MyAnswer 🎤

MyAnswer is a web application designed to facilitate remote examinations and assessments. It allows teachers to create tests, students to participate in exams, and provides automated evaluation and feedback using Google Cloud Vertex AI utilizing the Gemini 1.5x model.

Features

Teacher Dashboard: Create tests, manage questions, and review student submissions.
Student Dashboard: Join exams using a unique code, answer questions, and receive instant feedback.
Automated Evaluation: Automatically evaluates student responses, providing scores and detailed feedback.
Speech-to-Text Integration: Enables students to answer questions using speech input, which is converted to text for evaluation.
Text-to-Speech Integration: Provides audio feedback for students' answers and exam results.
Secure Authentication: Uses Firebase Authentication for secure user authentication and data management.

Technologies Used

Vertex AI: A managed machine learning (ML) platform provided by Google Cloud, used for generative models for text comparison and feedback generation.
Pyrebase: A Python wrapper for the Firebase platform, providing tools and services for building web and mobile applications.
Google Cloud Speech-to-Text (STT): A service that converts speech into text for further processing and analysis.
Streamlit: A Python library for building interactive web applications with simple Python scripts.
gTTS (Google Text-to-Speech): A Python library and CLI tool to interface with Google Translate's text-to-speech API.

Installation

Prerequisites

Basic knowledge of Python and web development.
A Google Cloud account.
Installed software: Python 3.12, Docker

Setting Up Firebase

Create a Firebase Project: Go to the Firebase Console and create a new project.

Firebase Configuration: Update the firebaseConfig dictionary in the app code with your Firebase project credentials:

firebaseConfig = {
    'apiKey': "YOUR_API_KEY",
    'authDomain': "YOUR_AUTH_DOMAIN",
    'projectId': "YOUR_PROJECT_ID",
    'storageBucket': "YOUR_STORAGE_BUCKET",
    'messagingSenderId': "YOUR_MESSAGING_SENDER_ID",
    'appId': "YOUR_APP_ID",
    'measurementId': "YOUR_MEASUREMENT_ID",
    'databaseURL': 'YOUR_DATABASE_URL'
}

Initialize Firebase: Ensure Firebase is initialized in the application code.

Setting Up Vertex AI SDK

Enable Vertex AI API: In the Google Cloud Console, enable the Vertex AI API for your project.
Install Vertex AI SDK: Install the Vertex AI SDK on your local machine:
```
pip install google-cloud-aiplatform
```

Initialize Vertex AI: Add the initialization code in your application:

import vertexai

vertexai.init(project="YOUR_PROJECT_ID", location="YOUR_LOCATION")

Running Locally

Clone this repository to your local machine:

git clone https://github.com/jebinshaju/myanswer.git
cd myanswer

Install the required dependencies:
```
pip install -r requirements.txt
```
Run the Streamlit application:
```
streamlit run app.py
```

Deployment

Dockerizing the Application

Create a Dockerfile: Add the Dockerfile to the root of your project:
Build the Docker Image:
```
docker build -t myanswer .
```

Deploying on Google Cloud Run

Follow these steps to deploy the application on Google Cloud Run:

Set Up Environment Variables:

GCP_PROJECT='your-gcp-project-id'
GCP_REGION='your-region'
AR_REPO='myanswer-repo'
SERVICE_NAME='myanswer'

Create Artifact Registry:

gcloud artifacts repositories create "$AR_REPO" --location="$GCP_REGION" --repository-format=Docker

Submit Build to Cloud Build:

gcloud builds submit --tag "$GCP_REGION-docker.pkg.dev/$GCP_PROJECT/$AR_REPO/$SERVICE_NAME"

Deploy to Cloud Run:

gcloud run deploy "$SERVICE_NAME" \
   --port=8080 \
   --image="$GCP_REGION-docker.pkg.dev/$GCP_PROJECT/$AR_REPO/$SERVICE_NAME" \
   --allow-unauthenticated \
   --region=$GCP_REGION \
   --platform=managed \
   --project=$GCP_PROJECT \
   --set-env-vars=GCP_PROJECT=$GCP_PROJECT,GCP_REGION=$GCP_REGION

Usage

Teacher Login: Teachers can log in using their credentials to access the dashboard.
Teacher Dashboard: Create a new test by providing the test name, questions, and correct answers.
Student Login: Students log in using their credentials or sign up if they are new users.
Student Dashboard: Enter the examination code provided by the teacher to start the exam.
Answer Questions: Students can answer questions using text input or speech-to-text.
Submit Answers: Submit the answers once completed to receive instant feedback and scores.

Live Site

The application is live and accessible at: MyAnswer Live Site

License

This project is licensed under the MIT License.