ResurrectAI is an AI-driven chat application designed to bring the wisdom and knowledge of great historical personalities to life. Leveraging advanced language models and fine-tuning techniques, ResurrectAI enables users to interact with AI avatars of iconic figures, gaining access to their insights, guidance, and philosophical teaching in realtime
ResurrectAI is a project designed to bring great historical personalities to life through their wisdom by creating a chat application where users can interact with these personalities and seek guidance on almost any topic. The app functions as a 24/7 buddy offering advice in various situations.
app.py
) requires a Linux machine to run.app.py
).Clone the Repository:
git clone https://github.com/harshit0414/resurrectai.git
cd resurrectai
Create a Virtual Environment:
python3 -m venv venv
source venv/bin/activate # Linux
Install Dependencies:
Install the required packages using the requirements.txt
file:
pip install -r requirements.txt
Install Unsloth and Additional Libraries: Run the following commands to install Unsloth and other dependencies required for both the Flask app and the Jupyter notebooks:
pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
pip install --no-deps xformers trl peft accelerate bitsandbytes triton
app.py
)Start the Flask Application:
python app.py
Access the Web Interface:
Once the application is running, open your browser and navigate to http://localhost:5000
to interact with the AI model.
Example: Screenshot showing the ResurrectAI web interface.
If you do not have a Linux machine, you can use the provided Jupyter notebooks:
Training the Model:
Open the ResurrectAI_Training.ipynb
notebook in Jupyter and follow the steps to train the AI model.
Example: Screenshot showing the training process in Jupyter.
Running Inference:
Use the ResurrectAI_Inference.ipynb
notebook to run inference and interact with the model in a non-Linux environment.
To allow users to download and use the ResurrectAI Flutter app with their own Firebase project, follow these steps:
Set up a Firebase Project:
Modify google-services.json
(Android) or GoogleService-Info.plist
(iOS):
google-services.json
(for Android) or GoogleService-Info.plist
(for iOS) file from your Firebase console.android/app/
for Android (google-services.json
)ios/Runner/
for iOS (GoogleService-Info.plist
)Install Firebase SDK: Ensure you have the necessary Firebase packages installed in your Flutter project by following the official Firebase documentation for Flutter: Firebase for Flutter.
flutter pub add firebase_core
flutter pub add firebase_auth
# Add other Firebase packages as needed
Initialize Firebase in Flutter:
In your main.dart
, initialize Firebase before running the app:
void main() async {
WidgetsFlutterBinding.ensureInitialized();
await Firebase.initializeApp();
runApp(MyApp());
}
The Flutter application is developed but not yet connected to the AI model for interactivity. Once connected, instructions for using the mobile app will be provided in future updates.
Example: Screenshot showing Android Application developed in Flutter.
If you'd like to contribute to ResurrectAI, feel free to fork the repository, make your changes, and submit a pull request. Ensure that your code adheres to the projects coding standards.
For any queries or support, please contact [email protected] or open an issue in the repository.