SnapSnack is a food recognition chatbot that uses Twilio to receive image messages and OpenAI to recognize the food item. The chatbot then retrieves the nutritional information for the food item using the USDA API and responds with a summary of the information.

To run this project, you will need the following:

• Twilio Account and Phone Number
• OpenAI Account
• USDA API Key
• Google Cloud Account

To get started, clone the repository to your local machine:

git clone https://github.com/your-username/food-recognition-chatbot.git
cd food-recognition-chatbot

Create a .env file in the project directory and add your Twilio and OpenAI credentials and your USDA API key as environment variables. For example:

python -m venv venv
source venv/bin/activate  # for Mac/Linux
.\venv\Scripts\activate  # for Windows

Download the Google Cloud Vision API JSON file as cloud.json and place it in the project directory.

Create a virtual environment for the project and activate it:

Copy code
python -m venv venv
source venv/bin/activate  # for Mac/Linux
.\venv\Scripts\activate  # for Windows

Install the required Python packages using pip:

pip install -r requirements.txt

Run the app with the following command:

python app.py

This will start a local server on localhost with debug mode enabled and listening on port 8080. You should see output in the terminal indicating that the server is running.

In another terminal window, run the following command to set up ngrok:

ngrok http 8080

This command will create a public URL that tunnels to your locally running app on port 8080.

In the Twilio console, add the forwarding URL generated by ngrok as a webhook when "A Message Comes In". Remember to add /detect_food to the back of the webhook link.

Send a picture of a food item to the Twilio number and the chatbot will respond with the nutritional information for the food item.

To use the chatbot, send an image message of a food item to your Twilio number. The chatbot will respond with a summary of the nutritional information for the food item, including the calories, fat content, protein content, and carbohydrate content.

This project is licensed under the MIT License. See the LICENSE file for more information.

This project was built using the following software and libraries:

• Twilio
• OpenAI API
• USDA API
• Google Cloud Vision API