mrutunjay-kinagi/ragsearch

This project aims to build a Retrieval-Augmented Generation (RAG) engine to provide context-aware recommendations based on user queries.

40
/ 100
Emerging

Supports multiple data input formats (CSV, JSON, Parquet) and integrates with Cohere for embeddings alongside dual vector storage backends—FAISS for in-memory performance or ChromaDB for persistent SQLite-backed search. Built as a Python library with Flask-based web UI, targeting natural language queries over structured datasets with configurable embedding and retrieval pipelines.

No commits in the last 6 months. Available on PyPI.

Stale 6m
Maintenance 2 / 25
Adoption 7 / 25
Maturity 18 / 25
Community 13 / 25

How are scores calculated?

Stars

3

Forks

2

Language

Python

License

MIT

Category

local-rag-stacks

Last pushed

Sep 07, 2025

Monthly downloads

37

Commits (30d)

0

Dependencies

10

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/mrutunjay-kinagi/ragsearch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.