Allan Vaccarizi This workflow corresponds to n8n.io template #8916 — we link there as the canonical source.
This workflow follows the Chat Trigger → Documentdefaultdataloader recipe pattern — see all workflows that pair these two integrations.
The workflow JSON
Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →
{
"meta": {
"templateCredsSetupCompleted": true
},
"nodes": [
{
"id": "eb4ca5ac-5ec2-447e-b903-df92db68346d",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
2656,
1536
],
"parameters": {
"width": 480,
"height": 976,
"content": "## RAG\n\n### How it works\n\n1. A one-time setup flow (triggered by a chat message) creates the required Postgres/Supabase database tables and match function.\n2. Google Drive triggers fire whenever a file is created or updated, feeding a batch loop that processes each file one at a time.\n3. Old document records and vector rows are deleted from Supabase/Postgres before re-processing begins.\n4. Document metadata is upserted into Postgres and the file is downloaded from Google Drive.\n5. A switch routes each file to the appropriate extractor (PDF, Word/Doc, Excel, or CSV); tabular data is also stored as raw rows in Postgres.\n6. Extracted text is embedded with OpenAI and inserted into the Supabase vector store, while tabular summaries update the document metadata schema.\n\n### Setup steps\n\n- - [ ] Configure Google Drive OAuth2 credentials for the 'File Created' and 'File Updated' triggers and the 'Download File' node.\n- - [ ] Configure Supabase credentials for the 'Delete Old Doc Rows', 'Delete Old Data Rows', and 'Insert into Supabase Vectorstore' nodes.\n- - [ ] Configure Postgres credentials for all Postgres nodes (table creation, metadata upsert, schema update, row insert).\n- - [ ] Set your OpenAI API key in the 'Embeddings OpenAI1' node.\n- - [ ] Run the setup flow once via the chat trigger to create the required database tables and vector-match function.\n- - [ ] Configure the Google Drive folder ID(s) to watch in the trigger nodes.\n- - [ ] Tune the Character Text Splitter chunk size and overlap to match your document sizes.\n\n### Customization\n\nYou can adjust the text splitter chunk size and overlap to improve retrieval quality. The Switch node can be extended with additional file-type branches. The Summarize node logic can be modified to change how tabular content is condensed before vectorisation."
},
"typeVersion": 1
},
{
"id": "d8cc6d5f-f050-4381-826e-b22bca043be5",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
3216,
1536
],
"parameters": {
"color": 7,
"width": 816,
"height": 320,
"content": "## One-time database setup\n\nTriggered by a chat message, this cluster runs SQL queries to create the documents vector table, match function, document metadata table, and tabular data rows table in Postgres/Supabase."
},
"typeVersion": 1
},
{
"id": "8caf1911-051e-4d32-892c-012b891cc885",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
3216,
1952
],
"parameters": {
"color": 7,
"height": 560,
"content": "## Google Drive file triggers\n\nTwo Google Drive triggers detect newly created or updated files and feed them into the batch loop for processing."
},
"typeVersion": 1
},
{
"id": "323c81bc-09d9-4a2e-9c10-bd54f34f6063",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
3552,
2016
],
"parameters": {
"color": 7,
"height": 400,
"content": "## Batch loop entry point\n\nSplits the list of detected files into individual items so each file is processed sequentially. Also receives the completion signal from the vector store to advance to the next item."
},
"typeVersion": 1
},
{
"id": "a95966ea-5bf9-4859-8059-df91f17d12cb",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
3824,
2080
],
"parameters": {
"color": 7,
"width": 544,
"height": 496,
"content": "## Set file identity and clean old data\n\nSets key file metadata fields (ID, type, title, URL), then deletes the file's existing document rows and vector data rows from Supabase so stale content is removed before re-ingestion."
},
"typeVersion": 1
},
{
"id": "438dcd38-b6ed-415d-8821-e5c11c1a8962",
"name": "Sticky Note5",
"type": "n8n-nodes-base.stickyNote",
"position": [
4400,
2112
],
"parameters": {
"color": 7,
"width": 496,
"height": 320,
"content": "## Upsert metadata and download file\n\nUpserts the document metadata record into Postgres, then downloads the actual file binary from Google Drive ready for text extraction."
},
"typeVersion": 1
},
{
"id": "6139a026-2aad-46d8-978f-cf4fabc2077e",
"name": "Sticky Note6",
"type": "n8n-nodes-base.stickyNote",
"position": [
4928,
2032
],
"parameters": {
"color": 7,
"height": 432,
"content": "## Route file by type\n\nInspects the file type and routes it to the correct extraction branch: PDF, Office document, Excel spreadsheet, or CSV."
},
"typeVersion": 1
},
{
"id": "428555eb-5882-45c5-9eb6-c279d4a32791",
"name": "Sticky Note7",
"type": "n8n-nodes-base.stickyNote",
"position": [
5216,
1744
],
"parameters": {
"color": 7,
"height": 880,
"content": "## Extract text from PDF and documents\n\nExtracts plain text from PDF files and from generic office/word documents, producing text ready for direct vectorisation."
},
"typeVersion": 1
},
{
"id": "de9e0754-f10f-4c16-8e73-1c7730c068cb",
"name": "Sticky Note8",
"type": "n8n-nodes-base.stickyNote",
"position": [
5488,
2016
],
"parameters": {
"color": 7,
"width": 832,
"height": 544,
"content": "## Extract and store tabular data\n\nExtracts rows from Excel and CSV files, inserts raw row data into a Postgres table, then aggregates all rows and summarises them for downstream vectorisation."
},
"typeVersion": 1
},
{
"id": "7a567ab6-749b-4ea8-ac85-02704a434353",
"name": "Sticky Note10",
"type": "n8n-nodes-base.stickyNote",
"position": [
6832,
1888
],
"parameters": {
"color": 7,
"width": 544,
"height": 720,
"content": "## Embed and store in vector store\n\nUses OpenAI embeddings and a character text splitter to chunk and embed extracted text, then inserts the resulting vectors into the Supabase vector store. Sub-nodes (embeddings model, data loader, text splitter) configure how documents are split and encoded."
},
"typeVersion": 1
},
{
"id": "9075b294-9e8b-488b-b062-31e732635572",
"name": "Load Document Data",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
7120,
2320
],
"parameters": {
"options": {
"metadata": {
"metadataValues": [
{
"name": "=file_id",
"value": "={{ $('Set File Metadata Fields').first().json.file_id }}"
},
{
"name": "file_title",
"value": "={{ $('Set File Metadata Fields').first().json.file_title }}"
}
]
}
},
"jsonData": "={{ $json.data || $json.text || $json.concatenated_data }}",
"jsonMode": "expressionData"
},
"typeVersion": 1
},
{
"id": "18713d69-3d8a-4cb3-99ee-59b1b1cd862b",
"name": "OpenAI Embeddings",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
6880,
2320
],
"parameters": {
"model": "text-embedding-3-small",
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "4be45908-ebd7-4c7f-b660-580144afe62f",
"name": "Download File from Drive",
"type": "n8n-nodes-base.googleDrive",
"position": [
4752,
2272
],
"parameters": {
"fileId": {
"__rl": true,
"mode": "id",
"value": "={{ $('Set File Metadata Fields').item.json.file_id }}"
},
"options": {
"googleFileConversion": {
"conversion": {
"docsToFormat": "text/plain"
}
}
},
"operation": "download"
},
"credentials": {
"googleDriveOAuth2Api": {
"name": "<your credential>"
}
},
"executeOnce": true,
"typeVersion": 3
},
{
"id": "1f84d55b-6b29-4583-b191-be4e46390091",
"name": "When Drive File Created",
"type": "n8n-nodes-base.googleDriveTrigger",
"position": [
3264,
2192
],
"parameters": {
"event": "fileCreated",
"options": {},
"pollTimes": {
"item": [
{
"mode": "everyMinute"
}
]
},
"triggerOn": "specificFolder",
"folderToWatch": {
"__rl": true,
"mode": "url",
"value": "https://drive.google.com/drive/u/0/folders/195OWvKSKZjsdyAIXeqoC9z__QKCRHC8i"
}
},
"credentials": {
"googleDriveOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "cde9ebef-1b74-4264-b87f-167d437a2e49",
"name": "When Drive File Updated",
"type": "n8n-nodes-base.googleDriveTrigger",
"position": [
3264,
2352
],
"parameters": {
"event": "fileUpdated",
"options": {},
"pollTimes": {
"item": [
{
"mode": "everyMinute"
}
]
},
"triggerOn": "specificFolder",
"folderToWatch": {
"__rl": true,
"mode": "url",
"value": "https://drive.google.com/drive/u/0/folders/195OWvKSKZjsdyAIXeqoC9z__QKCRHC8i"
}
},
"credentials": {
"googleDriveOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "f1acf69a-aa94-4ad9-b86b-2df94d658071",
"name": "Extract Text from Document",
"type": "n8n-nodes-base.extractFromFile",
"position": [
5264,
2464
],
"parameters": {
"options": {},
"operation": "text"
},
"typeVersion": 1,
"alwaysOutputData": true
},
{
"id": "23e8180a-f0c1-4bd2-ab1e-b3e065d356e8",
"name": "Delete Old Doc Rows in Supabase",
"type": "n8n-nodes-base.supabase",
"position": [
4064,
2256
],
"parameters": {
"tableId": "documents",
"operation": "delete",
"filterType": "string",
"filterString": "=metadata->>file_id=like.*{{ $json.file_id }}*"
},
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
},
"typeVersion": 1,
"alwaysOutputData": true
},
{
"id": "58a8e3b9-0c0c-4576-8d70-273e00c2adc6",
"name": "Set File Metadata Fields",
"type": "n8n-nodes-base.set",
"position": [
3872,
2416
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "10646eae-ae46-4327-a4dc-9987c2d76173",
"name": "file_id",
"type": "string",
"value": "={{ $json.id }}"
},
{
"id": "f4536df5-d0b1-4392-bf17-b8137fb31a44",
"name": "file_type",
"type": "string",
"value": "={{ $json.mimeType }}"
},
{
"id": "77d782de-169d-4a46-8a8e-a3831c04d90f",
"name": "file_title",
"type": "string",
"value": "={{ $json.name }}"
},
{
"id": "9bde4d7f-e4f3-4ebd-9338-dce1350f9eab",
"name": "file_url",
"type": "string",
"value": "={{ $json.webViewLink }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "af85c4ec-8d0e-497b-b984-abcbf1f2f52d",
"name": "Extract Text from PDF",
"type": "n8n-nodes-base.extractFromFile",
"position": [
5264,
1984
],
"parameters": {
"options": {},
"operation": "pdf"
},
"typeVersion": 1
},
{
"id": "3e01040c-982e-4086-aee6-09d197944817",
"name": "Aggregate Tabular Data",
"type": "n8n-nodes-base.aggregate",
"position": [
5968,
2160
],
"parameters": {
"options": {},
"aggregate": "aggregateAllItemData"
},
"typeVersion": 1
},
{
"id": "41c8cc7f-b4b0-4486-9e84-06c446ed2438",
"name": "Split Text into Chunks",
"type": "@n8n/n8n-nodes-langchain.textSplitterCharacterTextSplitter",
"position": [
7024,
2432
],
"parameters": {},
"typeVersion": 1
},
{
"id": "26195379-8c3d-4374-ac3c-f52dccd858b6",
"name": "Summarize Tabular Data",
"type": "n8n-nodes-base.summarize",
"position": [
6176,
2160
],
"parameters": {
"options": {},
"fieldsToSummarize": {
"values": [
{
"field": "data",
"aggregation": "concatenate"
}
]
}
},
"typeVersion": 1
},
{
"id": "b653c385-9f0e-4788-8256-5fa151959286",
"name": "Route by File Type",
"type": "n8n-nodes-base.switch",
"position": [
4976,
2240
],
"parameters": {
"rules": {
"values": [
{
"conditions": {
"options": {
"version": 1,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"operator": {
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $('Set File Metadata Fields').item.json.file_type }}",
"rightValue": "application/pdf"
}
]
}
},
{
"conditions": {
"options": {
"version": 1,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "2ae7faa7-a936-4621-a680-60c512163034",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $('Set File Metadata Fields').item.json.file_type }}",
"rightValue": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
}
]
}
},
{
"conditions": {
"options": {
"version": 1,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "fc193b06-363b-4699-a97d-e5a850138b0e",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $('Set File Metadata Fields').item.json.file_type }}",
"rightValue": "=application/vnd.google-apps.spreadsheet"
}
]
}
},
{
"conditions": {
"options": {
"version": 1,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "b69f5605-0179-4b02-9a32-e34bb085f82d",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $('Set File Metadata Fields').item.json.file_type }}",
"rightValue": "application/vnd.google-apps.document"
}
]
}
}
]
},
"options": {
"fallbackOutput": 3
}
},
"typeVersion": 3
},
{
"id": "5cb57260-3097-4ea5-a1ef-b85da261147c",
"name": "Insert Embeddings to Vectorstore",
"type": "@n8n/n8n-nodes-langchain.vectorStoreSupabase",
"position": [
7040,
2096
],
"parameters": {
"mode": "insert",
"options": {
"queryName": "match_documents"
},
"tableName": {
"__rl": true,
"mode": "list",
"value": "documents",
"cachedResultName": "documents"
}
},
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "b1cff829-93fa-4ae9-81ec-3bbc837255c2",
"name": "Extract Data from Excel",
"type": "n8n-nodes-base.extractFromFile",
"position": [
5536,
2144
],
"parameters": {
"options": {},
"operation": "xlsx"
},
"typeVersion": 1
},
{
"id": "ac206afa-d0b6-4a92-9b24-d98f775ed203",
"name": "Build Schema and Data",
"type": "n8n-nodes-base.set",
"position": [
6400,
2144
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "f422e2e0-381c-46ea-8f38-3f58c501d8b9",
"name": "schema",
"type": "string",
"value": "={{ $('Extract Data from Excel').isExecuted ? $('Extract Data from Excel').first().json.keys().toJsonString() : $('Extract Data from CSV').first().json.keys().toJsonString() }}"
},
{
"id": "bb07c71e-5b60-4795-864c-cc3845b6bc46",
"name": "data",
"type": "string",
"value": "={{ $json.concatenated_data }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "1cde953c-8543-4c50-8d13-eb79040a5375",
"name": "Extract Data from CSV",
"type": "n8n-nodes-base.extractFromFile",
"position": [
5536,
2304
],
"parameters": {
"options": {}
},
"typeVersion": 1
},
{
"id": "65e1b876-308f-4302-bcfd-28491095a5a1",
"name": "Loop Over Drive Files",
"type": "n8n-nodes-base.splitInBatches",
"position": [
3600,
2256
],
"parameters": {
"options": {
"reset": false
}
},
"typeVersion": 3
},
{
"id": "2c1f573d-8e64-4528-b550-b67bb7d6795d",
"name": "Delete Old Data Rows in Supabase",
"type": "n8n-nodes-base.supabase",
"position": [
4224,
2416
],
"parameters": {
"filters": {
"conditions": [
{
"keyName": "dataset_id",
"keyValue": "={{ $('Set File Metadata Fields').item.json.file_id }}",
"condition": "eq"
}
]
},
"tableId": "document_rows",
"operation": "delete"
},
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
},
"executeOnce": true,
"typeVersion": 1,
"alwaysOutputData": true
},
{
"id": "a056a860-6824-44f8-9b40-71ff9265880f",
"name": "Insert Document Metadata to DB",
"type": "n8n-nodes-base.postgres",
"position": [
4448,
2272
],
"parameters": {
"table": {
"__rl": true,
"mode": "list",
"value": "document_metadata",
"cachedResultName": "document_metadata"
},
"schema": {
"__rl": true,
"mode": "list",
"value": "public"
},
"columns": {
"value": {
"id": "={{ $('Set File Metadata Fields').item.json.file_id }}",
"url": "={{ $('Set File Metadata Fields').item.json.file_url }}",
"title": "={{ $('Set File Metadata Fields').item.json.file_title }}"
},
"schema": [
{
"id": "id",
"type": "string",
"display": true,
"removed": false,
"required": true,
"displayName": "id",
"defaultMatch": true,
"canBeUsedToMatch": true
},
{
"id": "title",
"type": "string",
"display": true,
"required": false,
"displayName": "title",
"defaultMatch": false,
"canBeUsedToMatch": false
},
{
"id": "url",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "url",
"defaultMatch": false,
"canBeUsedToMatch": false
},
{
"id": "created_at",
"type": "dateTime",
"display": true,
"required": false,
"displayName": "created_at",
"defaultMatch": false,
"canBeUsedToMatch": false
},
{
"id": "schema",
"type": "string",
"display": true,
"removed": true,
"required": false,
"displayName": "schema",
"defaultMatch": false,
"canBeUsedToMatch": false
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"id"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {},
"operation": "upsert"
},
"credentials": {
"postgres": {
"name": "<your credential>"
}
},
"executeOnce": true,
"typeVersion": 2.5
},
{
"id": "3da25fe9-637b-4ca4-a337-8e498543af98",
"name": "Insert Table Rows to DB",
"type": "n8n-nodes-base.postgres",
"position": [
6016,
2384
],
"parameters": {
"table": {
"__rl": true,
"mode": "list",
"value": "document_rows",
"cachedResultName": "document_rows"
},
"schema": {
"__rl": true,
"mode": "list",
"value": "public"
},
"columns": {
"value": {
"row_data": "={{ $json.toJsonString().replaceAll(/'/g, \"''\") }}",
"dataset_id": "={{ $('Set File Metadata Fields').item.json.file_id }}"
},
"schema": [
{
"id": "id",
"type": "number",
"display": true,
"removed": true,
"required": false,
"displayName": "id",
"defaultMatch": true,
"canBeUsedToMatch": true
},
{
"id": "dataset_id",
"type": "string",
"display": true,
"required": false,
"displayName": "dataset_id",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "row_data",
"type": "object",
"display": true,
"required": false,
"displayName": "row_data",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"id"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {}
},
"credentials": {
"postgres": {
"name": "<your credential>"
}
},
"typeVersion": 2.5
},
{
"id": "809b6222-4b26-4f65-af47-844804024f94",
"name": "Update Document Schema in DB",
"type": "n8n-nodes-base.postgres",
"position": [
6640,
2144
],
"parameters": {
"table": {
"__rl": true,
"mode": "list",
"value": "document_metadata",
"cachedResultName": "document_metadata"
},
"schema": {
"__rl": true,
"mode": "list",
"value": "public"
},
"columns": {
"value": {
"id": "={{ $('Set File Metadata Fields').item.json.file_id }}",
"schema": "={{ $json.schema }}"
},
"schema": [
{
"id": "id",
"type": "string",
"display": true,
"removed": false,
"required": true,
"displayName": "id",
"defaultMatch": true,
"canBeUsedToMatch": true
},
{
"id": "title",
"type": "string",
"display": true,
"removed": true,
"required": false,
"displayName": "title",
"defaultMatch": false,
"canBeUsedToMatch": false
},
{
"id": "url",
"type": "string",
"display": true,
"removed": true,
"required": false,
"displayName": "url",
"defaultMatch": false,
"canBeUsedToMatch": false
},
{
"id": "created_at",
"type": "dateTime",
"display": true,
"required": false,
"displayName": "created_at",
"defaultMatch": false,
"canBeUsedToMatch": false
},
{
"id": "schema",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "schema",
"defaultMatch": false,
"canBeUsedToMatch": false
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"id"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {},
"operation": "upsert"
},
"credentials": {
"postgres": {
"name": "<your credential>"
}
},
"typeVersion": 2.5
},
{
"id": "0ec9c71b-e944-47b7-a081-c060c86b5f3f",
"name": "Create Document Metadata Table",
"type": "n8n-nodes-base.postgres",
"position": [
3696,
1696
],
"parameters": {
"query": "CREATE TABLE {{ $('When Chat Message Received').item.json.chatInput }}_document_metadata (\n id TEXT PRIMARY KEY,\n title TEXT,\n url TEXT,\n created_at TIMESTAMP DEFAULT NOW(),\n schema TEXT\n);",
"options": {},
"operation": "executeQuery"
},
"credentials": {
"postgres": {
"name": "<your credential>"
}
},
"executeOnce": false,
"typeVersion": 2.5,
"alwaysOutputData": false
},
{
"id": "d958dd8f-1bf4-4e8b-834c-221bea7d7739",
"name": "Create Document Rows Table",
"type": "n8n-nodes-base.postgres",
"position": [
3888,
1696
],
"parameters": {
"query": "CREATE TABLE {{ $('When Chat Message Received').item.json.chatInput }}_document_rows (\n id SERIAL PRIMARY KEY,\n dataset_id TEXT REFERENCES {{ $('When Chat Message Received').item.json.chatInput }}_document_metadata(id),\n row_data JSONB -- Store the actual row data\n);",
"options": {},
"operation": "executeQuery"
},
"credentials": {
"postgres": {
"name": "<your credential>"
}
},
"typeVersion": 2.5
},
{
"id": "9b05e1cc-cb66-4c17-a048-e8cbfb47ea4d",
"name": "Create Docs Table and Match Fn",
"type": "n8n-nodes-base.postgres",
"position": [
3472,
1696
],
"parameters": {
"query": "-- Create a table to store your documents\nCREATE TABLE {{ $json.chatInput }}_documents (\n id bigserial primary key,\n content text, -- corresponds to Document.pageContent\n metadata jsonb, -- corresponds to Document.metadata\n embedding vector(1536) -- 1536 works for OpenAI embeddings, change if needed\n);\n\n-- Create an index for better performance\nCREATE INDEX {{ $json.chatInput }}_documents_embedding_idx \nON {{ $json.chatInput }}_documents \nUSING ivfflat (embedding vector_cosine_ops);\n\n-- Create a function to search for documents\nCREATE OR REPLACE FUNCTION match_{{ $json.chatInput }}_documents (\n query_embedding vector(1536),\n match_count int DEFAULT 10,\n filter jsonb DEFAULT '{}'\n)\nRETURNS TABLE (\n id bigint,\n content text,\n metadata jsonb,\n similarity float\n)\nLANGUAGE plpgsql\nAS $$\nBEGIN\n RETURN QUERY\n SELECT\n doc.id,\n doc.content,\n doc.metadata,\n 1 - (doc.embedding <=> query_embedding) as similarity\n FROM {{ $('Chercher nom dernier client').item.json['Dernier client'] }}_documents doc\n WHERE \n CASE \n WHEN filter != '{}' THEN doc.metadata @> filter\n ELSE TRUE\n END\n ORDER BY doc.embedding <=> query_embedding\n LIMIT match_count;\nEND;\n$$;\n\n-- Grant permissions\nGRANT EXECUTE ON FUNCTION match_{{ $json.chatInput }}_documents TO authenticated;\nGRANT EXECUTE ON FUNCTION match_{{ $json.chatInput }}_documents TO anon;",
"options": {},
"operation": "executeQuery"
},
"credentials": {
"postgres": {
"name": "<your credential>"
}
},
"typeVersion": 2.5
},
{
"id": "bba201fe-1734-40ee-9fc0-05e2b8033b99",
"name": "When Chat Message Received",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
3264,
1696
],
"parameters": {
"options": {}
},
"typeVersion": 1.3
},
{
"id": "dce2f1ce-984d-464c-a946-48cac48cd236",
"name": "Sticky Note11",
"type": "n8n-nodes-base.stickyNote",
"position": [
6352,
1984
],
"parameters": {
"color": 7,
"width": 432,
"height": 320,
"content": "## Update tabular schema metadata\n\nAfter summarisation, sets the schema and data fields and upserts the inferred column schema back into the document metadata table in Postgres."
},
"typeVersion": 1
},
{
"id": "a0e1b511-1632-42ea-8129-26863852466d",
"name": "Sticky Note13",
"type": "n8n-nodes-base.stickyNote",
"position": [
4560,
1200
],
"parameters": {
"width": 816,
"height": 336,
"content": "## Need more advanced automation solutions? Contact us for custom enterprise workflows!\n\n# Growth-AI.fr\n\n## https://www.linkedin.com/in/allanvaccarizi/\n## https://www.linkedin.com/in/hugo-marinier-%F0%9F%A7%B2-6537b633/"
},
"typeVersion": 1
},
{
"id": "5704ead4-1f7d-47df-b8f9-c5e1128ca0fd",
"name": "Sticky Note16",
"type": "n8n-nodes-base.stickyNote",
"position": [
5408,
1168
],
"parameters": {
"width": 1024,
"height": 400,
"content": ""
},
"typeVersion": 1
}
],
"connections": {
"OpenAI Embeddings": {
"ai_embedding": [
[
{
"node": "Insert Embeddings to Vectorstore",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Load Document Data": {
"ai_document": [
[
{
"node": "Insert Embeddings to Vectorstore",
"type": "ai_document",
"index": 0
}
]
]
},
"Route by File Type": {
"main": [
[
{
"node": "Extract Text from PDF",
"type": "main",
"index": 0
}
],
[
{
"node": "Extract Data from Excel",
"type": "main",
"index": 0
}
],
[
{
"node": "Extract Data from CSV",
"type": "main",
"index": 0
}
],
[
{
"node": "Extract Text from Document",
"type": "main",
"index": 0
}
]
]
},
"Build Schema and Data": {
"main": [
[
{
"node": "Update Document Schema in DB",
"type": "main",
"index": 0
}
]
]
},
"Extract Data from CSV": {
"main": [
[
{
"node": "Aggregate Tabular Data",
"type": "main",
"index": 0
},
{
"node": "Insert Table Rows to DB",
"type": "main",
"index": 0
}
]
]
},
"Extract Text from PDF": {
"main": [
[
{
"node": "Insert Embeddings to Vectorstore",
"type": "main",
"index": 0
}
]
]
},
"Loop Over Drive Files": {
"main": [
[],
[
{
"node": "Set File Metadata Fields",
"type": "main",
"index": 0
}
]
]
},
"Aggregate Tabular Data": {
"main": [
[
{
"node": "Summarize Tabular Data",
"type": "main",
"index": 0
}
]
]
},
"Split Text into Chunks": {
"ai_textSplitter": [
[
{
"node": "Load Document Data",
"type": "ai_textSplitter",
"index": 0
}
]
]
},
"Summarize Tabular Data": {
"main": [
[
{
"node": "Build Schema and Data",
"type": "main",
"index": 0
},
{
"node": "Insert Embeddings to Vectorstore",
"type": "main",
"index": 0
}
]
]
},
"Extract Data from Excel": {
"main": [
[
{
"node": "Aggregate Tabular Data",
"type": "main",
"index": 0
},
{
"node": "Insert Table Rows to DB",
"type": "main",
"index": 0
}
]
]
},
"When Drive File Created": {
"main": [
[
{
"node": "Loop Over Drive Files",
"type": "main",
"index": 0
}
]
]
},
"When Drive File Updated": {
"main": [
[
{
"node": "Loop Over Drive Files",
"type": "main",
"index": 0
}
]
]
},
"Download File from Drive": {
"main": [
[
{
"node": "Route by File Type",
"type": "main",
"index": 0
}
]
]
},
"Set File Metadata Fields": {
"main": [
[
{
"node": "Delete Old Doc Rows in Supabase",
"type": "main",
"index": 0
}
]
]
},
"Extract Text from Document": {
"main": [
[
{
"node": "Insert Embeddings to Vectorstore",
"type": "main",
"index": 0
}
]
]
},
"When Chat Message Received": {
"main": [
[
{
"node": "Create Docs Table and Match Fn",
"type": "main",
"index": 0
}
]
]
},
"Create Docs Table and Match Fn": {
"main": [
[
{
"node": "Create Document Metadata Table",
"type": "main",
"index": 0
}
]
]
},
"Create Document Metadata Table": {
"main": [
[
{
"node": "Create Document Rows Table",
"type": "main",
"index": 0
}
]
]
},
"Insert Document Metadata to DB": {
"main": [
[
{
"node": "Download File from Drive",
"type": "main",
"index": 0
}
]
]
},
"Delete Old Doc Rows in Supabase": {
"main": [
[
{
"node": "Delete Old Data Rows in Supabase",
"type": "main",
"index": 0
}
]
]
},
"Delete Old Data Rows in Supabase": {
"main": [
[
{
"node": "Insert Document Metadata to DB",
"type": "main",
"index": 0
}
]
]
},
"Insert Embeddings to Vectorstore": {
"main": [
[
{
"node": "Loop Over Drive Files",
"type": "main",
"index": 0
}
]
]
}
}
}
Credentials you'll need
Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.
googleDriveOAuth2ApiopenAiApipostgressupabaseApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
📺 Full walkthrough video: https://youtu.be/r5kN_la0O7I
Source: https://n8n.io/workflows/8916/ — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
Chat with docs - 5minAI New version. Uses httpRequest, documentDefaultDataLoader, textSplitterRecursiveCharacterTextSplitter, embeddingsOpenAi. Event-driven trigger; 62 nodes.
HTTP Request, Document Default Data Loader, Text Splitter Recursive Character Text Splitter +10
I prepared a detailed guide that illustrates the entire process of building an AI agent using Supabase and Google Drive within N8N workflows.
HTTP Request, Document Default Data Loader, Text Splitter Recursive Character Text Splitter +10
RAG AI Agent Template V5. Uses lmChatOpenAi, documentDefaultDataLoader, embeddingsOpenAi, googleDrive. Event-driven trigger; 56 nodes.
OpenAI Chat, Document Default Data Loader, OpenAI Embeddings +12
Wordpress Ai Chatbot To Enhance User Experience With Supabase And Openai. Uses manualTrigger, embeddingsOpenAi, documentDefaultDataLoader, textSplitterTokenSplitter. Event-driven trigger; 53 nodes.
OpenAI Embeddings, Document Default Data Loader, Text Splitter Token Splitter +9
RAG & GenAI App With WordPress Content. Uses manualTrigger, embeddingsOpenAi, documentDefaultDataLoader, textSplitterTokenSplitter. Event-driven trigger; 53 nodes.
OpenAI Embeddings, Document Default Data Loader, Text Splitter Token Splitter +9