{ "meta": { "templateCredsSetupCompleted": true }, "nodes": [ { "id": "450b1757-d8d1-4eda-9ba8-8c3aedf9e1b3", "name": "Send a document", "type": "n8n-nodes-base.telegram", "position": [ 1120, 1120 ], "parameters": { "chatId": "123456789", "operation": "sendDocument", "binaryData": true, "additionalFields": {} }, "credentials": { "telegramApi": { "name": "" } }, "typeVersion": 1.2 }, { "id": "67914cf7-ac64-4da6-ba43-f899539721be", "name": "Structured Output Parser1", "type": "@n8n/n8n-nodes-langchain.outputParserStructured", "position": [ 480, 1152 ], "parameters": { "autoFix": true, "jsonSchemaExample": "{\n \"news_summary\": {\n \"headline\": \"string\",\n \"source_url\": \"string\",\n \"published_date\": \"string\",\n \"key_points\": \"string\",\n \"summary\": \"string\",\n \"extracted_images_url\": \"string\"\n }\n}\n" }, "typeVersion": 1.3 }, { "id": "8f10cdbc-761b-47c4-a9ca-e9c2453f4abb", "name": "VLM Agent2", "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi", "position": [ 368, 1056 ], "parameters": { "model": { "__rl": true, "mode": "id", "value": "=vlm-agent-1" }, "options": {} }, "credentials": { "openAiApi": { "name": "" } }, "typeVersion": 1.2 }, { "id": "aec1ecd0-f22e-4e2a-a083-c33bc9533e99", "name": "VLM Agent3", "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi", "position": [ 768, 1088 ], "parameters": { "model": { "__rl": true, "mode": "id", "value": "vlm-agent-1" }, "options": {} }, "credentials": { "openAiApi": { "name": "" } }, "typeVersion": 1.2 }, { "id": "95cd43fc-86ff-47bc-acce-910236b6da97", "name": "Split Out", "type": "n8n-nodes-base.splitOut", "position": [ 1152, 752 ], "parameters": { "options": {}, "fieldToSplitOut": "output.research_paper_summary.extracted_images_url" }, "typeVersion": 1 }, { "id": "fdc0c429-edd0-4457-8fac-c9bc0fb3b467", "name": "HTTP Request1", "type": "n8n-nodes-base.httpRequest", "position": [ 1168, 928 ], "parameters": { "url": "={{ $json['output.research_paper_summary.extracted_images_url'] }}", "options": {} }, "typeVersion": 4.2 }, { "id": "1e005ab8-0e64-4e6c-ad90-2da728df3529", "name": "No Operation, do nothing1", "type": "n8n-nodes-base.noOp", "position": [ 944, 1008 ], "parameters": {}, "typeVersion": 1 }, { "id": "e58f4e54-5dca-4d2f-8589-87212c422825", "name": "Embeddings OpenAI", "type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi", "position": [ 576, 1568 ], "parameters": { "options": {} }, "credentials": { "openAiApi": { "name": "" } }, "typeVersion": 1.2 }, { "id": "1caedd4b-5aa1-419d-b87d-604b912e8ab2", "name": "Default Data Loader", "type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader", "position": [ 1120, 1568 ], "parameters": { "options": {}, "dataType": "binary" }, "typeVersion": 1.1 }, { "id": "f812c98d-5fc0-48ff-9f48-5206e7ac3b32", "name": "Insert Data to Store", "type": "@n8n/n8n-nodes-langchain.vectorStoreInMemory", "position": [ 880, 1280 ], "parameters": { "mode": "insert", "memoryKey": { "__rl": true, "mode": "list", "value": "vector_store_key", "cachedResultName": "vector_store_key" } }, "typeVersion": 1.2 }, { "id": "13d1d33d-ccad-4ca3-be6a-d3e8e6772f29", "name": "Query Data Tool", "type": "@n8n/n8n-nodes-langchain.vectorStoreInMemory", "position": [ 288, 1632 ], "parameters": { "mode": "retrieve-as-tool", "toolName": "knowledge_base", "memoryKey": { "__rl": true, "mode": "list", "value": "vector_store_key" }, "toolDescription": "Use this knowledge base to answer questions from the user" }, "typeVersion": 1.2 }, { "id": "e8174bcc-08be-447e-96ce-72c1fcee74a9", "name": "AI Agent", "type": "@n8n/n8n-nodes-langchain.agent", "position": [ 192, 1408 ], "parameters": { "text": "={{ $json.message.text }}", "options": {}, "promptType": "define", "hasOutputParser": true }, "typeVersion": 2 }, { "id": "a6ec2ab2-2478-4103-a615-aee03deacaa9", "name": "Sticky Note2", "type": "n8n-nodes-base.stickyNote", "position": [ -80, 1248 ], "parameters": { "color": 7, "width": 584, "height": 508, "content": "\n\n\n\n## Chat with LLM\n\nAsk anything and get answer in telegram about \nprovided newspaper link" }, "typeVersion": 1 }, { "id": "fabb3694-03c3-4a0e-96fb-e31d71b05928", "name": "Sticky Note3", "type": "n8n-nodes-base.stickyNote", "position": [ 720, 1520 ], "parameters": { "color": 4, "width": 320, "height": 240, "content": "### Embeddings\n\nThe Insert and Retrieve operation use the same embedding node.\n\nThis is to ensure that they are using the **exact same embeddings and settings**.\n\nDifferent embeddings might not work at all, or have unintended consequences.\n" }, "typeVersion": 1 }, { "id": "dd6bf692-7902-4691-9832-65e3bb9354c6", "name": "Code", "type": "n8n-nodes-base.code", "position": [ -48, 1040 ], "parameters": { "jsCode": "const results = [];\n\nfor (const item of $input.all()) {\n const url = item.json.URL_PARSE; // Input URL field\n\n try {\n // Fetch the raw HTML content\n const html = await this.helpers.httpRequest({\n method: 'GET',\n url,\n headers: {\n 'User-Agent': 'Mozilla/5.0',\n },\n });\n\n // --- Extract title ---\n const titleMatch = html.match(/(.*?)<\\/title>/i);\n const title = titleMatch ? titleMatch[1].trim() : null;\n\n // --- Extract meta description ---\n const descMatch = html.match(/<meta\\s+name=[\"']description[\"']\\s+content=[\"']([^\"']+)[\"']/i);\n const description = descMatch ? descMatch[1].trim() : null;\n\n // --- Extract all paragraphs (<p>...</p>) ---\n const paragraphs = [];\n const pRegex = /<p[^>]*>(.*?)<\\/p>/gi;\n let match;\n while ((match = pRegex.exec(html)) !== null) {\n // Remove all HTML tags from paragraph text\n const cleanText = match[1].replace(/<[^>]+>/g, '').trim();\n if (cleanText) paragraphs.push(cleanText);\n }\n const text = paragraphs.join('\\n\\n');\n\n // --- Extract all <img> URLs ---\n const images = [];\n const imgRegex = /<img[^>]+src=[\"']([^\"']+)[\"']/gi;\n let imgMatch;\n while ((imgMatch = imgRegex.exec(html)) !== null) {\n images.push(imgMatch[1]);\n }\n\n // --- Extract Open Graph metadata ---\n const ogTitleMatch = html.match(/<meta property=[\"']og:title[\"'] content=[\"']([^\"']+)[\"']/i);\n const ogImageMatch = html.match(/<meta property=[\"']og:image[\"'] content=[\"']([^\"']+)[\"']/i);\n const ogTitle = ogTitleMatch ? ogTitleMatch[1] : null;\n const ogImage = ogImageMatch ? ogImageMatch[1] : null;\n\n // --- Short summary (first 3 paragraphs) ---\n const summary = paragraphs.slice(0, 3).join('\\n\\n');\n\n // --- Add all extracted data to original item ---\n item.json.source_url = url;\n item.json.title = title;\n item.json.description = description;\n item.json.text = text;\n item.json.images = images;\n item.json.summary = summary;\n\n } catch (error) {\n // --- Handle errors ---\n item.json.source_url = url;\n item.json.title = null;\n item.json.description = null;\n item.json.text = null;\n item.json.images = [];\n item.json.summary = null;\n }\n\n results.push(item);\n}\n\n// Return updated items for downstream nodes\nreturn results;\n" }, "typeVersion": 2 }, { "id": "b2eacd7c-ff24-4daa-8bf7-f51270914b0e", "name": "Sticky Note", "type": "n8n-nodes-base.stickyNote", "position": [ -656, 1248 ], "parameters": { "width": 576, "height": 640, "content": "\n1. **Telegram Trigger Node** \n - Listens for incoming messages from a Telegram bot.\n - Captures the message text.\n\n2. **Link Detection** \n - The workflow checks the message for any valid HTTP/HTTPS URLs.\n\n3. **Scraping Node (Function Node)** \n - When a link is detected, the URL is passed to the scraping node.\n - The node fetches the webpage, extracts:\n - Page title\n - Meta description\n - All paragraph text\n - Images\n - Open Graph metadata\n - Short summary (first 3 paragraphs)\n\n4. **Output** \n - The extracted data is stored in JSON format.\n - Can be sent back to Telegram, stored in a database, or used in other workflows.\n\n" }, "typeVersion": 1 }, { "id": "20955189-44a2-45e6-bf8d-638ff043a849", "name": "Check Whether URL", "type": "n8n-nodes-base.if", "position": [ -416, 1712 ], "parameters": { "options": {}, "conditions": { "options": { "version": 2, "leftValue": "", "caseSensitive": true, "typeValidation": "loose" }, "combinator": "and", "conditions": [ { "id": "405c9d7c-b745-4a57-9123-3d19af7def77", "operator": { "type": "boolean", "operation": "true", "singleValue": true }, "leftValue": "={{ $json.message.link_preview_options.url }}", "rightValue": "https" } ] }, "looseTypeValidation": true }, "typeVersion": 2.2 }, { "id": "4b29201d-3dd3-4539-9d77-8fad7bc2df30", "name": "Listen to Telegram for Link", "type": "n8n-nodes-base.telegramTrigger", "position": [ -880, 1712 ], "parameters": { "updates": [ "message" ], "additionalFields": { "chatIds": "123456789" } }, "credentials": { "telegramApi": { "name": "<your credential>" } }, "typeVersion": 1.2 }, { "id": "78878d14-d80d-4cc1-946b-0e2f5d2e25d4", "name": "Rename Link Field", "type": "n8n-nodes-base.set", "position": [ -208, 1744 ], "parameters": { "options": {}, "assignments": { "assignments": [ { "id": "5a6f8e47-e620-44cf-a004-66310ad8f158", "name": "URL_PARSE", "type": "string", "value": "={{ $json.message.link_preview_options.url }}" } ] } }, "typeVersion": 3.4 }, { "id": "88dda24f-69ad-425f-ba93-b7df42312bf9", "name": "Sticky Note1", "type": "n8n-nodes-base.stickyNote", "position": [ -160, 608 ], "parameters": { "color": 4, "width": 512, "height": 640, "content": "# Web Page Scraper\n\n## Input\n- Expects `URL_PARSE` containing a valid HTTP/HTTPS URL.\n\n## Processing\n1. Fetches the page HTML using n8n\u2019s `httpRequest`.\n2. Extracts:\n - Page `<title>` and meta description\n - All paragraph text\n - `<img>` URLs\n - Open Graph title & image\n3. Generates a short summary (first 3 paragraphs).\n4. Handles errors by recording messages and keeping other fields empty.\n" }, "typeVersion": 1 }, { "id": "7ec330a3-8a34-44d7-8d3a-1e6f2ef57b22", "name": "VLM Run Highlighter", "type": "@n8n/n8n-nodes-langchain.agent", "onError": "continueErrorOutput", "position": [ 544, 848 ], "parameters": { "text": "=Generate and give explanation of important parts of the following newspaper daily- {{$json.source_url + $json.title + $json.description + $json.text + $json.images + $json.summary}}. Highlight important news, and provide correct complete urls for news image downloading. If correct complete urls not found leave blank- \"\". Give result according to JSON schema.", "options": {}, "promptType": "define", "hasOutputParser": true }, "typeVersion": 1.7 }, { "id": "b0330b9d-bddc-4a41-8ee4-9ae31c008fe4", "name": "Sticky Note4", "type": "n8n-nodes-base.stickyNote", "position": [ 352, 624 ], "parameters": { "color": 5, "width": 512, "height": 624, "content": "# Daily Newspaper Summarizer\n\n## Processing\n1. Analyze text \u2192 generate summary and highlight important news.\n2. Extract images \u2192 generate presigned URLs.\n3. Output JSON schema:\n - `summary`\n - `important_news`\n - `images`" }, "typeVersion": 1 }, { "id": "81ea8e52-b29e-49e3-8ac6-3cd9fb3594cb", "name": "Check URLs Validity", "type": "n8n-nodes-base.if", "position": [ 928, 768 ], "parameters": { "options": {}, "conditions": { "options": { "version": 2, "leftValue": "", "caseSensitive": true, "typeValidation": "loose" }, "combinator": "and", "conditions": [ { "id": "5a38f01f-075d-4d2f-a1b4-94503a993ad5", "operator": { "type": "boolean", "operation": "true", "singleValue": true }, "leftValue": "={{ $json.output.news_summary.extracted_images_url }}", "rightValue": "=\"\"" } ] }, "looseTypeValidation": true }, "typeVersion": 2.2 }, { "id": "00425b38-d2fd-4c5b-aed7-3df8b1e02d1e", "name": "Covert to Text File", "type": "n8n-nodes-base.convertToFile", "position": [ 1296, 1312 ], "parameters": { "options": {}, "operation": "toText", "sourceProperty": "output" }, "typeVersion": 1.1 }, { "id": "14d5ab95-3f79-4eaa-8cc0-5c924a6a79ec", "name": "Sticky Note5", "type": "n8n-nodes-base.stickyNote", "position": [ 864, 512 ], "parameters": { "color": 3, "width": 544, "height": 736, "content": "# Telegram Notifier\n\n\n## How it Works\n1. Extract URLs and split them.\n2. Download images, make document containing news highlights and send as Telegram files.\n\n" }, "typeVersion": 1 }, { "id": "3b0760e0-c63f-4f40-baa3-9aa1dae71382", "name": "Sticky Note9", "type": "n8n-nodes-base.stickyNote", "position": [ 512, 1248 ], "parameters": { "color": 6, "width": 896, "height": 224, "content": "## Store Highlight Report \n## Embedding\n\nConvert highlight summary file \ninto embedding to strore in vector database" }, "typeVersion": 1 }, { "id": "0e063212-ab90-4a78-9eb7-aed52a7e6910", "name": "OpenAI Chat Model", "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi", "position": [ 144, 1632 ], "parameters": { "model": { "__rl": true, "mode": "list", "value": "gpt-4.1-nano", "cachedResultName": "gpt-4.1-nano" }, "options": {} }, "credentials": { "openAiApi": { "name": "<your credential>" } }, "typeVersion": 1.2 }, { "id": "6bdcf79b-0d02-49db-88fc-049cb4ebbeab", "name": "Send a Reply", "type": "n8n-nodes-base.telegram", "position": [ -32, 1616 ], "parameters": { "text": "={{ $json.output }}", "chatId": "123456789", "additionalFields": {} }, "credentials": { "telegramApi": { "name": "<your credential>" } }, "typeVersion": 1.2 }, { "id": "277945f2-897e-4b0a-8972-0f3654c57fed", "name": "Start Asking", "type": "n8n-nodes-base.telegram", "position": [ 1280, 1120 ], "parameters": { "text": "=Start asking about provided link now", "chatId": "123456789", "forceReply": {}, "replyMarkup": "forceReply", "additionalFields": {} }, "credentials": { "telegramApi": { "name": "<your credential>" } }, "typeVersion": 1.2 }, { "id": "3657f4e8-3134-4c34-ba3c-9e6ac01f2fa4", "name": "Sticky Note6", "type": "n8n-nodes-base.stickyNote", "position": [ -656, 400 ], "parameters": { "color": 6, "width": 496, "height": 848, "content": "# \ud83d\udcf0 Newspaper Agent\n\n## Overview\n- The Newspaper Agent workflow automates the process of analyzing and summarizing online news articles directly within **n8n**. \n- It listens for shared links from Telegram, scrapes the article content, summarizes it using a **Vision-Language Model (VLM)**, sends structured highlights and related images back to Telegram, and stores the summarized data for later conversational queries. User can chat and explore information from newspaper.\n\n## How It Works\n- The workflow starts when a user sends a newspaper link through **Telegram**. \n- It then:\n 1. **Validates the URL** and scrapes article text, metadata, and images. \n 2. **Sends content to VLM Run**, which generates structured highlights (headline, key points, summary, and extracted images). \n 3. **Downloads and validates** the extracted image URLs. \n 4. **Sends the summarized report** back to the user on Telegram. \n 5. **Embeds the processed text** into a vector store for semantic Q&A using OpenAI embe\n\n## Requirements\n- **Telegram Bot Credentials** \u2014 For listening to incoming messages and sending replies. \n- **VLM Run API Credentials** \u2014 Used for generating structured video-language summaries. \n- **OpenAI API Key** \u2014 For creating text embeddings and interactive Q&A. \n- **Google Drive OAuth2 (Optional)** \u2014 If you want to store or share extracted summaries or images externally. \n- **HTTP Request Permissions** \u2014 To scrape content and download images from provided URLs. \n" }, "typeVersion": 1 } ], "connections": { "Code": { "main": [ [ { "node": "VLM Run Highlighter", "type": "main", "index": 0 } ] ] }, "AI Agent": { "main": [ [ { "node": "Send a Reply", "type": "main", "index": 0 } ] ] }, "Split Out": { "main": [ [ { "node": "HTTP Request1", "type": "main", "index": 0 } ] ] }, "VLM Agent2": { "ai_languageModel": [ [ { "node": "VLM Run Highlighter", "type": "ai_languageModel", "index": 0 } ] ] }, "VLM Agent3": { "ai_languageModel": [ [ { "node": "Structured Output Parser1", "type": "ai_languageModel", "index": 0 } ] ] }, "Start Asking": { "main": [ [] ] }, "HTTP Request1": { "main": [ [ { "node": "Send a document", "type": "main", "index": 0 } ] ] }, "Query Data Tool": { "ai_tool": [ [ { "node": "AI Agent", "type": "ai_tool", "index": 0 } ] ] }, "Send a document": { "main": [ [ { "node": "Start Asking", "type": "main", "index": 0 } ] ] }, "Check Whether URL": { "main": [ [ { "node": "Rename Link Field", "type": "main", "index": 0 } ], [ { "node": "AI Agent", "type": "main", "index": 0 } ] ] }, "Embeddings OpenAI": { "ai_embedding": [ [ { "node": "Insert Data to Store", "type": "ai_embedding", "index": 0 }, { "node": "Query Data Tool", "type": "ai_embedding", "index": 0 } ] ] }, "OpenAI Chat Model": { "ai_languageModel": [ [ { "node": "AI Agent", "type": "ai_languageModel", "index": 0 } ] ] }, "Rename Link Field": { "main": [ [ { "node": "Code", "type": "main", "index": 0 } ] ] }, "Check URLs Validity": { "main": [ [ { "node": "Split Out", "type": "main", "index": 0 } ], [ { "node": "No Operation, do nothing1", "type": "main", "index": 0 } ] ] }, "Covert to Text File": { "main": [ [ { "node": "Send a document", "type": "main", "index": 0 }, { "node": "Insert Data to Store", "type": "main", "index": 0 } ] ] }, "Default Data Loader": { "ai_document": [ [ { "node": "Insert Data to Store", "type": "ai_document", "index": 0 } ] ] }, "VLM Run Highlighter": { "main": [ [ { "node": "Covert to Text File", "type": "main", "index": 0 }, { "node": "Check URLs Validity", "type": "main", "index": 0 } ], [ { "node": "VLM Run Highlighter", "type": "main", "index": 0 } ] ] }, "Structured Output Parser1": { "ai_outputParser": [ [ { "node": "VLM Run Highlighter", "type": "ai_outputParser", "index": 0 } ] ] }, "Listen to Telegram for Link": { "main": [ [ { "node": "Check Whether URL", "type": "main", "index": 0 } ] ] } } }