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
automation_financial_recording. Uses telegramTrigger, telegram, googleGemini, lmChatGoogleGemini. Event-driven trigger; 35 nodes.
Telegram Trigger, Telegram, Google Gemini +4
automation_financial_recording. Uses telegramTrigger, telegram, googleGemini, lmChatGoogleGemini. Event-driven trigger; 35 nodes.
Telegram Trigger, Telegram, Google Gemini +4
automation_financial_recording. Uses telegramTrigger, telegram, googleGemini, lmChatGoogleGemini. Event-driven trigger; 35 nodes.
Telegram Trigger, Telegram, Google Gemini +4
Social Media Audio Extractor. Uses telegramTrigger, telegram, openAi, httpRequest. Event-driven trigger; 31 nodes.
Telegram Trigger, Telegram, OpenAI +2