Talking Terry

A hands-free phone that can answer any question powered by GPT-4, LangChain, and APIs from SerpAPI, Yelp, Twilio, and more!

Key Features

Answers any question!
Utilizes APIs from SerpAPI, Yelp, Twilio, BruinLearn/Canvas, and Weather API for retrieval-augmented geneneration and to ensure accuracy
Built with Raspberry Pi, GPS module, microphone, and a speaker
Saves every conversation to Google Cloud Platform
Portable and convenient to use
Remembers and references past conversations

How To Use

To clone and run this application, you'll need Git, Python, OpenAI, Google Cloud CLI, pip, and LangChain installed on your computer. From your command line:

# Clone this repository
$ git clone https://github.com/tranbrandon1233/TalkingTerry

# Go into the repository
$ cd TalkingTerry

# Install requirements
$ pip install -r requirements.txt

# Install Google Cloud CLI (if necessary)
$ (New-Object Net.WebClient).DownloadFile("https://dl.google.com/dl/cloudsdk/channels/rapid/GoogleCloudSDKInstaller.exe", "$env:Temp\GoogleCloudSDKInstaller.exe")

& $env:Temp\GoogleCloudSDKInstaller.exe
  
# Initialize gcloud
$ gcloud init

# Complete authentication
$ gcloud auth application-default login

# Run the app
$ python transcribe.py

Credits

This software uses the following packages: