Skip to content

jogoldberg/swg

 
 

Repository files navigation

Swg

 

Solve With Google - Healthcare Assistant Chatbot

Github top language Github language count Repository size License

About   |   Technologies   |   Requirements   |   Starting   |   License   |   Author


🎯 About

Using Google Gemini, a family of large language models from Google DeepMind, known for its ability to understand and respond to different kinds of information, we will create a ChatBot to serve as a Virtual Assistant during the patient’s care journey

🚀 Technologies

The following tools were used in this project:

✅ Requirements

Before starting 🏁, you need to have Python, Chainlit and GCloud CLI installed.

🏁 Starting

1. Make sure that you have docker installed.

2. Login to google gloud and setup the projrct. Make sure that Vertex AI is enabled.

gcloud auth application-default login
gcloud config set project <PROJECT_ID>

3. Create a .env file and add the following env varibales

OPENAI_API_KEY=sk-<***************************>
QDRANT_URL=http://localhost:6333

Then run the script

chmod +x run.sh 
./run.sh

The Script will do the following

  • Run Qdrant Database in case its not running
  • Install the requirements
  • extract the content of the PDF file in pdfInput folder and upload it to qdrant.
  • extract the content of the text file in Pdata Folder.
  • start the chatbot application
  • The page is available in http://localhost:8000

📝 License

This project is under license from MIT. For more details, see the LICENSE file.

Authors

Made with ❤️ by Deloitte Consulting BV -- Amsterdam, Netherlands

Authors: Shyam Sundar, Joshua Goldberg, Wouter ten Brink, Gino Arcangeli

 

Back to top

About

Solve With Google Bot

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 84.3%
  • Shell 15.7%