π Mindstride is a RAG-based chat assistant designed to support mental health, personal growth, and self-improvement. This project leverages advanced AI technologies to provide a personalized and insightful experience, drawing from the wisdom of over 70 books on mental well-being, personal development, and self-discovery.
- Mental Health Support: Offers guidance and support for enhancing mental well-being.
- Personal Growth: Assists users on their journey towards personal development.
- Self-Improvement: Provides tools and insights for self-discovery and improvement.
- Backend: FastAPI
- Vector Database: Pinecone
- Embeddings: Generated from 70+ books on relevant topics
- Langchain: For managing and querying text chains
- APIs:
- OpenAI API: Queries using GPT-3.5
- Hugging Face Inference API: For creating embeddings
- Infrastructure: Hosted on AWS Lambda
- Clone the repository:
git clone https://github.com/debankanmitra/GenaiAssistant.git cd backend
- Set up a virtual environment:
python3 -m venv venv source venv/bin/activate
- Install the dependencies:
pip install -r requirements.txt
- Configure environment variables for Pinecone, OpenAI API, and Hugging Face Inference API keys.
- Start the FastAPI server:
uvicorn main:app --reload
Mindstride is licensed under the MIT License.