LangChain Appointment Booking Chatbot

A demo project showcasing how to build an appointment booking chatbot using Python, LangChain, MCP, the Google Gemini API, Gradio, Pipedream, and Google Calendar.

Prerequisites

Before you begin, ensure you have the following:

• Python 3.8 or higher

Setting Up the Google API Key for Gemini

For detailed instructions on obtaining a Google API key to use Gemini in this demo, please refer to Google's official documentation:

• Getting Started with Gemini API

Enabling the Google Calendar API

To use the Google Calendar API, you will need to enable it. For detailed instructions on how to do this, please refer to the Google Calendar API Quickstart Guide.

Setting Up Pipedream

For this example, you will need to sign up for a free Pipedream account and connect your Google Calendar to it. Please follow the instructions below to get your Pipedream URL:

1. Sign up for a Pipedream account Sign up for a free account on Pipedream.

2. Connect Google Calendar to Pipedream Follow the instructions on Pipedream's Google Calendar MCP page to connect your Google Calendar to Pipedream.

3. Get your Pipedream URL After connecting your Google Calendar to Pipedream copy the MCP server URL under Configuration: Pipedream's Google Calendar MCP page

Running the Demo

1. Clone the repository

   git clone <repository-url>
   cd langchain-appointment-booking-demo
   

2. Create and activate a virtual environment (recommended)

   python -m venv .venv
   source .venv/bin/activate
   

3. Install dependencies

   pip install -r requirements.txt
   

4. Set up environment variables Copy the .env.example file to a .env file in the project root and replace the placeholders with your actual Google API key and Pipedream URL.

Running the Application

1. Start the chatbot

   python app.py
   

2. Access the web interface Open your web browser and navigate to the URL shown in the terminal (typically http://localhost:7860)

How to Use

Sample conversation starters:

• "Hi, I'd like to book a dental appointment"
• "When is my next appointment?"
• "Can you reschedule my upcoming appointment?"
• "Let's cancel my appointment"

Customization

Modifying the Prompt

You can customize the chatbot's behavior by editing the prompt variable in app.py. The current prompt includes instructions for handling appointments, but you can modify it to suit your specific needs.

Changing the AI Model

To use a different model from Google's Gemini API, modify the model name in the ChatGoogleGenerativeAI initialization in app.py.