n8n Telegram Fitness Bot: Custom Workout Plans from Photo/Text using Gemini AI

This n8n workflow automates the generation of custom workout plans based on user input via Telegram. Users can send a photo or text description of their current fitness level or desired workout, and the workflow leverages Google Gemini AI to create a personalized plan, which is then sent back to the user on Telegram.

What it does

1. Listens for Telegram Messages: The workflow is triggered whenever a new message is received in a configured Telegram bot.
2. Identifies Input Type: It checks if the incoming Telegram message contains a photo or a text message.
3. Processes Photo Input (if applicable): If a photo is provided, it downloads the photo from Telegram.
4. Generates Workout Plan with Gemini AI:
   • It uses a Google Gemini AI agent to analyze the user's input (either the text message or the photo and a default prompt).
   • A simple memory is used to maintain context within the conversation.
   • An HTTP Request node is used to fetch the image data if a photo was sent.
   • A Code node processes the incoming message and prepares it for the AI agent, potentially formulating a prompt based on the image or text.
5. Sends Workout Plan to Telegram: The generated workout plan from the AI agent is sent back to the user via Telegram.

Prerequisites/Requirements

• n8n Instance: A running n8n instance.
• Telegram Bot: A Telegram bot token and chat ID. You'll need to create a bot via BotFather on Telegram.
• Google Gemini API Key: Access to the Google Gemini API for generating workout plans. This will be configured as a credential in the "Google Gemini Chat Model" node.
• Google Gemini Credential: An n8n credential for Google Gemini.

Setup/Usage

1. Import the Workflow:
   • Copy the provided JSON code.
   • In your n8n instance, click "New" in the workflows sidebar.
   • Click "Import from JSON" and paste the workflow JSON.
2. Configure Telegram Trigger:
   • Click on the "Telegram Trigger" node.
   • Select or create a new Telegram API credential. You will need your Telegram Bot Token.
   • Ensure the "Updates" field is set to listen for "Message" events.
3. Configure Telegram Node:
   • Click on the "Telegram" node.
   • Select the same Telegram API credential used in the trigger.
   • Set the "Chat ID" to {{ $json.chat.id }} to reply to the user who sent the message.
   • Set the "Text" field to display the AI-generated workout plan (e.g., {{ $json.response }}).
4. Configure Google Gemini Chat Model:
   • Click on the "Google Gemini Chat Model" node.
   • Select or create a new Google Gemini API credential using your API Key.
   • Ensure the "Model" is set to an appropriate Gemini model (e.g., gemini-pro).
5. Configure Google Gemini Node:
   • Click on the "Google Gemini" node.
   • Select the same Google Gemini API credential.
6. Activate the Workflow:
   • Once all credentials are set up and nodes are configured, click the "Activate" toggle in the top right corner of the n8n editor to start the workflow.

Now, when you send a message or a photo to your Telegram bot, it should respond with a custom workout plan!