https://github.com/khushneetsingh/datasanity

DataSanity is a AI-powered web application for dataset cleaning, synthetic data generation, vectorization, and data enrichment using natural language prompts.
https://github.com/khushneetsingh/datasanity

cerebrus exa faiss-vector-database llm nextjs numpy pandas serperdev sqlite tailwindcss

Last synced: 4 months ago
JSON representation

DataSanity is a AI-powered web application for dataset cleaning, synthetic data generation, vectorization, and data enrichment using natural language prompts.

• Host: GitHub
• URL: https://github.com/khushneetsingh/datasanity
• Owner: KhushneetSingh
• License: apache-2.0
• Created: 2025-10-05T20:48:20.000Z (4 months ago)
• Default Branch: main
• Last Pushed: 2025-10-05T22:15:58.000Z (4 months ago)
• Last Synced: 2025-10-05T23:28:34.613Z (4 months ago)
• Topics: cerebrus, exa, faiss-vector-database, llm, nextjs, numpy, pandas, serperdev, sqlite, tailwindcss
• Language: JavaScript
• Homepage:
• Size: 10.3 MB
• Stars: 0
• Watchers: 0
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# DataSanity

An AI-powered web application for dataset cleaning, synthetic data generation, vectorization, and data enrichment using natural language prompts.

## Features

- Dataset cleaning with LLM detection of noisy, missing, or duplicate values

- Synthetic data generation based on schema or prompt

- Vectorization for RAG pipelines

- Data enrichment using web search APIs

- Natural language prompt-based workflow

- Support for CSV uploads and downloads

## Tech Stack

- Frontend: Next.js with Tailwind CSS

- Backend: FastAPI (Python)

- LLM Inference: Cerebras API

- Data Processing: pandas, numpy

- Embedding: sentence-transformers

- Vector Store: FAISS

- Web Search: Exa or Serper.dev

- Storage: SQLite + local filesystem