PitchLens-AI is a full-stack web application that analyzes startup pitch decks and generates actionable insights for venture capitalists. It extracts key sections (Team, Market, Product/Traction) from uploaded PDFs, enriches them with dummy public data, and uses AI to produce detailed analyses (summary, SWOT, risks).
- Frontend: ReactJS
- Backend: FastAPI (Python)
- Database: MongoDB
- AI: Hugging Face Models (BART for summarization, DistilGPT-2 for risk generation)
Prerequisites
- Node.js (v18+)
- Python 3.9+
- MongoDB Atlas account (cloud database)
- Git
Installation
- Clone the Repository:
git clone https://github.com/mdkamranalam/PitchLens-AI.git
cd PitchLens-AI- Frontend Setup:
- Navigate to the frontend diractory:
cd frontend- Install dependencies:
npm install- Start the developmetn server:
npm run dev- Access at http://localhost:5173.
- Backend Setup:
- Navigate to the backend diractory:
cd backend- Create and activate a virtual environment:
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate- Install dependencies:
pip install -r requirements.txt- Start the FastAPI server:
uvicorn main:app --reload- Access API docs at http://localhost:8000/docs.
- Database Setup with MongoDB Atlas:
- Create a
.envfile inbackend/
MONGO_URI=mongodb+srv://pitchlens_user:<password>@cluster0.mongodb.net/pitchlens?retryWrites=true&w=majority
HF_TOKEN=your_huggingface_api_token_here
FRONTEND_URL=http://localhost:5173
NOTE: There is .env.example is available in both frontend/ and backend/. You can refer this example for your .env/ files.