Skip to content

Repository files navigation

Sameekshak AI - Freight Compliance & Audit Pipeline

An intelligent document processing application built with FastAPI, React, SQLite, and Google Gemini API to analyze, log, validate, and prune freight compliance documents.

🛠️ Tech Stack

  • 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)

🚀 Local Deployment Setup

1. Backend Service Configuration

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

About

Sameekshak AI combines two brains: **Brain A (ML Engine)** extracts invoices, predicts costs, detects anomalies, and scores fraud risk with SHAP transparency, while **Brain B (RAG Engine)** ingests contracts, stores embeddings, checks compliance, and auto‑drafts clause‑citing dispute emails—delivering explainable, automated freight risk management.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages