๐Ÿ”ฌ Extract text from images & PDFs via Telegram with Mistral OCR to Markdown

โšก 2,556 views ยท ๐Ÿ”ฌ Document Extraction & Analysis

Description

This n8n template provides a complete solution for Optical Character Recognition (OCR) of image and PDF files directly within Telegram


Users can simply send PNG, JPEG, or PDF documents to your Telegram bot, and the workflow will process them, extract text using Mistral OCR, and return the content as a downloadable Markdown (.md) text file.

Key Features & How it Works:

This template is ideal for digitizing documents on the go, extracting text from scanned files, or converting image-based content into versatile, searchable text.

Getting Started

To get this powerful OCR bot up and running, follow these two main steps:

  1. Set Up Your Telegram Bot: First, youโ€™ll need to configure your Telegram bot and its webhooks. Follow the instructions detailed in the Telegram Bot Webhook Setup section to create your bot, obtain its API token, and set up the necessary webhook URLs.

  2. Configure Bot Settings: Next, youโ€™ll need to define key operational parameters for your bot. Proceed to the Settings Configuration section and populate the variables according to your preferences, including options for whitelist access.

๐Ÿ”— Nodes Used

HTTP Request, Webhook, Telegram, Convert to File

๐Ÿ“ฅ Import

Download workflow.json and import into n8n: Workflow menu โ†’ Import from File

๐Ÿ“– Importing guide ยท ๐Ÿ”‘ Credential setup