Hugging Face to Notion
Automate the discovery and summarization of new research papers from Hugging Face and store them directly in your Notion database. This powerful workflow leverages a scheduled trigger to periodically request the latest papers from Hugging Face, intelligently extracts key details like the paper URL and abstract using HTML parsing, and then checks your Notion database to prevent duplicate entries. For new papers, it fetches the full paper details and uses OpenAI to analyze and summarize the abstract, before finally storing all relevant information, including the OpenAI-generated summary, into your Notion workspace. This workflow is ideal for researchers, academics, or anyone needing to stay current with the latest AI and machine learning advancements without manually sifting through new publications. It saves significant time and effort by automating the entire research discovery, summarization, and organization process, ensuring you have a curated, up-to-date repository of relevant papers readily available in Notion.
Workflow JSON
{"id": "FU3MrLkaTHmfdG4n", "meta": {"instanceId": "3294023dd650d95df294922b9d55d174ef26f4a2e6cce97c8a4ab5f98f5b8c7b", "templateCredsSetupCompleted": true}, "name": "Hugging Face to Notion", "tags": [], "nodes": [{"id": "32d5bfee-97f1-4e92-b62e-d09bdd9c3821", "name": "Schedule Trigger", "type": "n8n-nodes-base.scheduleTrigger", "position": [-2640, -300], "parameters": {"rule": {"interval": [{"field": "weeks", "triggerAtDay": [1, 2, 3, 4, 5], "triggerAtHour": 8}]}}, "typeVersion": 1.2}, {"id": "b1f4078e-ac77-47ec-995c-f52fd98fafef", "name": "If", "type": "n8n-nodes-base.if", "position": [-1360, -280], "parameters": {"options": {}, "conditions": {"options": {"version": 2, "leftValue": "", "caseSensitive": true, "typeValidation": "strict"}, "combinator": "and", "conditions": [{"id": "7094d6db-1fa7-4b59-91cf-6bbd5b5f067e", "operator": {"type": "object", "operation": "empty", "singleValue": true}, "leftValue": "={{ $json }}", "rightValue": ""}]}}, "typeVersion": 2.2}, {"id": "afac08e1-b629-4467-86ef-907e4a5e8841", "name": "Loop Over Items", "type": "n8n-nodes-base.splitInBatches", "position": [-1760, -300], "parameters": {"options": {"reset": false}}, "typeVersion": 3}, {"id": "807ba450-9c89-4f88-aa84-91f43e3adfc6", "name": "Split Out", "type": "n8n-nodes-base.splitOut", "position": [-1960, -300], "parameters": {"options": {}, "fieldToSplitOut": "url, url"}, "typeVersion": 1}, {"id": "08dd3f15-2030-48f2-ab0f-f85f797268e1", "name": "Request Hugging Face Paper", "type": "n8n-nodes-base.httpRequest", "position": [-2440, -300], "parameters": {"url": "https://huggingface.co/papers", "options": {}, "sendQuery": true, "queryParameters": {"parameters": [{"name": "date", "value": "={{ $now.minus(1,'days').format('yyyy-MM-dd') }}"}]}}, "typeVersion": 4.2}, {"id": "f37ba769-d881-4aad-927d-ca1f4a68b9a1", "name": "Extract Hugging Face Paper", "type": "n8n-nodes-base.html", "position": [-2200, -300], "parameters": {"options": {}, "operation": "extractHtmlContent", "extractionValues": {"values": [{"key": "url", "attribute": "href", "cssSelector": ".line-clamp-3", "returnArray": true, "returnValue": "attribute"}]}}, "typeVersion": 1.2}, {"id": "94ba99bf-a33b-4311-a4e6-86490e1bb9ad", "name": "Check Paper URL Existed", "type": "n8n-nodes-base.notion", "position": [-1540, -280], "parameters": {"filters": {"conditions": [{"key": "URL|url", "urlValue": "={{ 'https://huggingface.co'+$json.url }}", "condition": "equals"}]}, "options": {}, "resource": "databasePage", "operation": "getAll", "databaseId": {"__rl": true, "mode": "list", "value": "17b67aba-1fcc-80ae-baa1-d88ffda7ae83", "cachedResultUrl": "https://www.notion.so/17b67aba1fcc80aebaa1d88ffda7ae83", "cachedResultName": "huggingface-abstract"}, "filterType": "manual"}, "credentials": {"notionApi": {"id": "", "name": "[Your notionApi]"}}, "typeVersion": 2.2, "alwaysOutputData": true}, {"id": "ece8dee2-e444-4557-aad9-5bdcb5ecd756", "name": "Request Hugging Face Paper Detail", "type": "n8n-nodes-base.httpRequest", "position": [-1080, -300], "parameters": {"url": "={{ 'https://huggingface.co'+$('Split Out').item.json.url }}", "options": {}}, "typeVersion": 4.2}, {"id": "53b266fe-e7c4-4820-92eb-78a6ba7a6430", "name": "OpenAI Analysis Abstract", "type": "@n8n/n8n-nodes-langchain.openAi", "position": [-640, -300], "parameters": {"modelId": {"__rl": true, "mode": "list", "value": "gpt-4o-2024-11-20", "cachedResultName": "GPT-4O-2024-11-20"}, "options": {}, "messages": {"values": [{"role": "system", "content": "Extract the following key details from the paper abstract:\n\nCore Introduction: Summarize the main contributions and objectives of the paper, highlighting its innovations and significance.\nKeyword Extraction: List 2-5 keywords that best represent the research direction and techniques of the paper.\nKey Data and Results: Extract important performance metrics, comparison results, and the paper's advantages over other studies.\nTechnical Details: Provide a brief overview of the methods, optimization techniques, and datasets mentioned in the paper.\nClassification: Assign an appropriate academic classification based on the content of the paper.\n\n\nOutput as json\uff1a\n{\n \"Core_Introduction\": \"PaSa is an advanced Paper Search agent powered by large language models that can autonomously perform a series of decisions (including invoking search tools, reading papers, and selecting relevant references) to provide comprehensive and accurate results for complex academic queries.\",\n \"Keywords\": [\n \"Paper Search Agent\",\n \"Large Language Models\",\n \"Reinforcement Learning\",\n \"Academic Queries\",\n \"Performance Benchmarking\"\n ],\n \"Data_and_Results\": \"PaSa outperforms existing baselines (such as Google, GPT-4, chatGPT) in tests using AutoScholarQuery (35k academic queries) and RealScholarQuery (real-world academic queries). For example, PaSa-7B exceeds Google with GPT-4o by 37.78% in recall@20 and 39.90% in recall@50.\",\n \"Technical_Details\": \"PaSa is optimized using reinforcement learning with the AutoScholarQuery synthetic dataset, demonstrating superior performance in multiple benchmarks.\",\n \"Classification\": [\n \"Artificial Intelligence (AI)\",\n \"Academic Search and Information Retrieval\",\n \"Natural Language Processing (NLP)\",\n \"Reinforcement Learning\"\n ]\n}\n```"}, {"content": "={{ $json.abstract }}"}]}, "jsonOutput": true}, "credentials": {"openAiApi": {"id": "", "name": "[Your openAiApi]"}}, "typeVersion": 1.8}, {"id": "f491cd7f-598e-46fd-b80c-04cfa9766dfd", "name": "Store Abstract Notion", "type": "n8n-nodes-base.notion", "position": [-300, -300], "parameters": {"options": {}, "resource": "databasePage", "databaseId": {"__rl": true, "mode": "list", "value": "17b67aba-1fcc-80ae-baa1-d88ffda7ae83", "cachedResultUrl": "https://www.notion.so/17b67aba1fcc80aebaa1d88ffda7ae83", "cachedResultName": "huggingface-abstract"}, "propertiesUi": {"propertyValues": [{"key": "URL|url", "urlValue": "={{ 'https://huggingface.co'+$('Split Out').item.json.url }}"}, {"key": "title|title", "title": "={{ $('Extract Hugging Face Paper Abstract').item.json.title }}"}, {"key": "abstract|rich_text", "textContent": "={{ $('Extract Hugging Face Paper Abstract').item.json.abstract.substring(0,2000) }}"}, {"key": "scrap-date|date", "date": "={{ $today.format('yyyy-MM-dd') }}", "includeTime": false}, {"key": "Classification|rich_text", "textContent": "={{ $json.message.content.Classification.join(',') }}"}, {"key": "Technical_Details|rich_text", "textContent": "={{ $json.message.content.Technical_Details }}"}, {"key": "Data_and_Results|rich_text", "textContent": "={{ $json.message.content.Data_and_Results }}"}, {"key": "keywords|rich_text", "textContent": "={{ $json.message.content.Keywords.join(',') }}"}, {"key": "Core Introduction|rich_text", "textContent": "={{ $json.message.content.Core_Introduction }}"}]}}, "credentials": {"notionApi": {"id": "", "name": "[Your notionApi]"}}, "typeVersion": 2.2}, {"id": "d5816a1c-d1fa-4be2-8088-57fbf68e6b43", "name": "Extract Hugging Face Paper Abstract", "type": "n8n-nodes-base.html", "position": [-840, -300], "parameters": {"options": {}, "operation": "extractHtmlContent", "extractionValues": {"values": [{"key": "abstract", "cssSelector": ".text-gray-700"}, {"key": "title", "cssSelector": ".text-2xl"}]}}, "typeVersion": 1.2}], "active": true, "pinData": {}, "settings": {"executionOrder": "v1"}, "versionId": "4b0ec2a3-253d-46d5-a4d4-1d9ff21ba4a3", "connections": {"If": {"main": [[{"node": "Request Hugging Face Paper Detail", "type": "main", "index": 0}], [{"node": "Loop Over Items", "type": "main", "index": 0}]]}, "Split Out": {"main": [[{"node": "Loop Over Items", "type": "main", "index": 0}]]}, "Loop Over Items": {"main": [[], [{"node": "Check Paper URL Existed", "type": "main", "index": 0}]]}, "Schedule Trigger": {"main": [[{"node": "Request Hugging Face Paper", "type": "main", "index": 0}]]}, "Store Abstract Notion": {"main": [[{"node": "Loop Over Items", "type": "main", "index": 0}]]}, "Check Paper URL Existed": {"main": [[{"node": "If", "type": "main", "index": 0}]]}, "OpenAI Analysis Abstract": {"main": [[{"node": "Store Abstract Notion", "type": "main", "index": 0}]]}, "Extract Hugging Face Paper": {"main": [[{"node": "Split Out", "type": "main", "index": 0}]]}, "Request Hugging Face Paper": {"main": [[{"node": "Extract Hugging Face Paper", "type": "main", "index": 0}]]}, "Request Hugging Face Paper Detail": {"main": [[{"node": "Extract Hugging Face Paper Abstract", "type": "main", "index": 0}]]}, "Extract Hugging Face Paper Abstract": {"main": [[{"node": "OpenAI Analysis Abstract", "type": "main", "index": 0}]]}}}How to Import This Workflow
- 1Copy the workflow JSON above using the Copy Workflow JSON button.
- 2Open your n8n instance and go to Workflows.
- 3Click Import from JSON and paste the copied workflow.
Don't have an n8n instance? Start your free trial at n8nautomation.cloud
Related Templates
Auto-create TikTok videos with VEED.io AI avatars, ElevenLabs & GPT-4
Automate the creation and distribution of trending TikTok videos using AI avatars. This workflow connects Telegram, Perplexity, OpenAI, ElevenLabs, VEED.io, and BLOTATO to generate scripts, synthesize voice, create video, and publish across multiple social platforms. Content creators and marketers can rapidly produce engaging short-form video content without manual editing.
Automate LinkedIn Posts with AI
Automate your LinkedIn content creation and publishing by leveraging AI with this powerful workflow. This n8n automation connects LinkedIn, OpenAI, and Notion to streamline your social media presence. A Schedule Trigger initiates the process daily, querying your Notion database for today's scheduled posts. For each post, the workflow fetches all content from its Notion page, including text blocks and an image URL, then uses OpenAI to reformat the post text for optimal engagement. The workflow then combines the rephrased text and fetched image, publishing the complete post directly to LinkedIn. Finally, it updates the post's status in Notion to "Done," ensuring your content calendar remains accurate. This workflow is ideal for content creators, marketers, and businesses looking to maintain a consistent and engaging LinkedIn presence without manual effort, saving significant time on content preparation and publishing while ensuring high-quality, AI-enhanced posts.
Customer Support Channel and Ticketing System with Slack and Linear
Automate your customer support channel and ticketing system by efficiently managing incoming requests from Slack and creating structured tickets in Linear. This workflow connects Slack to capture customer inquiries, then leverages OpenAI's AI capabilities to understand and categorize these requests. It regularly polls Slack for new messages in a designated support channel using a Schedule Trigger, extracts key information, and checks Linear to see if similar issues already exist. If a new, unique issue is identified, the workflow uses OpenAI's language model to generate a comprehensive ticket description and then creates a new ticket in Linear, ensuring all relevant details are captured. This automation is ideal for customer support teams, product managers, and operations personnel who need to streamline their issue tracking, reduce manual data entry, and ensure no customer request falls through the cracks. It significantly reduces the time spent on triaging and creating support tickets, allowing teams to focus more on resolving customer issues rather than administrative tasks, ultimately improving response times and customer satisfaction.