},
“Google Gemini Chat Model”: {
“ai_languageModel”: [
[
{
“node”: “AI Agent”,
“type”: “ai_languageModel”,
“index”: 0
}
]
]
},
“Wait”: {
“main”: [
[
{
“node”: “Send a text message”,
“type”: “main”,
“index”: 0
}
]
]
},
“Send a text message”: {
“main”: [

]
},
“AI Agent”: {
“main”: [
[
{
“node”: “Append Sheet”,
“type”: “main”,
“index”: 0
}
]
]
},
“Get Article”: {
“main”: [
[
{
“node”: “Simple Vector Store”,
“type”: “main”,
“index”: 0
}
]
]
},
“Simple Vector Store”: {
“main”: [
[
{
“node”: “Wait1”,
“type”: “main”,
“index”: 0
}
]
]
},
“Default Data Loader”: {
“ai_document”: [
[
{
“node”: “Simple Vector Store”,
“type”: “ai_document”,
“index”: 0
}
]
]
},
“Embeddings Google Gemini”: {
“ai_embedding”: [
[
{
“node”: “Simple Vector Store”,
“type”: “ai_embedding”,
“index”: 0
}
]
]
},
“Simple Vector Store1”: {
“ai_tool”: [
[
{
“node”: “AI Agent”,
“type”: “ai_tool”,
“index”: 0
}
]
]
},
“Embeddings Google Gemini1”: {
“ai_embedding”: [
[
{
“node”: “Simple Vector Store1”,
“type”: “ai_embedding”,
“index”: 0
}
]
]
},
“Wait1”: {
“main”: [
[
{
“node”: “AI Agent”,
“type”: “main”,
“index”: 0
}
]
]
}
},
“pinData”: {},
“meta”: {
“templateCredsSetupCompleted”: true,
“instanceId”: “ce0e513f732586fec848aca55a53d5f59f6c3dfc77a49c8756ef38d275aa794a”
}
} showing too many request

[Haian_Abou-Karam]

Try to use Local LLM, it’s free
See my new Tutorial:

---

Running a local LLM with LM Studio → n8n — fixed workflow (real case, step-by-step)

[Local_LLM_n8n_setup_troubleshooting] Introduction This guide shows how to connect a local LLM running in LM Studio to n8n (n8n inside Docker), how a common API mismatch looks in practice, and the simple correction that fixes it. It’s written as a zero-fluff, copy-paste friendly community post, including the exact debugging step that saved the day. One of the most significant benefits is that you can install free Local Language Models (LM) and make unlimited requests at zero cost, allowing han…

---