Extract Arabic text from PDFs with Mistral OCR, Telegram Bot & Google Docs
Ready for 3.0Ready for 3.0. This template uses no nodes that n8n 3.0 removes. No removed nodes, versions or helpers found. Static check, last run 2026-10-19.
What this workflow does
This workflow has 18 nodes and runs on Telegram events (message). Along the way it connects Telegram and Google Docs. It also calls api.mistral.ai over HTTP.
How it runs
Trigger: On Telegram events (message).
- Check If Document Attached (If): checks a condition and branches into true / false
- Download Document from Telegram (Telegram): work with file
- Request PDF File Format (Telegram): uses Telegram
- Upload PDF to Mistral AI (HTTP Request): calls api.mistral.ai (POST)
- Status: File Received (1/5) (Telegram): uses Telegram
- Get Mistral Signed URL (HTTP Request): calls an HTTP API
- Status: Sent to Processor (2/5) (Telegram): uses Telegram
- Process OCR with Mistral (HTTP Request): calls api.mistral.ai (POST)
- Status: File Signed (3/5) (Telegram): uses Telegram
- Parse OCR Results by Page (Code): runs custom JavaScript code
…plus 7 more steps. See the full node list below.
Services it uses
HTTP calls to: api.mistral.ai
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (8)
- Telegram
n8n-nodes-base.telegram - Telegram Trigger
n8n-nodes-base.telegramTrigger - If
n8n-nodes-base.if - HTTP Request
n8n-nodes-base.httpRequest - Code
n8n-nodes-base.code - Google Docs
n8n-nodes-base.googleDocs - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - Aggregate
n8n-nodes-base.aggregate
From the author
Arabic OCR Telegram Bot How it Works 1. Receive PDF Files - Users send PDF documents via Telegram to the bot 2. OCR Processing - Mistral AI's OCR service extracts Arabic text from document pages 3. Text Organization - Processes and formats extracted content…