Meelioo This workflow corresponds to n8n.io template #8860 — we link there as the canonical source.
This workflow follows the Agent → Chat Trigger 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": "1bb5bca6-10c4-4d9e-9435-3400fe80d2aa",
"name": "Default Data Loader",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
-960,
-1648
],
"parameters": {
"loader": "pdfLoader",
"options": {},
"dataType": "binary",
"textSplittingMode": "custom"
},
"typeVersion": 1.1
},
{
"id": "5759f41a-5c02-4d3d-8bee-1da84290bd39",
"name": "Azure OpenAI Chat Model1",
"type": "@n8n/n8n-nodes-langchain.lmChatAzureOpenAi",
"position": [
304,
-2048
],
"parameters": {
"model": "gpt-4.1-mini",
"options": {
"temperature": 0.1
}
},
"credentials": {
"azureOpenAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "587a276a-5405-418f-8c19-462cdd10fb36",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
304,
-2256
],
"parameters": {
"options": {
"systemMessage": "* You are a helpful assistant(A workflow in n8n) called Mookie.\n\n* Always retrieve your information from the vector store tool, called ''Postgres PGVector Store2''.\n\n* Do not answer irrelevant questions which their answer is not found in the vector store.\n\n* You must not hallucinate or generate false information. Use the vector store as your only source of information."
}
},
"typeVersion": 2.2
},
{
"id": "8538610d-7484-4096-affa-5855d3825d36",
"name": "Send PDF File",
"type": "n8n-nodes-base.httpRequest",
"position": [
-656,
-2176
],
"parameters": {
"url": "https://your_n8n_instance_url/webhook/ingest-pdf",
"method": "POST",
"options": {},
"sendBody": true,
"contentType": "multipart-form-data",
"sendHeaders": true,
"bodyParameters": {
"parameters": [
{
"name": "file",
"parameterType": "formBinaryData",
"inputDataFieldName": "data"
}
]
},
"headerParameters": {
"parameters": [
{
"name": "Content-Type",
"value": "application/pdf"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "e39c3c95-a9d0-4451-8ae3-92ff9b78eb50",
"name": "Embeddings Mistral Cloud",
"type": "@n8n/n8n-nodes-langchain.embeddingsMistralCloud",
"position": [
-928,
-1344
],
"parameters": {
"options": {}
},
"credentials": {
"mistralCloudApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "ea109c37-e951-4947-9b4e-5f24dcac0dfa",
"name": "Postgres PGVector Store",
"type": "@n8n/n8n-nodes-langchain.vectorStorePGVector",
"position": [
-928,
-1824
],
"parameters": {
"mode": "insert",
"options": {}
},
"credentials": {
"postgres": {
"name": "<your credential>"
}
},
"typeVersion": 1.3
},
{
"id": "32bcfb09-99d7-4883-b0bb-7c51b294dfff",
"name": "Loop Over Items",
"type": "n8n-nodes-base.splitInBatches",
"position": [
-1040,
-2256
],
"parameters": {
"options": {}
},
"typeVersion": 3
},
{
"id": "dc536bb3-09b4-4e99-9170-6d5ce7536590",
"name": "List All File Names",
"type": "n8n-nodes-base.googleDrive",
"position": [
-1232,
-2256
],
"parameters": {
"filter": {},
"options": {},
"resource": "fileFolder",
"returnAll": true,
"queryString": "myfiles"
},
"credentials": {
"googleDriveOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 3
},
{
"id": "f71096a3-a5af-4567-95ce-a63869849975",
"name": "Download Corresponding File",
"type": "n8n-nodes-base.googleDrive",
"position": [
-848,
-2176
],
"parameters": {
"fileId": {
"__rl": true,
"mode": "id",
"value": "={{ $('Loop Over Items').item.json.id }}"
},
"options": {
"binaryPropertyName": "data"
},
"operation": "download"
},
"credentials": {
"googleDriveOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 3
},
{
"id": "c5e62513-0da7-4fb3-a33b-50c0b876948d",
"name": "Run Ingestion",
"type": "n8n-nodes-base.manualTrigger",
"position": [
-1424,
-2256
],
"parameters": {},
"typeVersion": 1
},
{
"id": "d73b903d-b030-42b7-a1f0-44eb087ff017",
"name": "PDF Ingest Webhook",
"type": "n8n-nodes-base.webhook",
"position": [
-1120,
-1824
],
"parameters": {
"path": "ingest-pdf",
"options": {},
"httpMethod": "POST"
},
"typeVersion": 1
},
{
"id": "673e5655-924d-4b87-8b9d-a8d0d92fbea3",
"name": "Token Splitter",
"type": "@n8n/n8n-nodes-langchain.textSplitterTokenSplitter",
"position": [
-960,
-1488
],
"parameters": {
"chunkSize": 800,
"chunkOverlap": 80
},
"typeVersion": 1
},
{
"id": "22ad6959-4b23-40ca-97d6-a1780e93b81e",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1504,
-2336
],
"parameters": {
"color": 5,
"width": 1184,
"height": 384,
"content": "## LOAD FILES & SEND THEM TO WEBHOOK"
},
"typeVersion": 1
},
{
"id": "152563cd-493f-4862-b1df-9ce36d25c2c1",
"name": "Sticky Note5",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1504,
-1888
],
"parameters": {
"width": 1184,
"height": 352,
"content": "## RECEIVE FILES AND INGEST THEM"
},
"typeVersion": 1
},
{
"id": "7025aca3-98b9-4578-87a4-964fa1404d09",
"name": "Postgres PGVector Store2",
"type": "@n8n/n8n-nodes-langchain.vectorStorePGVector",
"position": [
368,
-1760
],
"parameters": {
"mode": "retrieve-as-tool",
"topK": 5,
"options": {},
"toolDescription": "=Work with data in Postgres Database with PGvector extension insalled. Retreive documents corresponding to the user request/question and prepare your answer based solely on these documents."
},
"credentials": {
"postgres": {
"name": "<your credential>"
}
},
"typeVersion": 1.3
},
{
"id": "04f31fae-759f-4568-9c1c-d0bb70bcb9a2",
"name": "Embeddings Mistral Cloud2",
"type": "@n8n/n8n-nodes-langchain.embeddingsMistralCloud",
"position": [
368,
-1600
],
"parameters": {
"options": {}
},
"credentials": {
"mistralCloudApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "c1e2f23a-661b-4f9f-841e-45e7a20fcb47",
"name": "Telegram Trigger",
"type": "n8n-nodes-base.telegramTrigger",
"position": [
-1376,
-1072
],
"parameters": {
"updates": [
"message"
],
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "d1b46c07-aed2-4a8d-8cf7-8c32a9f5d99f",
"name": "Azure OpenAI Chat Model3",
"type": "@n8n/n8n-nodes-langchain.lmChatAzureOpenAi",
"position": [
144,
-880
],
"parameters": {
"model": "gpt-4.1-mini",
"options": {
"temperature": 0.1
}
},
"credentials": {
"azureOpenAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "24829661-5ed7-42fd-a919-dd92aa429f79",
"name": "AI Agent2",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
144,
-1088
],
"parameters": {
"text": "={{ $json.message.text }}",
"options": {
"systemMessage": "* You are a helpful assistant(A workflow in n8n) called Mookie.\n\n* Always retrieve your information from the vector store tool, called ''Postgres PGVector Store3''.\n\n* Do not answer irrelevant questions which their answer is not found in the vector store.\n\n* You must not hallucinate or generate false information. Use the vector store as your only source of information."
},
"promptType": "define"
},
"typeVersion": 2.2
},
{
"id": "eef6da5b-38d7-44b1-9fce-368aba504860",
"name": "Postgres PGVector Store3",
"type": "@n8n/n8n-nodes-langchain.vectorStorePGVector",
"position": [
208,
-576
],
"parameters": {
"mode": "retrieve-as-tool",
"topK": 5,
"options": {},
"toolDescription": "Work with data in Postgres Database with PGvector extension insalled. Retreive documents corresponding to the user request/question and prepare your answer based solely on these documents."
},
"credentials": {
"postgres": {
"name": "<your credential>"
}
},
"typeVersion": 1.3
},
{
"id": "61176586-9a2e-45b9-8592-bf86c989ebf7",
"name": "Embeddings Mistral Cloud3",
"type": "@n8n/n8n-nodes-langchain.embeddingsMistralCloud",
"position": [
208,
-416
],
"parameters": {
"options": {}
},
"credentials": {
"mistralCloudApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "28a0b6b9-8be9-491b-83e9-54ecceee4e87",
"name": "Send a Text Message",
"type": "n8n-nodes-base.telegram",
"position": [
448,
-1088
],
"parameters": {
"text": "={{ $json.output }}",
"chatId": "={{ $('Telegram Trigger').item.json.message.from.id }}",
"additionalFields": {
"appendAttribution": false
}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "6eb22528-4c87-44cb-a152-7abeb45c43ff",
"name": "Simple Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
240,
-736
],
"parameters": {
"sessionKey": "={{ $('Telegram Trigger').item.json.message.from.id }}",
"sessionIdType": "customKey"
},
"typeVersion": 1.3
},
{
"id": "f381d0a0-7b41-489c-9499-467e77620c47",
"name": "Sticky Note6",
"type": "n8n-nodes-base.stickyNote",
"disabled": true,
"position": [
-16,
-2336
],
"parameters": {
"color": 6,
"width": 704,
"height": 304,
"content": "# CANVAS CHAT"
},
"typeVersion": 1
},
{
"id": "a1086f33-fda6-458a-b458-14e15064ddaa",
"name": "Sticky Note7",
"type": "n8n-nodes-base.stickyNote",
"disabled": true,
"position": [
-1504,
-1152
],
"parameters": {
"color": 6,
"width": 2192,
"height": 544,
"content": "# TELEGRAM CHAT"
},
"typeVersion": 1
},
{
"id": "b94c09c3-6451-4a5e-a85b-1aa497571d4e",
"name": "Send Refusal Message",
"type": "n8n-nodes-base.telegram",
"position": [
-864,
-768
],
"parameters": {
"text": "=Sorry, I couldn't understand. Could you rephrase your request?",
"chatId": "={{ $('Telegram Trigger').item.json.message.from.id }}",
"additionalFields": {
"appendAttribution": false
}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "909b0739-2bb6-4ab3-ad66-a5006b1cbf62",
"name": "Simple Memory2",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
400,
-1904
],
"parameters": {},
"typeVersion": 1.3
},
{
"id": "885d7ab7-769c-482f-9ccb-b5351bddd428",
"name": "Chat Trigger",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
80,
-2256
],
"parameters": {
"options": {}
},
"typeVersion": 1.3
},
{
"id": "14619b70-8499-49dc-9a0d-0c61e62b3ea5",
"name": "If Text Message Received",
"type": "n8n-nodes-base.if",
"position": [
-1216,
-1072
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "ae096eaf-c284-4cbe-b68c-e72f4c503f93",
"operator": {
"type": "string",
"operation": "exists",
"singleValue": true
},
"leftValue": "={{ $('Telegram Trigger').item.json.message.text }}",
"rightValue": ""
}
]
}
},
"typeVersion": 2.2
},
{
"id": "ad652cab-041e-445d-9f60-8feacba30c18",
"name": "If PDF File Received",
"type": "n8n-nodes-base.if",
"position": [
-1040,
-848
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "20a2d7ce-d67d-4efe-ba28-151edfeea6a5",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $('Telegram Trigger').item.json.message.document.mime_type }}",
"rightValue": "=application/pdf"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "ff0b610a-5a35-4602-9df7-f40fe58d7c3a",
"name": "Send Downloaded PDF File",
"type": "n8n-nodes-base.httpRequest",
"position": [
-320,
-1008
],
"parameters": {
"url": "https://your_n8n_instance_url/webhook/ingest-pdf",
"method": "POST",
"options": {},
"sendBody": true,
"contentType": "multipart-form-data",
"sendHeaders": true,
"bodyParameters": {
"parameters": [
{
"name": "file",
"parameterType": "formBinaryData",
"inputDataFieldName": "data"
}
]
},
"headerParameters": {
"parameters": [
{
"name": "Content-Type",
"value": "application/pdf"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "5c5d0290-6975-4bab-bd36-34c51b43c3b6",
"name": "Download PDF File",
"type": "n8n-nodes-base.telegram",
"position": [
-512,
-1008
],
"parameters": {
"fileId": "={{ $('Telegram Trigger').item.json.message.document.file_id }}",
"resource": "file",
"additionalFields": {
"mimeType": "application/pdf"
}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "f8ed9971-bea3-422b-a724-3bf66f7fc1ce",
"name": "Approve Ingestion",
"type": "n8n-nodes-base.telegram",
"position": [
-864,
-928
],
"parameters": {
"chatId": "={{ $('Telegram Trigger').item.json.message.from.id }}",
"message": "I will ingest the PDF file you provided. \n\nResuming ingestion upon approval.",
"options": {
"appendAttribution": false
},
"operation": "sendAndWait"
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "adda50a8-624a-4dde-ba84-478ae3e5fbfd",
"name": "If User Approved",
"type": "n8n-nodes-base.if",
"position": [
-688,
-928
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "20a2d7ce-d67d-4efe-ba28-151edfeea6a5",
"operator": {
"type": "boolean",
"operation": "true",
"singleValue": true
},
"leftValue": "={{ $json.data.approved }}",
"rightValue": "=application/pdf"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "3448fda2-4133-475d-97c4-683ab18e7e8d",
"name": "User Dissapproved",
"type": "n8n-nodes-base.telegram",
"position": [
-512,
-848
],
"parameters": {
"text": "=Terminated Ingestion.",
"chatId": "={{ $('Telegram Trigger').item.json.message.from.id }}",
"additionalFields": {
"appendAttribution": false
}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "a040371b-5896-4d2c-b80a-0614e3d6093c",
"name": "Send Finished Message",
"type": "n8n-nodes-base.telegram",
"position": [
-112,
-1008
],
"parameters": {
"text": "=Ingestion Completed Successfully.",
"chatId": "={{ $('Telegram Trigger').item.json.message.from.id }}",
"additionalFields": {
"appendAttribution": false
}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "b172fc47-6784-4c5d-841c-d3f0b52b059c",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-2112,
-2336
],
"parameters": {
"color": 4,
"width": 576,
"height": 1040,
"content": "# Credentials\nThis workflow requires 5 different credential configurations to connect with external services. Set up each credential in n8n's credential manager before activating the workflow.\n1. Azure OpenAI API\nUsed for: GPT-4 language model powering the AI agents\nRequired fields:\n\nResource name (your Azure OpenAI resource)\nAPI key from Azure portal\nAPI version (use latest available)\nDeployment name for GPT-4 model\n\nSetup guide: https://docs.n8n.io/integrations/builtin/credentials/azureopenai/\n2. Mistral Cloud API\nUsed for: Text embeddings to convert documents into searchable vectors\nRequired fields:\n\nAPI key from Mistral AI platform\nModel selection (use default embedding model)\n\nSetup guide: https://docs.n8n.io/integrations/builtin/credentials/mistralcloud/\n3. PostgreSQL Database\nUsed for: Vector storage with PGVector extension for document retrieval\nRequired fields:\n\nHost, port, database name\nUsername and password\nSSL settings (recommended: require)\nPrerequisites: Install PGVector extension in your PostgreSQL database\n\nSetup guide: https://docs.n8n.io/integrations/builtin/credentials/postgres/\n4. Google Drive OAuth2 API\nUsed for: Automatic PDF ingestion from designated Google Drive folder\nRequired fields:\n\nClient ID and Client Secret from Google Cloud Console\nOAuth2 authorization flow completion\nPrerequisites: Enable Google Drive API in Google Cloud Console\n\nSetup guide: https://docs.n8n.io/integrations/builtin/credentials/google/\n5. Telegram Bot API\nUsed for: Chat interface and file uploads via Telegram\nRequired fields:\n\nBot token from @BotFather\nBot username\nPrerequisites: Create bot via @BotFather on Telegram\n\nSetup guide: https://docs.n8n.io/integrations/builtin/credentials/telegram/\nImportant: Test each credential after setup to ensure proper connectivity before running the workflow."
},
"typeVersion": 1
},
{
"id": "da165d33-406b-4bce-b521-040e97c4c4e7",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
736,
-2336
],
"parameters": {
"color": 4,
"width": 688,
"height": 1376,
"content": "# Start Using This Workflow\n\n## Quick Setup (5 minutes)\n\n### 1. Update Your URLs\n- Open **Send PDF File** and **Send Downloaded PDF File** nodes\n- Replace `https://your_n8n_instance_url/webhook/ingest-pdf` with your actual n8n webhook URL\n- Copy the URL from your **PDF Ingest Webhook** node\n\n### 2. Configure Google Drive\n- In **List All File Names** node, change \"myfiles\" to your folder name\n- Create a folder in Google Drive and add some PDFs for testing\n\n### 3. Database Setup\n- Ensure your PostgreSQL has PGVector extension installed\n- The workflow creates tables automatically\n\n## Testing Your Setup\n\n### Step 1: Test Document Ingestion\n1. **Manual test:** Click **Run Ingestion** to process Google Drive PDFs\n2. **Telegram test:** Send a PDF to your bot, approve when asked\n3. Both should show \"Ingestion Completed Successfully\"\n\n### Step 2: Test Chat Features\n1. **Ask questions** about your uploaded documents\n2. Try both Telegram chat and the canvas chat interface\n3. The bot should answer based on your documents and refuse irrelevant questions\n\n## Key Settings to Adjust\n\n- **Chunk Size (800):** Make smaller for precise answers, larger for more context\n- **TopK (5):** Increase if bot says \"no relevant documents found\"\n- **Temperature (0.1):** Keep low for factual responses\n- **System Message:** Customize how your assistant behaves\n\n## Common Issues & Fixes\n\n**Bot not responding?** Check your Telegram bot token and webhook URLs\n\n**Poor document retrieval?** Increase TopK value from 5 to 10\n\n**Ingestion failing?** Verify Google Drive folder permissions and PDF file formats\n\n**Out of context errors?** Your documents might be too large - try smaller PDFs first\n\n## Pro Tips\n\n- Start with 2-3 small, well-formatted PDFs\n- Ask specific questions rather than broad topics\n- Use the Google Drive auto-ingestion for bulk processing\n- Use Telegram for real-time document uploads and chat"
},
"typeVersion": 1
}
],
"connections": {
"AI Agent2": {
"main": [
[
{
"node": "Send a Text Message",
"type": "main",
"index": 0
}
]
]
},
"Chat Trigger": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"Run Ingestion": {
"main": [
[
{
"node": "List All File Names",
"type": "main",
"index": 0
}
]
]
},
"Send PDF File": {
"main": [
[
{
"node": "Loop Over Items",
"type": "main",
"index": 0
}
]
]
},
"Simple Memory": {
"ai_memory": [
[
{
"node": "AI Agent2",
"type": "ai_memory",
"index": 0
}
]
]
},
"Simple Memory2": {
"ai_memory": [
[
{
"node": "AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Token Splitter": {
"ai_textSplitter": [
[
{
"node": "Default Data Loader",
"type": "ai_textSplitter",
"index": 0
}
]
]
},
"Loop Over Items": {
"main": [
[],
[
{
"node": "Download Corresponding File",
"type": "main",
"index": 0
}
]
]
},
"If User Approved": {
"main": [
[
{
"node": "Download PDF File",
"type": "main",
"index": 0
}
],
[
{
"node": "User Dissapproved",
"type": "main",
"index": 0
}
]
]
},
"Telegram Trigger": {
"main": [
[
{
"node": "If Text Message Received",
"type": "main",
"index": 0
}
]
]
},
"Approve Ingestion": {
"main": [
[
{
"node": "If User Approved",
"type": "main",
"index": 0
}
]
]
},
"Download PDF File": {
"main": [
[
{
"node": "Send Downloaded PDF File",
"type": "main",
"index": 0
}
]
]
},
"PDF Ingest Webhook": {
"main": [
[
{
"node": "Postgres PGVector Store",
"type": "main",
"index": 0
}
]
]
},
"Default Data Loader": {
"ai_document": [
[
{
"node": "Postgres PGVector Store",
"type": "ai_document",
"index": 0
}
]
]
},
"List All File Names": {
"main": [
[
{
"node": "Loop Over Items",
"type": "main",
"index": 0
}
]
]
},
"If PDF File Received": {
"main": [
[
{
"node": "Approve Ingestion",
"type": "main",
"index": 0
}
],
[
{
"node": "Send Refusal Message",
"type": "main",
"index": 0
}
]
]
},
"Postgres PGVector Store": {
"main": [
[]
]
},
"Azure OpenAI Chat Model1": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Azure OpenAI Chat Model3": {
"ai_languageModel": [
[
{
"node": "AI Agent2",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Embeddings Mistral Cloud": {
"ai_embedding": [
[
{
"node": "Postgres PGVector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"If Text Message Received": {
"main": [
[
{
"node": "AI Agent2",
"type": "main",
"index": 0
}
],
[
{
"node": "If PDF File Received",
"type": "main",
"index": 0
}
]
]
},
"Postgres PGVector Store2": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Postgres PGVector Store3": {
"ai_tool": [
[
{
"node": "AI Agent2",
"type": "ai_tool",
"index": 0
}
]
]
},
"Send Downloaded PDF File": {
"main": [
[
{
"node": "Send Finished Message",
"type": "main",
"index": 0
}
]
]
},
"Embeddings Mistral Cloud2": {
"ai_embedding": [
[
{
"node": "Postgres PGVector Store2",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Embeddings Mistral Cloud3": {
"ai_embedding": [
[
{
"node": "Postgres PGVector Store3",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Download Corresponding File": {
"main": [
[
{
"node": "Send PDF File",
"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.
azureOpenAiApigoogleDriveOAuth2ApimistralCloudApipostgrestelegramApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This workflow creates an intelligent document assistant called "Mookie" that can answer questions based on your uploaded documents. Here's how it operates: Document Ingestion: The system can automatically load PDF files from Google Drive or accept PDFs uploaded directly through…
Source: https://n8n.io/workflows/8860/ — 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.
This comprehensive workflow bundle is designed as a powerful starter kit, enabling you to build a multi-functional AI assistant on Telegram. It seamlessly integrates AI-powered voice interactions, an
Telegram Trigger, Telegram, OpenAI +19
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
Auto repost job with RAG is a workflow designed to automatically extract, process, and publish job listings from monitored sources using Google Drive, OpenAI, Supabase, and WordPress. This integration
Google Drive, Supabase Vector Store, OpenAI Embeddings +12
RAG AI Agent Template V5. Uses lmChatOpenAi, documentDefaultDataLoader, embeddingsOpenAi, googleDrive. Event-driven trigger; 56 nodes.
OpenAI Chat, Document Default Data Loader, OpenAI Embeddings +12