Library / Documents, PDF & OCR
Documents, PDF & OCR
Read Text from Telegram Images with Gemini OCR
When an image is sent to Telegram, the workflow downloads it, runs Gemini OCR and replies with the extracted text.
What it does
## HTTP Gemini OCR Setting Define Gemini Model on URL https://generativelanguage.googleapis.com/v1beta/models/[Gemini Model]:generateContent example: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent ... Authentication Generic Credential Type Generic Auth Type Query Auth Query Auth + Create new credential (take if from https://aistudio.google.com/) ... Body Content Type JSON Specify Body Using JSON JSON { "contents": [ { "role": "user", "parts": [ { "inlineData": { "mimeType": "image/jpeg", "data": "{{ $json.data }}" } }, { "text": "Extract text" } ] } ] }
The steps
- Telegram Trigger
- Clean Input Data
- get file
- Telegram
- Gemini OCR
- Extract from File
Similar automations
Documents, PDF & OCRRead Text from Telegram Images with Gemini OCR8 stepsDocuments, PDF & OCRExtract Text from a Local PDF File3 stepsDocuments, PDF & OCRExtract text from Google Drive PDFs and images with Gemini into CSV12 stepsDocuments, PDF & OCRExtract text from PDFs and images into CSV with Gemini and Google Drive12 steps