AI Agent To Chat With Files In Supabase Storage

Ready-to-use n8n workflow template for ai. This automation connects Supabase, OpenAI with 33 nodes. Import directly into your n8n instance and customize for your needs.

33 nodesmanual trigger4 views0 copiesAI
SupabaseOpenAI

Workflow JSON

{"meta": {"instanceId": "6a2a7715680b8313f7cb4676321c5baa46680adfb913072f089f2766f42e43bd"}, "nodes": [{"id": "f577f6bd-b1a4-48ec-9329-7bccc3fc1463", "name": "Get All files", "type": "n8n-nodes-base.httpRequest", "position": [400, -100], "parameters": {"url": "=https://yqtvdcvjboenlblgcivl.supabase.co/storage/v1/object/list/private", "method": "POST", "options": {}, "jsonBody": "={\n \"prefix\": \"\",\n \"limit\": 100,\n \"offset\": 0,\n \"sortBy\": {\n \"column\": \"name\",\n \"order\": \"asc\"\n }\n}", "sendBody": true, "specifyBody": "json", "authentication": "predefinedCredentialType", "nodeCredentialType": "supabaseApi"}, "credentials": {"supabaseApi": {"id": "", "name": "[Your supabaseApi]"}}, "typeVersion": 4.2}, {"id": "10693bc8-560d-4cf6-8bd0-2fe3f4d863d1", "name": "Default Data Loader", "type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader", "position": [1780, 100], "parameters": {"options": {"metadata": {"metadataValues": [{"name": "=file_id", "value": "={{ $json.id }}"}]}}, "jsonData": "={{ $('Merge').item.json.data ?? $('Merge').item.json.text }}", "jsonMode": "expressionData"}, "typeVersion": 1}, {"id": "49428060-e707-4269-8344-77b301f56f7c", "name": "Recursive Character Text Splitter", "type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter", "position": [1780, 280], "parameters": {"options": {}, "chunkSize": 500, "chunkOverlap": 200}, "typeVersion": 1}, {"id": "08742063-e235-4874-a128-b352786b19ce", "name": "Extract Document PDF", "type": "n8n-nodes-base.extractFromFile", "position": [1240, 0], "parameters": {"options": {}, "operation": "pdf"}, "typeVersion": 1, "alwaysOutputData": false}, {"id": "21f19360-d7ce-4106-ae5a-aa0f15b7c4aa", "name": "Embeddings OpenAI", "type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi", "position": [1600, 80], "parameters": {"model": "text-embedding-3-small", "options": {}}, "credentials": {"openAiApi": {"id": "", "name": "[Your openAiApi]"}}, "typeVersion": 1}, {"id": "4147409f-8686-418f-b979-04f8c8e7fe42", "name": "Create File record2", "type": "n8n-nodes-base.supabase", "position": [1540, -100], "parameters": {"tableId": "files", "fieldsUi": {"fieldValues": [{"fieldId": "name", "fieldValue": "={{ $('Loop Over Items').item.json.name }}"}, {"fieldId": "storage_id", "fieldValue": "={{ $('Loop Over Items').item.json.id }}"}]}}, "credentials": {"supabaseApi": {"id": "", "name": "[Your supabaseApi]"}}, "typeVersion": 1}, {"id": "016f1afe-172b-4609-b451-8d67609214d3", "name": "If", "type": "n8n-nodes-base.if", "position": [720, -100], "parameters": {"options": {}, "conditions": {"options": {"version": 2, "leftValue": "", "caseSensitive": true, "typeValidation": "strict"}, "combinator": "and", "conditions": [{"id": "9b14e306-a04d-40f7-bc5b-b8eda8d8f7f2", "operator": {"type": "boolean", "operation": "true", "singleValue": true}, "leftValue": "={{ \n !$('Aggregate').item.json.data || \n !Array.isArray($('Aggregate').item.json.data) || \n !$('Aggregate').item.json.data.some(item => \n item.storage_id === $('Loop Over Items').item.json.id \n ) \n}}", "rightValue": ""}, {"id": "c3c0af88-9aea-4539-8948-1b69e601c27c", "operator": {"type": "string", "operation": "notEquals"}, "leftValue": "={{ $json.name }}", "rightValue": ".emptyFolderPlaceholder"}]}}, "typeVersion": 2.2}, {"id": "75e8a7db-8c4a-4ad8-b902-062cbc93e1eb", "name": "Get All Files", "type": "n8n-nodes-base.supabase", "position": [20, -100], "parameters": {"tableId": "files", "operation": "getAll"}, "credentials": {"supabaseApi": {"id": "", "name": "[Your supabaseApi]"}}, "typeVersion": 1, "alwaysOutputData": true}, {"id": "b22a3bab-f615-4d8a-8832-ce25b1a385fe", "name": "Download", "type": "n8n-nodes-base.httpRequest", "position": [900, -100], "parameters": {"url": "=https://yqtvdcvjboenlblgcivl.supabase.co/storage/v1/object/private/{{ $json.name }}", "options": {}, "authentication": "predefinedCredentialType", "nodeCredentialType": "supabaseApi"}, "credentials": {"supabaseApi": {"id": "", "name": "[Your supabaseApi]"}}, "typeVersion": 4.2}, {"id": "50d1fede-4bd0-4cd4-b74a-7d689fe211cc", "name": "Loop Over Items", "type": "n8n-nodes-base.splitInBatches", "position": [560, -100], "parameters": {"options": {}, "batchSize": "=1"}, "typeVersion": 3}, {"id": "f9c23b5e-0b40-4886-b54f-59fb46132d3f", "name": "When clicking \u2018Test workflow\u2019", "type": "n8n-nodes-base.manualTrigger", "position": [-160, -100], "parameters": {}, "typeVersion": 1}, {"id": "0a0ec290-2c3d-40ba-8d03-6abf75202e73", "name": "Aggregate", "type": "n8n-nodes-base.aggregate", "position": [220, -100], "parameters": {"options": {}, "aggregate": "aggregateAllItemData"}, "typeVersion": 1, "alwaysOutputData": true}, {"id": "32b3e2e1-2d25-4dd1-93e8-3f693beb7b6f", "name": "When chat message received", "type": "@n8n/n8n-nodes-langchain.chatTrigger", "position": [800, -1020], "webhookId": "3c40d311-7996-4ed4-b2fa-c73bea5f4cf5", "parameters": {"options": {}}, "typeVersion": 1.1}, {"id": "79073b5c-a4ad-45a6-bbfa-e900a05bfde3", "name": "OpenAI Chat Model1", "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi", "position": [940, -820], "parameters": {"options": {}}, "credentials": {"openAiApi": {"id": "", "name": "[Your openAiApi]"}}, "typeVersion": 1}, {"id": "f8663483-76d5-4fc8-ad07-7eec815ff7a6", "name": "Embeddings OpenAI2", "type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi", "position": [1020, -540], "parameters": {"model": "text-embedding-3-small", "options": {}}, "credentials": {"openAiApi": {"id": "", "name": "[Your openAiApi]"}}, "typeVersion": 1}, {"id": "a1458799-d379-46de-93e6-a5ba0c665163", "name": "OpenAI Chat Model2", "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi", "position": [1300, -680], "parameters": {"options": {}}, "credentials": {"openAiApi": {"id": "", "name": "[Your openAiApi]"}}, "typeVersion": 1}, {"id": "d6eeda2f-c984-406d-a625-726840308413", "name": "Vector Store Tool1", "type": "@n8n/n8n-nodes-langchain.toolVectorStore", "position": [1100, -820], "parameters": {"name": "knowledge_base", "topK": 8, "description": "Retrieve data about user request"}, "typeVersion": 1}, {"id": "e1d9a348-7d44-4ad1-adbd-2c9a31e06876", "name": "Switch", "type": "n8n-nodes-base.switch", "position": [1060, -100], "parameters": {"rules": {"values": [{"outputKey": "txt", "conditions": {"options": {"version": 1, "leftValue": "", "caseSensitive": true, "typeValidation": "strict"}, "combinator": "and", "conditions": [{"operator": {"type": "boolean", "operation": "true", "singleValue": true}, "leftValue": "={{$binary.data?.fileExtension == undefined }}", "rightValue": "txt"}]}, "renameOutput": true}, {"outputKey": "pdf", "conditions": {"options": {"version": 1, "leftValue": "", "caseSensitive": true, "typeValidation": "strict"}, "combinator": "and", "conditions": [{"id": "bf04cbec-dd86-4607-988f-4c96b6fd4b58", "operator": {"type": "string", "operation": "equals"}, "leftValue": "={{$binary.data.fileExtension }}", "rightValue": "pdf"}]}, "renameOutput": true}]}, "options": {}}, "typeVersion": 3.1}, {"id": "d38afb92-87ae-4e2a-a712-ec24b1efd105", "name": "Insert into Supabase Vectorstore", "type": "@n8n/n8n-nodes-langchain.vectorStoreSupabase", "position": [1700, -100], "parameters": {"mode": "insert", "options": {"queryName": "match_documents"}, "tableName": {"__rl": true, "mode": "list", "value": "documents", "cachedResultName": "documents"}}, "credentials": {"supabaseApi": {"id": "", "name": "[Your supabaseApi]"}}, "typeVersion": 1}, {"id": "1a903b2e-cab0-4798-b820-ec08d6a71ddd", "name": "Merge", "type": "n8n-nodes-base.merge", "position": [1380, -100], "parameters": {}, "typeVersion": 3}, {"id": "3afd552e-4995-493e-9cd5-ef496dfe359f", "name": "AI Agent", "type": "@n8n/n8n-nodes-langchain.agent", "position": [1020, -1020], "parameters": {"options": {}}, "typeVersion": 1.7}, {"id": "d9688acc-311b-42fd-afa8-2c0e493be34b", "name": "Supabase Vector Store", "type": "@n8n/n8n-nodes-langchain.vectorStoreSupabase", "position": [1020, -660], "parameters": {"options": {"metadata": {"metadataValues": [{"name": "file_id", "value": "300b0128-0955-4058-b0d3-a9aefe728432"}]}}, "tableName": {"__rl": true, "mode": "list", "value": "documents", "cachedResultName": "documents"}}, "credentials": {"supabaseApi": {"id": "", "name": "[Your supabaseApi]"}}, "typeVersion": 1}, {"id": "66df007c-0418-4551-950e-32e7d79840bd", "name": "Sticky Note", "type": "n8n-nodes-base.stickyNote", "position": [340, -220], "parameters": {"height": 89.3775420487804, "content": "### Replace Storage name, database ID and credentials."}, "typeVersion": 1}, {"id": "b164b520-20dd-44a4-aa3b-647391786b20", "name": "Sticky Note1", "type": "n8n-nodes-base.stickyNote", "position": [-20, -220], "parameters": {"height": 80, "content": "### Replace credentials."}, "typeVersion": 1}, {"id": "8688c219-5af4-4e54-9fd1-91851829445b", "name": "Sticky Note2", "type": "n8n-nodes-base.stickyNote", "position": [1540, -220], "parameters": {"height": 80, "content": "### Replace credentials."}, "typeVersion": 1}, {"id": "45c6ece4-f849-4496-8149-31385f5e36a4", "name": "Sticky Note3", "type": "n8n-nodes-base.stickyNote", "position": [840, -220], "parameters": {"height": 89.3775420487804, "content": "### Replace Storage name, database ID and credentials."}, "typeVersion": 1}, {"id": "2ca07cb0-b5f4-4761-b954-faf2131872d9", "name": "Sticky Note4", "type": "n8n-nodes-base.stickyNote", "position": [1500, 220], "parameters": {"height": 80, "content": "### Replace credentials."}, "typeVersion": 1}, {"id": "8d682dae-6f88-42f0-a717-affffd37d882", "name": "Sticky Note5", "type": "n8n-nodes-base.stickyNote", "position": [1140, -520], "parameters": {"height": 80, "content": "### Replace credentials."}, "typeVersion": 1}, {"id": "796b5dca-d60e-43a9-afe8-194244643557", "name": "Sticky Note9", "type": "n8n-nodes-base.stickyNote", "position": [-520, -940], "parameters": {"color": 7, "width": 330.5152611046425, "height": 239.5888196628349, "content": "### ... or watch set up video [10 min]\n[![Youtube Thumbnail](https://res.cloudinary.com/de9jgixzm/image/upload/v1739773273/Youtube%20Thumbs/Chat%20With%20FIles.png)](https://www.youtube.com/watch?v=glWUkdZe_3w)\n"}, "typeVersion": 1}, {"id": "eba121de-a3f7-4ba5-8396-f7d64e648322", "name": "Sticky Note7", "type": "n8n-nodes-base.stickyNote", "position": [-820, -1460], "parameters": {"color": 7, "width": 636.2128494576581, "height": 497.1532689930921, "content": "![5min Logo](https://res.cloudinary.com/de9jgixzm/image/upload/v1739773200/Skool%20Assets/ejm3hqnvhgwpnu2fv92s.png)\n## AI Agent To Chat With Files In Supabase Storage\n**Made by [Mark Shcherbakov](https://www.linkedin.com/in/marklowcoding/) from community [5minAI](https://www.skool.com/5minai-2861)**\n\nManually retrieving and analyzing specific information from large document repositories is time-consuming and inefficient. This workflow automates the process by vectorizing documents and enabling AI-powered interactions, making it easy to query and retrieve context-based information from uploaded files.\n\nThe workflow integrates Supabase with an AI-powered chatbot to process, store, and query text and PDF files. The steps include:\n- Fetching and comparing files to avoid duplicate processing.\n- Handling file downloads and extracting content based on the file type.\n- Converting documents into vectorized data for contextual information retrieval.\n- Storing and querying vectorized data from a Supabase vector store.\n\n"}, "typeVersion": 1}, {"id": "df054036-d6b9-4f53-86cb-85ad96f07d0e", "name": "Sticky Note6", "type": "n8n-nodes-base.stickyNote", "position": [-820, -940], "parameters": {"color": 7, "width": 280.2462120317618, "height": 545.9087885077763, "content": "### Set up steps\n\n1. **Fetch File List from Supabase**:\n - Use Supabase to retrieve the stored file list from a specified bucket.\n - Add logic to manage empty folder placeholders returned by Supabase, avoiding incorrect processing.\n\n2. **Compare and Filter Files**:\n - Aggregate the files retrieved from storage and compare them to the existing list in the Supabase `files` table.\n - Exclude duplicates and skip placeholder files to ensure only unprocessed files are handled.\n\n3. **Handle File Downloads**:\n - Download new files using detailed storage configurations for public/private access.\n - Adjust the storage settings and GET requests to match your Supabase setup.\n\n4. **File Type Processing**:\n - Use a Switch node to target specific file types (e.g., PDFs or text files).\n - Employ relevant tools to process the content:\n - For PDFs, extract embedded content.\n - For text files, directly process the text data.\n\n5. **Content Chunking**:\n - Break large text data into smaller chunks using the Text Splitter node.\n - Define chunk size (default: 500 tokens) and overlap to retain necessary context across chunks.\n\n6. **Vector Embedding Creation**:\n - Generate vectorized embeddings for the processed content using OpenAI's embedding tools.\n - Ensure metadata, such as file ID, is included for easy data retrieval.\n\n7. **Store Vectorized Data**:\n - Save the vectorized information into a dedicated Supabase vector store.\n - Use the default schema and table provided by Supabase for seamless setup.\n\n8. **AI Chatbot Integration**:\n - Add a chatbot node to handle user input and retrieve relevant document chunks.\n - Use metadata like file ID for targeted queries, especially when multiple documents are involved."}, "typeVersion": 1}, {"id": "450a1e49-4be9-451a-9d05-2860e29c3695", "name": "Sticky Note8", "type": "n8n-nodes-base.stickyNote", "position": [540, -1160], "parameters": {"color": 5, "width": 951.7421645394404, "height": 809.7437181509877, "content": "## Scenario 2 - AI agent"}, "typeVersion": 1}, {"id": "c3814c5d-8881-4598-897e-268019bee1bc", "name": "Sticky Note10", "type": "n8n-nodes-base.stickyNote", "position": [-260, -280], "parameters": {"color": 5, "width": 2304.723519246249, "height": 739.2522526116408, "content": "## Scenario 1 - Flow for adding new files from Supabase storage"}, "typeVersion": 1}], "pinData": {}, "connections": {"If": {"main": [[{"node": "Download", "type": "main", "index": 0}], [{"node": "Loop Over Items", "type": "main", "index": 0}]]}, "Merge": {"main": [[{"node": "Create File record2", "type": "main", "index": 0}]]}, "Switch": {"main": [[{"node": "Merge", "type": "main", "index": 0}], [{"node": "Extract Document PDF", "type": "main", "index": 0}]]}, "Download": {"main": [[{"node": "Switch", "type": "main", "index": 0}]]}, "Aggregate": {"main": [[{"node": "Get All files", "type": "main", "index": 0}]]}, "Get All Files": {"main": [[{"node": "Aggregate", "type": "main", "index": 0}]]}, "Get All files": {"main": [[{"node": "Loop Over Items", "type": "main", "index": 0}]]}, "Loop Over Items": {"main": [null, [{"node": "If", "type": "main", "index": 0}]]}, "Embeddings OpenAI": {"ai_embedding": [[{"node": "Insert into Supabase Vectorstore", "type": "ai_embedding", "index": 0}]]}, "Embeddings OpenAI2": {"ai_embedding": [[{"node": "Supabase Vector Store", "type": "ai_embedding", "index": 0}]]}, "OpenAI Chat Model1": {"ai_languageModel": [[{"node": "AI Agent", "type": "ai_languageModel", "index": 0}]]}, "OpenAI Chat Model2": {"ai_languageModel": [[{"node": "Vector Store Tool1", "type": "ai_languageModel", "index": 0}]]}, "Vector Store Tool1": {"ai_tool": [[{"node": "AI Agent", "type": "ai_tool", "index": 0}]]}, "Create File record2": {"main": [[{"node": "Insert into Supabase Vectorstore", "type": "main", "index": 0}]]}, "Default Data Loader": {"ai_document": [[{"node": "Insert into Supabase Vectorstore", "type": "ai_document", "index": 0}]]}, "Extract Document PDF": {"main": [[{"node": "Merge", "type": "main", "index": 1}]]}, "Supabase Vector Store": {"ai_vectorStore": [[{"node": "Vector Store Tool1", "type": "ai_vectorStore", "index": 0}]]}, "When chat message received": {"main": [[{"node": "AI Agent", "type": "main", "index": 0}]]}, "Insert into Supabase Vectorstore": {"main": [[{"node": "Loop Over Items", "type": "main", "index": 0}]]}, "Recursive Character Text Splitter": {"ai_textSplitter": [[{"node": "Default Data Loader", "type": "ai_textSplitter", "index": 0}]]}, "When clicking \u2018Test workflow\u2019": {"main": [[{"node": "Get All Files", "type": "main", "index": 0}]]}}}

How to Import This Workflow

  1. 1Copy the workflow JSON above using the Copy Workflow JSON button.
  2. 2Open your n8n instance and go to Workflows.
  3. 3Click Import from JSON and paste the copied workflow.

Don't have an n8n instance? Start your free trial at n8nautomation.cloud

Ready to automate with n8n?

Get affordable managed n8n hosting with 24/7 support.