Notion knowledge base AI assistant
Empower your team to instantly access information from your Notion knowledge base using an AI assistant. This workflow connects OpenAI's advanced language models with your Notion databases, allowing users to query your internal documentation through a chat interface. When a chat message is received, the workflow first retrieves details about your Notion databases, then an AI Agent processes the user's query, leveraging a window buffer memory to maintain context and intelligently search for relevant information within your Notion records. This eliminates the need for manual searching, providing immediate answers to common questions about company policies, project details, or product specifications, significantly reducing support time and improving team efficiency by making your knowledge base truly conversational and accessible.
Workflow JSON
{"meta": {"instanceId": "205b3bc06c96f2dc835b4f00e1cbf9a937a74eeb3b47c99d0c30b0586dbf85aa"}, "nodes": [{"id": "d1d4291e-fa37-43d0-81e0-f0a594371426", "name": "OpenAI Chat Model", "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi", "position": [680, 620], "parameters": {"model": "gpt-4o", "options": {"timeout": 25000, "temperature": 0.7}}, "credentials": {"openAiApi": {"id": "", "name": "[Your openAiApi]"}}, "typeVersion": 1}, {"id": "68e6805b-9c19-4c9e-a300-8983f2b7c28a", "name": "Search notion database", "type": "@n8n/n8n-nodes-langchain.toolHttpRequest", "position": [980, 620], "parameters": {"url": "=https://api.notion.com/v1/databases/{{ $json.notionID }}/query", "method": "POST", "jsonBody": "{\n \"filter\": {\n \"or\": [\n {\n \"property\": \"question\",\n \"rich_text\": {\n \"contains\": \"{keyword}\"\n }\n },\n {\n \"property\": \"tags\",\n \"multi_select\": {\n \"contains\": \"{tag}\"\n }\n }\n ]\n },\n \"sorts\": [\n {\n \"property\": \"updated_at\",\n \"direction\": \"ascending\"\n }\n ]\n}", "sendBody": true, "specifyBody": "json", "authentication": "predefinedCredentialType", "toolDescription": "=Use this tool to search the \"\" Notion app database.\n\nIt is structured with question and answer format. \nYou can filter query result by:\n- By keyword\n- filter by tag.\n\nKeyword and Tag have an OR relationship not AND.\n\n", "nodeCredentialType": "notionApi", "placeholderDefinitions": {"values": [{"name": "keyword", "description": "Searches question of the record. Use one keyword at a time."}, {"name": "tag", "description": "=Options: {{ $json.tagsOptions }}"}]}}, "credentials": {"notionApi": {"id": "", "name": "[Your notionApi]"}}, "typeVersion": 1.1}, {"id": "c3164d38-a9fb-4ee3-b6bd-fccb4aa5a1a4", "name": "Get database details", "type": "n8n-nodes-base.notion", "position": [420, 380], "parameters": {"simple": false, "resource": "database", "databaseId": {"__rl": true, "mode": "list", "value": "7ea9697d-4875-441e-b262-1105337d232e", "cachedResultUrl": "https://www.notion.so/7ea9697d4875441eb2621105337d232e", "cachedResultName": "StarLens Company Knowledge Base"}}, "credentials": {"notionApi": {"id": "", "name": "[Your notionApi]"}}, "typeVersion": 2.2}, {"id": "98300243-efcc-4427-88da-c1af8a91ddae", "name": "Window Buffer Memory", "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow", "position": [820, 620], "parameters": {"contextWindowLength": 4}, "typeVersion": 1.2}, {"id": "a8473f48-1343-4eb2-8e48-ec89377a2a00", "name": "Search inside database record", "type": "@n8n/n8n-nodes-langchain.toolHttpRequest", "notes": " ", "position": [1140, 620], "parameters": {"url": "https://api.notion.com/v1/blocks/{page_id}/children", "fields": "id, type, paragraph.text, heading_1.text, heading_2.text, heading_3.text, bulleted_list_item.text, numbered_list_item.text, to_do.text, children", "dataField": "results", "authentication": "predefinedCredentialType", "fieldsToInclude": "selected", "toolDescription": "=Use this tool to retrieve Notion page content using the page ID. \n\nIt is structured with question and answer format. \nYou can filter query result by:\n- By keyword\n- filter by tag.\n\nKeyword and Tag have an OR relationship not AND.\n\n", "optimizeResponse": true, "nodeCredentialType": "notionApi", "placeholderDefinitions": {"values": [{"name": "page_id", "description": "Notion page id from 'Search notion database' tool results"}]}}, "credentials": {"notionApi": {"id": "", "name": "[Your notionApi]"}}, "notesInFlow": true, "typeVersion": 1.1}, {"id": "115c328e-84b0-43d2-8df7-8b3f74cbb2fb", "name": "Format schema", "type": "n8n-nodes-base.set", "position": [620, 380], "parameters": {"options": {}, "assignments": {"assignments": [{"id": "a8e58791-ba51-46a2-8645-386dd1a0ff6e", "name": "sessionId", "type": "string", "value": "={{ $('When chat message received').item.json.sessionId }}"}, {"id": "434209de-39d5-43d8-a964-0fcb7396306c", "name": "action", "type": "string", "value": "={{ $('When chat message received').item.json.action }}"}, {"id": "cad4c972-51a9-4e16-a627-b00eea77eb30", "name": "chatInput", "type": "string", "value": "={{ $('When chat message received').item.json.chatInput }}"}, {"id": "8e88876c-2714-494d-bd5e-5e80c99f83e3", "name": "notionID", "type": "string", "value": "={{ $('Get database details').item.json.id }}"}, {"id": "a88a15f6-317c-4d2e-9d64-26f5ccaf7a97", "name": "databaseName", "type": "string", "value": "={{ $json.title[0].text.content }}"}, {"id": "7c3bf758-8ed3-469a-8695-6777f4af4fb9", "name": "tagsOptions", "type": "string", "value": "={{ $json.properties.tags.multi_select.options.map(item => item.name).join(',') }}"}]}}, "typeVersion": 3.4}, {"id": "3b82f4fe-6c0c-4e6e-a387-27de31fec758", "name": "Sticky Note", "type": "n8n-nodes-base.stickyNote", "position": [-340, 240], "parameters": {"color": 6, "width": 462.3561535890252, "height": 95.12709218477178, "content": "## Notion knowledge base assistant [v1]\nBuilt as part of the [30 Day AI Sprint](https://30dayaisprint.notion.site/) by [@maxtkacz](https://x.com/maxtkacz)\n"}, "typeVersion": 1}, {"id": "31debc55-6608-4e64-be18-1bc0fc0fbf16", "name": "Sticky Note1", "type": "n8n-nodes-base.stickyNote", "position": [-340, 1060], "parameters": {"color": 7, "width": 462.3561535890252, "height": 172.4760209818479, "content": "### FAQ\n- In `Get database details` if you see a `The resource you are requesting could not be found` error, you need to add your connection to the database (in the Notion app).\n- The `Get database details` pulls most recent `Tags` and informs AI Agent of them. However this step adds ~250-800ms per run. Watch detailed video to see how to remove this step. "}, "typeVersion": 1}, {"id": "9f48e548-f032-477c-960d-9c99d61443df", "name": "AI Agent", "type": "@n8n/n8n-nodes-langchain.agent", "position": [820, 380], "parameters": {"text": "={{ $json.chatInput }}", "options": {"systemMessage": "=# Role:\nYou are a helpful agent. Query the \"{{ $json.databaseName }}\" Notion database to find relevant records or summarize insights based on multiple records.\n\n# Behavior:\n\nBe clear, very concise, efficient, and accurate in responses. Do not hallucinate.\nIf the request is ambiguous, ask for clarification. Do not embellish, only use facts from the Notion records. Do not offer general advice.\n\n# Error Handling:\n\nIf no matching records are found, try alternative search criteria. Example 1: Laptop, then Computer, then Equipment. Example 2: meetings, then meeting.\nClearly explain any issues with queries (e.g., missing fields or unsupported filters).\n\n# Output:\n\nReturn concise, user-friendly results or summaries.\nFor large sets, show top results by default and offer more if needed. Output URLs in markdown format. \n\nWhen a record has the answer to user question, always output the URL to that page. Do not output links twice."}, "promptType": "define"}, "typeVersion": 1.6}, {"id": "f1274a12-128c-4549-a19b-6bfc3beccd89", "name": "When chat message received", "type": "@n8n/n8n-nodes-langchain.chatTrigger", "position": [220, 380], "webhookId": "b76d02c0-b406-4d21-b6bf-8ad2c623def3", "parameters": {"public": true, "options": {"title": "Notion Knowledge Base", "subtitle": ""}, "initialMessages": "=Happy {{ $today.weekdayLong }}!\nKnowledge source assistant at your service. How can I help you?"}, "typeVersion": 1.1}, {"id": "2e25e4bc-7970-4d00-a757-ba1e418873aa", "name": "Sticky Note2", "type": "n8n-nodes-base.stickyNote", "position": [-340, 360], "parameters": {"color": 7, "width": 463.90418399676537, "height": 318.2958135288425, "content": "### Template set up quickstart video \ud83d\udc47\n[](https://www.youtube.com/watch?v=ynLZwS2Nhnc)\n"}, "typeVersion": 1}, {"id": "ba6fe953-fd5c-497f-ac2a-7afa04b7e6cc", "name": "Sticky Note3", "type": "n8n-nodes-base.stickyNote", "position": [-340, 700], "parameters": {"color": 7, "width": 461.5634274842711, "height": 332.14098134070576, "content": "### Written set up steps\n1. Add a Notion credential to your n8n workspace (follow [this Notion guide](https://developers.notion.com/docs/create-a-notion-integration))\n2. [Duplicate Company knowledge base Notion template](https://www.notion.so/templates/knowledge-base-ai-assistant-with-n8n) to your Notion workspace, then make sure to share the new knowledge base with connection you created in Step 1. \n3. Add Notion cred to `Get database details`:`Credential to connect with` parameter, then to `Search notion database`:`Notion API` parameter (same for `Search inside database record`)\n4. Add OpenAI credential to `Open AI Chat Model` node (tested and working with Anthropic Claude 3.5 too)\n5. In `Get database details`, select the db you created from Step 2 in `Database` dropdown.\n6. Click `Chat` button to test the workflow. Then Activate it and copy the `Chat URL` from `When chat message received`."}, "typeVersion": 1}], "pinData": {}, "connections": {"Format schema": {"main": [[{"node": "AI Agent", "type": "main", "index": 0}]]}, "OpenAI Chat Model": {"ai_languageModel": [[{"node": "AI Agent", "type": "ai_languageModel", "index": 0}]]}, "Get database details": {"main": [[{"node": "Format schema", "type": "main", "index": 0}]]}, "Window Buffer Memory": {"ai_memory": [[{"node": "AI Agent", "type": "ai_memory", "index": 0}]]}, "Search notion database": {"ai_tool": [[{"node": "AI Agent", "type": "ai_tool", "index": 0}]]}, "When chat message received": {"main": [[{"node": "Get database details", "type": "main", "index": 0}]]}, "Search inside database record": {"ai_tool": [[{"node": "AI Agent", "type": "ai_tool", "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.