Abdulrahman Alhalabi This workflow corresponds to n8n.io template #7892 — we link there as the canonical source.
This workflow follows the Google Docs → HTTP Request 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
},
"name": "Extract Arabic Text from PDFs with Mistral OCR & Telegram Bot to Google Docs",
"nodes": [
{
"id": "workflow-start-sticky",
"name": "\ud83d\udccb Workflow Overview",
"type": "n8n-nodes-base.stickyNote",
"position": [
-480,
720
],
"parameters": {
"width": 320,
"height": 240,
"content": "## Arabic PDF OCR Telegram Bot\n\nThis workflow:\n1. Receives PDF files via Telegram\n2. Uses Mistral AI OCR to extract Arabic text\n3. Creates a Google Doc with extracted content\n4. Sends progress updates to user\n\n**Requirements:**\n- Telegram Bot API credentials\n- Mistral AI API credentials \n- Google Docs API credentials"
},
"typeVersion": 1
},
{
"id": "3067ee6f-21dc-4206-a087-629a1ec2b484",
"name": "Download Document from Telegram",
"type": "n8n-nodes-base.telegram",
"position": [
224,
864
],
"parameters": {
"fileId": "={{ $json.message.document.file_id }}",
"resource": "file",
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "2130cb79-a8ac-4ab1-b432-7d6bf3996715",
"name": "Telegram Bot Trigger",
"type": "n8n-nodes-base.telegramTrigger",
"position": [
-240,
880
],
"parameters": {
"updates": [
"message"
],
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "e5980bbd-fa94-46e6-aa2d-d8c3768082a7",
"name": "Check If Document Attached",
"type": "n8n-nodes-base.if",
"position": [
-16,
880
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "f514a6e8-30b6-4662-9827-3487ca7edbb3",
"operator": {
"type": "string",
"operation": "exists",
"singleValue": true
},
"leftValue": "={{ $json.message.document.file_name }}",
"rightValue": ""
}
]
}
},
"typeVersion": 2.2
},
{
"id": "validation-sticky",
"name": "\ud83d\udd0d Document Validation",
"type": "n8n-nodes-base.stickyNote",
"position": [
-16,
760
],
"parameters": {
"width": 200,
"height": 80,
"content": "Checks if the Telegram message contains a document attachment. Only PDF files should be processed."
},
"typeVersion": 1
},
{
"id": "138f927c-073f-4b90-a54c-2421ae98def0",
"name": "Upload PDF to Mistral AI",
"type": "n8n-nodes-base.httpRequest",
"position": [
480,
1104
],
"parameters": {
"url": "https://api.mistral.ai/v1/files",
"method": "POST",
"options": {},
"sendBody": true,
"contentType": "multipart-form-data",
"authentication": "genericCredentialType",
"bodyParameters": {
"parameters": [
{
"name": "purpose",
"value": "ocr"
},
{
"name": "file",
"parameterType": "formBinaryData",
"inputDataFieldName": "=data"
}
]
},
"genericAuthType": "httpHeaderAuth"
},
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "mistral-upload-sticky",
"name": "\ud83d\udce4 Mistral AI Upload",
"type": "n8n-nodes-base.stickyNote",
"position": [
480,
1000
],
"parameters": {
"width": 200,
"height": 80,
"content": "Uploads the PDF file to Mistral AI's file storage for OCR processing. Returns a file ID for subsequent operations."
},
"typeVersion": 1
},
{
"id": "b786de5e-14a0-4332-b386-682cd2303cad",
"name": "Get Mistral Signed URL",
"type": "n8n-nodes-base.httpRequest",
"position": [
704,
992
],
"parameters": {
"url": "=https://api.mistral.ai/v1/files/{{ $json.id }}/url",
"options": {},
"sendQuery": true,
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"queryParameters": {
"parameters": [
{
"name": "expiry",
"value": "24"
}
]
}
},
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "e9a16218-816e-4c05-b0d6-4bea6b3d44b8",
"name": "Process OCR with Mistral",
"type": "n8n-nodes-base.httpRequest",
"position": [
944,
912
],
"parameters": {
"url": "https://api.mistral.ai/v1/ocr",
"method": "POST",
"options": {},
"jsonBody": "={\n \"model\": \"mistral-ocr-latest\",\n \"document\": {\n \"type\": \"document_url\",\n \"document_url\": \"{{ $json.url }}\"\n },\n \"include_image_base64\": true\n}",
"sendBody": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth"
},
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "ocr-processing-sticky",
"name": "\ud83e\udd16 OCR Processing",
"type": "n8n-nodes-base.stickyNote",
"position": [
944,
800
],
"parameters": {
"width": 200,
"height": 80,
"content": "Mistral AI processes the PDF and extracts text using OCR. The response includes markdown-formatted text organized by pages."
},
"typeVersion": 1
},
{
"id": "20911406-a0ed-4d0a-9e21-5b2d502bf6b4",
"name": "Parse OCR Results by Page",
"type": "n8n-nodes-base.code",
"position": [
1200,
912
],
"parameters": {
"jsCode": "// Extract pages from OCR results and format for processing\nconst pages = items[0].json.pages || [];\nconst output = [];\n\nfor (const page of pages) {\n // page.index is your page number (0-based). Add +1 for 1-based numbering\n const pageNumber = page.index+1;\n const content = page.markdown; // Extract markdown content\n const images = page.images;\n \n output.push({\n json: { pageNumber, content },\n });\n}\n\nreturn output;\n"
},
"typeVersion": 2
},
{
"id": "485286ee-6874-4913-b9a0-55bc150f371b",
"name": "Update Google Doc with Content",
"type": "n8n-nodes-base.googleDocs",
"position": [
2144,
848
],
"parameters": {
"actionsUi": {
"actionFields": [
{
"text": "={{ \n $('Aggregate OCR Results').item.json.content.map((c, i) => \n `${c}\\n\\n(Page Number: ${$('Aggregate OCR Results').item.json.pageNumber[i]})`\n ).join('\\n\\n--------\\n\\n')\n}}\n\n",
"action": "insert"
}
]
},
"operation": "update",
"documentURL": "={{ $json.id }}"
},
"credentials": {
"googleDocsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 2
},
{
"id": "e63eac1d-a055-44b5-acf4-6f955d8b843d",
"name": "Create New Google Doc",
"type": "n8n-nodes-base.googleDocs",
"position": [
1664,
912
],
"parameters": {
"title": "=OCR Result from {{ $('Telegram Bot Trigger').item.json.message.document.file_name }}",
"folderId": "1ZJzZimxzxtlq--x2BxwgBLQ5PMJ96f2s"
},
"credentials": {
"googleDocsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 2
},
{
"id": "google-docs-sticky",
"name": "\ud83d\udcc4 Google Docs Creation",
"type": "n8n-nodes-base.stickyNote",
"position": [
1664,
800
],
"parameters": {
"width": 200,
"height": 80,
"content": "Creates a new Google Doc with the extracted text content, organized by page numbers for easy reference."
},
"typeVersion": 1
},
{
"id": "87ca83dd-d76c-4837-84b4-420147788bfb",
"name": "Process Document Updates",
"type": "n8n-nodes-base.splitInBatches",
"position": [
1872,
768
],
"parameters": {
"options": {},
"batchSize": "=1"
},
"typeVersion": 3
},
{
"id": "d55b3813-8b0d-46c6-a629-b24f3b8a9b38",
"name": "Aggregate OCR Results",
"type": "n8n-nodes-base.aggregate",
"position": [
1440,
912
],
"parameters": {
"options": {},
"fieldsToAggregate": {
"fieldToAggregate": [
{
"fieldToAggregate": "=pageNumber"
},
{
"fieldToAggregate": "content"
}
]
}
},
"typeVersion": 1
},
{
"id": "0ea6ad36-f231-4eb2-9f67-1c17738e7c8f",
"name": "Send Document Link to User",
"type": "n8n-nodes-base.telegram",
"position": [
2384,
720
],
"parameters": {
"text": "=<a href=\"https://docs.google.com/document/d/{{ $json.documentId }}\">{{ $('Create New Google Doc').item.json.name }}</a>\n",
"chatId": "={{ $('Telegram Bot Trigger').item.json.message.chat.id }}",
"additionalFields": {
"parse_mode": "HTML",
"appendAttribution": false,
"message_thread_id": 0,
"reply_to_message_id": 0,
"disable_web_page_preview": false
}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"notesInFlow": false,
"typeVersion": 1.2
},
{
"id": "313d1ec1-9529-41b6-ae95-0ea9427a1d33",
"name": "Request PDF File Format",
"type": "n8n-nodes-base.telegram",
"position": [
80,
1072
],
"parameters": {
"text": "Please send the file in PDF format",
"chatId": "={{ $('Telegram Bot Trigger').item.json.message.chat.id }}",
"additionalFields": {
"appendAttribution": false
}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"notesInFlow": false,
"typeVersion": 1.2
},
{
"id": "4790cab5-de75-4d68-a7a8-ec07bea7c7b0",
"name": "Status: File Received (1/5)",
"type": "n8n-nodes-base.telegram",
"position": [
400,
768
],
"parameters": {
"text": "File received successfully (1/5)",
"chatId": "={{ $('Telegram Bot Trigger').item.json.message.chat.id }}",
"additionalFields": {
"appendAttribution": false
}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"notesInFlow": false,
"typeVersion": 1.2
},
{
"id": "d793d21a-f248-4dec-8798-a4a37336a650",
"name": "Status: Sent to Processor (2/5)",
"type": "n8n-nodes-base.telegram",
"position": [
640,
768
],
"parameters": {
"text": "File sent to processor (2/5)",
"chatId": "={{ $('Telegram Bot Trigger').item.json.message.chat.id }}",
"additionalFields": {
"appendAttribution": false
}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"notesInFlow": false,
"typeVersion": 1.2
},
{
"id": "79cb13ce-e794-48e3-bb79-929aaa0be07d",
"name": "Status: File Signed (3/5)",
"type": "n8n-nodes-base.telegram",
"position": [
880,
752
],
"parameters": {
"text": "File signed for processing (3/5)",
"chatId": "={{ $('Telegram Bot Trigger').item.json.message.chat.id }}",
"additionalFields": {
"appendAttribution": false
}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"notesInFlow": false,
"typeVersion": 1.2
},
{
"id": "8787ffff-8643-416e-85ca-2dc3bdc22f22",
"name": "Status: Results Received (4/5)",
"type": "n8n-nodes-base.telegram",
"position": [
1120,
768
],
"parameters": {
"text": "OCR results received (4/5)",
"chatId": "={{ $('Telegram Bot Trigger').item.json.message.chat.id }}",
"additionalFields": {
"appendAttribution": false
}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"notesInFlow": false,
"typeVersion": 1.2
},
{
"id": "3dfb1769-9f47-4e39-8b48-0b9476a3b5ed",
"name": "Status: Creating Document (5/5)",
"type": "n8n-nodes-base.telegram",
"position": [
1584,
720
],
"parameters": {
"text": "Creating document after processing (5/5)",
"chatId": "={{ $('Telegram Bot Trigger').item.json.message.chat.id }}",
"additionalFields": {
"appendAttribution": false
}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"notesInFlow": false,
"typeVersion": 1.2
},
{
"id": "progress-updates-sticky",
"name": "\ud83d\udcc8 Progress Updates",
"type": "n8n-nodes-base.stickyNote",
"position": [
400,
640
],
"parameters": {
"width": 320,
"height": 80,
"content": "Users receive real-time progress updates via Telegram messages, showing the current step (1/5 through 5/5) in the OCR processing workflow."
},
"typeVersion": 1
},
{
"id": "final-result-sticky",
"name": "\u2705 Final Result",
"type": "n8n-nodes-base.stickyNote",
"position": [
2384,
600
],
"parameters": {
"width": 200,
"height": 80,
"content": "Users receive a clickable link to the Google Doc containing the extracted Arabic text, organized by page numbers."
},
"typeVersion": 1
}
],
"connections": {
"Telegram Bot Trigger": {
"main": [
[
{
"node": "Check If Document Attached",
"type": "main",
"index": 0
}
]
]
},
"Aggregate OCR Results": {
"main": [
[
{
"node": "Create New Google Doc",
"type": "main",
"index": 0
},
{
"node": "Status: Creating Document (5/5)",
"type": "main",
"index": 0
}
]
]
},
"Create New Google Doc": {
"main": [
[
{
"node": "Process Document Updates",
"type": "main",
"index": 0
}
]
]
},
"Get Mistral Signed URL": {
"main": [
[
{
"node": "Process OCR with Mistral",
"type": "main",
"index": 0
},
{
"node": "Status: File Signed (3/5)",
"type": "main",
"index": 0
}
]
]
},
"Process Document Updates": {
"main": [
[],
[
{
"node": "Update Google Doc with Content",
"type": "main",
"index": 0
}
]
]
},
"Process OCR with Mistral": {
"main": [
[
{
"node": "Parse OCR Results by Page",
"type": "main",
"index": 0
},
{
"node": "Status: Results Received (4/5)",
"type": "main",
"index": 0
}
]
]
},
"Upload PDF to Mistral AI": {
"main": [
[
{
"node": "Get Mistral Signed URL",
"type": "main",
"index": 0
},
{
"node": "Status: Sent to Processor (2/5)",
"type": "main",
"index": 0
}
]
]
},
"Parse OCR Results by Page": {
"main": [
[
{
"node": "Aggregate OCR Results",
"type": "main",
"index": 0
}
]
]
},
"Check If Document Attached": {
"main": [
[
{
"node": "Download Document from Telegram",
"type": "main",
"index": 0
}
],
[
{
"node": "Request PDF File Format",
"type": "main",
"index": 0
}
]
]
},
"Update Google Doc with Content": {
"main": [
[
{
"node": "Process Document Updates",
"type": "main",
"index": 0
},
{
"node": "Send Document Link to User",
"type": "main",
"index": 0
}
]
]
},
"Download Document from Telegram": {
"main": [
[
{
"node": "Upload PDF to Mistral AI",
"type": "main",
"index": 0
},
{
"node": "Status: File Received (1/5)",
"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.
googleDocsOAuth2ApihttpHeaderAuthtelegramApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Receive PDF Files - Users send PDF documents via Telegram to the bot OCR Processing - Mistral AI's OCR service extracts Arabic text from document pages Text Organization - Processes and formats extracted content with page numbers Create Google Doc - Generates a formatted…
Source: https://n8n.io/workflows/7892/ — 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.
Description Turn your Telegram bot into a powerful OCR (Optical Character Recognition) tool. This workflow allows you to send any image (like a screenshot, a photo of a document, or a picture of a sig
Telegram Trigger, Telegram, HTTP Request
Social Media Audio Extractor. Uses telegramTrigger, telegram, openAi, httpRequest. Event-driven trigger; 31 nodes.
Telegram Trigger, Telegram, OpenAI +2
Transform your receipt management with this comprehensive n8n workflow that automatically processes receipts through Telegram, extracts transaction data using AI, and stores it across multiple platfor
Telegram Trigger, Telegram, HTTP Request +4
Flow1. Uses telegram, openAi, telegramTrigger, httpRequest. Event-driven trigger; 10 nodes.
Telegram, OpenAI, Telegram Trigger +1
This n8n template provides a complete solution for Optical Character Recognition (OCR) of image and PDF files directly within Telegram
HTTP Request, Telegram