This n8n workflow automates the process of extracting text from images received on Telegram. When a user sends a photo to a designated Telegram bot, the workflow automatically downloads the image, processes it through Gemini OCR, and sends the extracted text back to the user on Telegram.
Here’s how it works step-by-step:
1. **Telegram Trigger:** The workflow is initiated whenever a new message with a photo is received by the Telegram bot. It downloads the photo attached in the message.
2. **Clean Input Data:** The downloaded photo’s file ID and chat ID are extracted and prepared for further processing.
3. **Get File:** The bot retrieves the actual image file from Telegram using the file ID.
4. **Decode Image Data:** The image file is processed into binary data suitable for OCR.
5. **Gemini OCR Request:** The binary image data is sent via an HTTP POST request to the Gemini API, which performs OCR to extract text from the image.
6. **Send Result Back:** The recognized text from the OCR is sent back to the original Telegram chat, informing the user of the extracted content.
This workflow is ideal for automating the extraction of text from images sent via Telegram, useful in scenarios such as digitizing handwritten notes, processing scanned documents, or quick data entry from images.
Additional notes in the workflow provide detailed instructions and setup guidance for configuring the Gemini API and Telegram bot credentials, making it a comprehensive solution for image-to-text automation.
Reviews
There are no reviews yet.