An intelligent document processing application built with FastAPI, React, SQLite, and Google Gemini API to analyze, log, validate, and prune freight compliance documents.
- Frontend: React, Tailwind CSS, Vite
- Backend: FastAPI, Python ThreadPoolExecutor Async Workers
- Database: SQLite3 (Relational Persistence Layer)
- Engines:
pdfplumber(Regex Parsing) + Google Gemini 2.5 Flash (VLM Multi-Modal API Ingestion)
Ensure you are running Python 3.11+. Move into the project directory, initialize your environment variables, and boot the API server:
# Navigate to the workspace and activate virtual environment
cd "Sameekshak AI"
python -m venv venv
source venv/Scripts/activate # Windows: .\venv\Scripts\Activate.ps1
# Install required architecture dependencies
pip install -r requirements.txt
# Configure your Gemini Authentication Token
export GEMINI_API_KEY="AIzaSyYourSecretAPIKey" # PowerShell: $env:GEMINI_API_KEY="AIzaSy..."
# Start the Uvicorn Hot-Reload Development Engine
uvicorn app.main:app --reload --port 8000