MediMentor AI is an advanced educational assistant designed to provide accurate, accessible information on medical topics.
To empower medical education by offering an intelligent, user-friendly resource for students, healthcare professionals, and medical enthusiasts.
- Focused on medical education topics
- Clear explanations of complex concepts
- Adaptive learning based on user knowledge level
- Encourages further exploration in medicine
Covers a wide range of medical education topics including anatomy, physiology, pathology, diagnostics, treatments, and healthcare systems.
- For educational purposes only
- Not for personal medical advice
- Consult healthcare professionals for health concerns
We welcome user feedback to continuously improve MediMentor AI.
MediMentor AI is an educational tool and not a substitute for professional medical advice or treatment.
-
User prompts Baatcheet.
-
Frontend (optional): Preprocesses prompt.
-
Frontend sends prompt + history to Gemini API.
-
Backend (Gemini): Processes prompt & history, generates response.**
-
Backend sends response to Frontend.
-
Frontend displays response.
-
Backend stores prompt & response in Internet Computer canister.
Benefits:
- Improved context for future interactions.
- Personalized experience based on chat history.
- Ability to resume conversations from past points.
To learn more before you start working with baatcheet, see the following documentation available online:
Before you begin, ensure you have met the following requirements:
-
dfx: You have installed the latest version of the DFINITY Canister SDK,
dfx
. You can download it from the DFINITY SDK page. installation guide -
Node.js: You have installed Node.js, version 18 or above.
Please ensure all these prerequisites are met before proceeding with the setup of the project.
Local Development with Gemini and Content Security Policy (CSP)
Important: When deploying this frontend locally and attempting to interact with the Gemini generative language model API, you may encounter errors due to Content Security Policy (CSP) restrictions.
For seamless local interaction with frontend and AI, we strongly recommendusing the Vite development server
. Vite handles CORS (Cross-Origin Resource Sharing) issues, allowing you to interact with Gemini without modifying the CSP.
If you want to test your project locally, you can use the following commands:
Cloning repo:
git clone https://github.com/ahdrahees/baatcheet.git
cd baatcheet
chmod +x deploy-local.sh
./deploy-local.sh
You will see a URL in terminal example
http://localhost:3000/
from vite. And you can open this URL in Browser and start interacting with MediMentor AI
# Installing Dependencies
npm i
# Starts the replica, running in the background
dfx start --background
# Deploys your Backend canisters to the replica and generates your candid interface
dfx deploy backend
#Deploy intenet idenity canister
dfx deploy internet_identity
Once the job completes, your application will be available at http://localhost:8080?canisterId={asset_canister_id}
.
If you have made changes to your backend canister, you can generate a new candid interface with
npm run generate
at any time. This is recommended before starting the frontend development server, and will be run automatically any time you run dfx deploy
.
If you are making frontend changes, you can start a development server with
npm start
You will see a URL in terminal example http://localhost:3000/
from vite. And you can open this URL in Browser and start interacting with MediMentor AI