n8n Intelligent FAQ Telegram Bot with Google Gemini and Supabase

This n8n workflow creates an intelligent FAQ Telegram bot that leverages Google Gemini for AI-powered responses and Supabase for knowledge base storage. It allows users to ask questions in Telegram, and the bot will provide answers based on the stored information and Gemini's conversational capabilities.

What it does

This workflow automates the following steps:

1. Listens for Telegram Messages: It acts as a Telegram bot, listening for incoming messages from users.
2. Processes User Input: When a message is received, it extracts the user's query.
3. Routes Messages: It includes a conditional logic to potentially filter or route messages based on certain criteria (though the current JSON doesn't specify the exact conditions, it provides the framework).
4. Prepares Data for AI Agent: It transforms the incoming data into a format suitable for the AI agent.
5. Engages AI Agent: It uses an AI Agent (powered by LangChain) to process the user's query. This agent is configured with a Google Gemini Chat Model.
6. Retrieves Information from Supabase: The AI Agent is likely configured to use Supabase as a tool to retrieve relevant FAQ answers or knowledge base entries.
7. Generates AI Response: Google Gemini, via the AI Agent, generates a conversational response based on the user's query and the information retrieved from Supabase.
8. Sends Response to Telegram: Finally, the generated AI response is sent back to the user in the Telegram chat.

Prerequisites/Requirements

To use this workflow, you will need:

• n8n Instance: A running instance of n8n.
• Telegram Bot Token: A Telegram bot token obtained from BotFather.
• Google Gemini API Key: An API key for Google Gemini (or Google Cloud project configured for Gemini access).
• Supabase Project: A Supabase project with a database table containing your FAQ data.
• n8n LangChain Nodes: Ensure the @n8n/n8n-nodes-langchain package is installed in your n8n instance for the AI Agent and Google Gemini Chat Model nodes.

Setup/Usage

1. Import the Workflow:

   • Download the provided JSON file.
   • In your n8n instance, go to "Workflows" and click "New".
   • Click the three dots in the top right corner and select "Import from JSON".
   • Paste the JSON content or upload the file.

2. Configure Credentials:

   • Telegram Trigger: Configure the "Telegram Trigger" node (Node ID: 50) with your Telegram Bot API credentials.
   • Telegram: Configure the "Telegram" node (Node ID: 49) with the same Telegram Bot API credentials.
   • Google Gemini Chat Model: Configure the "Google Gemini Chat Model" node (Node ID: 1262) with your Google Gemini API key.
   • Supabase: Configure the "Supabase" node (Node ID: 545) with your Supabase credentials (Project URL and Anon Key).

3. Configure Supabase Data:

   • Ensure your Supabase project has a table (e.g., faqs) with columns that the AI Agent can query to find answers. Common columns might be question and answer.

4. Configure AI Agent:

   • The "AI Agent" node (Node ID: 1119) will need to be configured to use the "Google Gemini Chat Model" and the "Supabase" node as a tool. You'll define how the agent should interact with Supabase to retrieve information (e.g., by providing a description of the Supabase tool and its capabilities).

5. Activate the Workflow:

   • Once all credentials and configurations are set, activate the workflow by toggling the "Active" switch in the top right corner of the workflow editor.

Your intelligent FAQ Telegram bot should now be ready to answer questions!